andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-05-02 15:52:34 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

refactor: extract files module to standalone crewai-files package

Browse Source
This commit is contained in:
Greyson LaLonde
2026-01-22 15:06:20 -05:00
parent a064b84ead
commit b95a3a9bc8
62 changed files with 639 additions and 582 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
lib/crewai/pyproject.toml
View File

@@ -99,13 +99,7 @@ a2a = [
"aiocache[redis,memcached]~=0.12.3",
]
file-processing = [
"Pillow~=10.4.0",
"pypdf~=4.0.0",
"python-magic>=0.4.27",
"aiocache~=0.12.3",
"aiofiles~=24.1.0",
"tinytag~=1.10.0",
"av~=13.0.0",
"crewai-files",
]
@@ -133,6 +127,7 @@ torchvision = [
{ index = "pytorch-nightly", marker = "python_version >= '3.13'" },
{ index = "pytorch", marker = "python_version < '3.13'" },
]
crewai-files = { workspace = true }
[build-system]

9
lib/crewai/src/crewai/__init__.py
View File

@@ -3,10 +3,7 @@ from typing import Any
import urllib.request
import warnings
from crewai.agent.core import Agent
from crewai.crew import Crew
from crewai.crews.crew_output import CrewOutput
from crewai.files import (
from crewai_files import (
AudioFile,
File,
ImageFile,
@@ -14,6 +11,10 @@ from crewai.files import (
TextFile,
VideoFile,
)
from crewai.agent.core import Agent
from crewai.crew import Crew
from crewai.crews.crew_output import CrewOutput
from crewai.flow.flow import Flow
from crewai.knowledge.knowledge import Knowledge
from crewai.llm import LLM

6
lib/crewai/src/crewai/agents/crew_agent_executor.py
View File

@@ -10,6 +10,7 @@ from collections.abc import Callable
import logging
from typing import TYPE_CHECKING, Any, Literal, cast
from crewai_files import FileProcessor
from pydantic import BaseModel, GetCoreSchemaHandler, ValidationError
from pydantic_core import CoreSchema, core_schema
@@ -24,7 +25,6 @@ from crewai.events.types.logging_events import (
AgentLogsExecutionEvent,
AgentLogsStartedEvent,
)
from crewai.files import FileProcessor
from crewai.hooks.llm_hooks import (
get_after_llm_call_hooks,
get_before_llm_call_hooks,
@@ -238,7 +238,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
processor = FileProcessor(constraints=provider)
files = processor.process_files(files)
from crewai.files import get_upload_cache
from crewai_files import get_upload_cache
upload_cache = get_upload_cache()
content_blocks = self.llm.format_multimodal_content(
@@ -280,7 +280,7 @@ class CrewAgentExecutor(CrewAgentExecutorMixin):
processor = FileProcessor(constraints=provider)
files = await processor.aprocess_files(files)
from crewai.files import get_upload_cache
from crewai_files import get_upload_cache
upload_cache = get_upload_cache()
content_blocks = await self.llm.aformat_multimodal_content(

7
lib/crewai/src/crewai/crews/utils.py
View File

@@ -6,15 +6,16 @@ import asyncio
from collections.abc import Callable, Coroutine, Iterable
from typing import TYPE_CHECKING, Any
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.crews.crew_output import CrewOutput
from crewai.files import (
from crewai_files import (
AudioFile,
ImageFile,
PDFFile,
TextFile,
VideoFile,
)
from crewai.agents.agent_builder.base_agent import BaseAgent
from crewai.crews.crew_output import CrewOutput
from crewai.rag.embeddings.types import EmbedderConfig
from crewai.types.streaming import CrewStreamingOutput, FlowStreamingOutput
from crewai.utilities.file_store import store_files

145
lib/crewai/src/crewai/files/__init__.py
View File

@@ -1,145 +0,0 @@
"""File handling utilities for crewAI tasks."""
from crewai.files.cleanup import (
cleanup_expired_files,
cleanup_provider_files,
cleanup_uploaded_files,
)
from crewai.files.content_types import (
AudioExtension,
AudioFile,
AudioMimeType,
BaseFile,
File,
FileInput,
FileMode,
ImageExtension,
ImageFile,
ImageMimeType,
PDFContentType,
PDFExtension,
PDFFile,
TextContentType,
TextExtension,
TextFile,
VideoExtension,
VideoFile,
VideoMimeType,
)
from crewai.files.file import (
FileBytes,
FilePath,
FileSource,
FileSourceInput,
FileStream,
FileUrl,
RawFileInput,
)
from crewai.files.processing import (
ANTHROPIC_CONSTRAINTS,
BEDROCK_CONSTRAINTS,
GEMINI_CONSTRAINTS,
OPENAI_CONSTRAINTS,
AudioConstraints,
FileHandling,
FileProcessingError,
FileProcessor,
FileTooLargeError,
FileValidationError,
ImageConstraints,
PDFConstraints,
ProcessingDependencyError,
ProviderConstraints,
UnsupportedFileTypeError,
VideoConstraints,
get_constraints_for_provider,
)
from crewai.files.resolved import (
FileReference,
InlineBase64,
InlineBytes,
ResolvedFile,
ResolvedFileType,
UrlReference,
)
from crewai.files.resolver import (
FileResolver,
FileResolverConfig,
create_resolver,
)
from crewai.files.upload_cache import (
CachedUpload,
UploadCache,
get_upload_cache,
reset_upload_cache,
)
from crewai.files.uploaders import FileUploader, UploadResult, get_uploader
from crewai.files.utils import normalize_input_files, wrap_file_source
__all__ = [
"ANTHROPIC_CONSTRAINTS",
"BEDROCK_CONSTRAINTS",
"GEMINI_CONSTRAINTS",
"OPENAI_CONSTRAINTS",
"AudioConstraints",
"AudioExtension",
"AudioFile",
"AudioMimeType",
"BaseFile",
"CachedUpload",
"File",
"FileBytes",
"FileHandling",
"FileInput",
"FileMode",
"FilePath",
"FileProcessingError",
"FileProcessor",
"FileReference",
"FileResolver",
"FileResolverConfig",
"FileSource",
"FileSourceInput",
"FileStream",
"FileTooLargeError",
"FileUploader",
"FileUrl",
"FileValidationError",
"ImageConstraints",
"ImageExtension",
"ImageFile",
"ImageMimeType",
"InlineBase64",
"InlineBytes",
"PDFConstraints",
"PDFContentType",
"PDFExtension",
"PDFFile",
"ProcessingDependencyError",
"ProviderConstraints",
"RawFileInput",
"ResolvedFile",
"ResolvedFileType",
"TextContentType",
"TextExtension",
"TextFile",
"UnsupportedFileTypeError",
"UploadCache",
"UploadResult",
"UrlReference",
"VideoConstraints",
"VideoExtension",
"VideoFile",
"VideoMimeType",
"cleanup_expired_files",
"cleanup_provider_files",
"cleanup_uploaded_files",
"create_resolver",
"get_constraints_for_provider",
"get_upload_cache",
"get_uploader",
"normalize_input_files",
"reset_upload_cache",
"wrap_file_source",
]

373
lib/crewai/src/crewai/files/cleanup.py
View File

@@ -1,373 +0,0 @@
"""Cleanup utilities for uploaded files."""
from __future__ import annotations
import asyncio
import logging
from typing import TYPE_CHECKING
from crewai.files.upload_cache import CachedUpload, UploadCache
from crewai.files.uploaders import get_uploader
if TYPE_CHECKING:
from crewai.files.uploaders.base import FileUploader
logger = logging.getLogger(__name__)
def _safe_delete(
uploader: FileUploader,
file_id: str,
provider: str,
) -> bool:
"""Safely delete a file, logging any errors.
Args:
uploader: The file uploader to use.
file_id: The file ID to delete.
provider: Provider name for logging.
Returns:
True if deleted successfully, False otherwise.
"""
try:
if uploader.delete(file_id):
logger.debug(f"Deleted {file_id} from {provider}")
return True
logger.warning(f"Failed to delete {file_id} from {provider}")
return False
except Exception as e:
logger.warning(f"Error deleting {file_id} from {provider}: {e}")
return False
def cleanup_uploaded_files(
cache: UploadCache,
*,
delete_from_provider: bool = True,
providers: list[str] | None = None,
) -> int:
"""Clean up uploaded files from the cache and optionally from providers.
Args:
cache: The upload cache to clean up.
delete_from_provider: If True, delete files from the provider as well.
providers: Optional list of providers to clean up. If None, cleans all.
Returns:
Number of files cleaned up.
"""
cleaned = 0
provider_uploads: dict[str, list[CachedUpload]] = {}
for provider in _get_providers_from_cache(cache):
if providers is not None and provider not in providers:
continue
provider_uploads[provider] = cache.get_all_for_provider(provider)
if delete_from_provider:
for provider, uploads in provider_uploads.items():
uploader = get_uploader(provider)
if uploader is None:
logger.warning(
f"No uploader available for {provider}, skipping cleanup"
)
continue
for upload in uploads:
if _safe_delete(uploader, upload.file_id, provider):
cleaned += 1
cache.clear()
logger.info(f"Cleaned up {cleaned} uploaded files")
return cleaned
def cleanup_expired_files(
cache: UploadCache,
*,
delete_from_provider: bool = False,
) -> int:
"""Clean up expired files from the cache.
Args:
cache: The upload cache to clean up.
delete_from_provider: If True, attempt to delete from provider as well.
Note: Expired files may already be deleted by the provider.
Returns:
Number of expired entries removed from cache.
"""
expired_entries: list[CachedUpload] = []
if delete_from_provider:
for provider in _get_providers_from_cache(cache):
expired_entries.extend(
upload
for upload in cache.get_all_for_provider(provider)
if upload.is_expired()
)
removed = cache.clear_expired()
if delete_from_provider:
for upload in expired_entries:
uploader = get_uploader(upload.provider)
if uploader is not None:
try:
uploader.delete(upload.file_id)
except Exception as e:
logger.debug(f"Could not delete expired file {upload.file_id}: {e}")
return removed
def cleanup_provider_files(
provider: str,
*,
cache: UploadCache | None = None,
delete_all_from_provider: bool = False,
) -> int:
"""Clean up all files for a specific provider.
Args:
provider: Provider name to clean up.
cache: Optional upload cache to clear entries from.
delete_all_from_provider: If True, delete all files from the provider,
not just cached ones.
Returns:
Number of files deleted.
"""
deleted = 0
uploader = get_uploader(provider)
if uploader is None:
logger.warning(f"No uploader available for {provider}")
return 0
if delete_all_from_provider:
try:
files = uploader.list_files()
for file_info in files:
file_id = file_info.get("id") or file_info.get("name")
if file_id and uploader.delete(file_id):
deleted += 1
except Exception as e:
logger.warning(f"Error listing/deleting files from {provider}: {e}")
elif cache is not None:
uploads = cache.get_all_for_provider(provider)
for upload in uploads:
if _safe_delete(uploader, upload.file_id, provider):
deleted += 1
cache.remove_by_file_id(upload.file_id, provider)
logger.info(f"Deleted {deleted} files from {provider}")
return deleted
def _get_providers_from_cache(cache: UploadCache) -> set[str]:
"""Get unique provider names from cache entries.
Args:
cache: The upload cache.
Returns:
Set of provider names.
"""
return cache.get_providers()
async def _asafe_delete(
uploader: FileUploader,
file_id: str,
provider: str,
) -> bool:
"""Async safely delete a file, logging any errors.
Args:
uploader: The file uploader to use.
file_id: The file ID to delete.
provider: Provider name for logging.
Returns:
True if deleted successfully, False otherwise.
"""
try:
if await uploader.adelete(file_id):
logger.debug(f"Deleted {file_id} from {provider}")
return True
logger.warning(f"Failed to delete {file_id} from {provider}")
return False
except Exception as e:
logger.warning(f"Error deleting {file_id} from {provider}: {e}")
return False
async def acleanup_uploaded_files(
cache: UploadCache,
*,
delete_from_provider: bool = True,
providers: list[str] | None = None,
max_concurrency: int = 10,
) -> int:
"""Async clean up uploaded files from the cache and optionally from providers.
Args:
cache: The upload cache to clean up.
delete_from_provider: If True, delete files from the provider as well.
providers: Optional list of providers to clean up. If None, cleans all.
max_concurrency: Maximum number of concurrent delete operations.
Returns:
Number of files cleaned up.
"""
cleaned = 0
provider_uploads: dict[str, list[CachedUpload]] = {}
for provider in _get_providers_from_cache(cache):
if providers is not None and provider not in providers:
continue
provider_uploads[provider] = await cache.aget_all_for_provider(provider)
if delete_from_provider:
semaphore = asyncio.Semaphore(max_concurrency)
async def delete_one(file_uploader: FileUploader, cached: CachedUpload) -> bool:
"""Delete a single file with semaphore limiting."""
async with semaphore:
return await _asafe_delete(
file_uploader, cached.file_id, cached.provider
)
tasks: list[asyncio.Task[bool]] = []
for provider, uploads in provider_uploads.items():
uploader = get_uploader(provider)
if uploader is None:
logger.warning(
f"No uploader available for {provider}, skipping cleanup"
)
continue
tasks.extend(
asyncio.create_task(delete_one(uploader, cached)) for cached in uploads
)
results = await asyncio.gather(*tasks, return_exceptions=True)
cleaned = sum(1 for r in results if r is True)
await cache.aclear()
logger.info(f"Cleaned up {cleaned} uploaded files")
return cleaned
async def acleanup_expired_files(
cache: UploadCache,
*,
delete_from_provider: bool = False,
max_concurrency: int = 10,
) -> int:
"""Async clean up expired files from the cache.
Args:
cache: The upload cache to clean up.
delete_from_provider: If True, attempt to delete from provider as well.
max_concurrency: Maximum number of concurrent delete operations.
Returns:
Number of expired entries removed from cache.
"""
expired_entries: list[CachedUpload] = []
if delete_from_provider:
for provider in _get_providers_from_cache(cache):
uploads = await cache.aget_all_for_provider(provider)
expired_entries.extend(upload for upload in uploads if upload.is_expired())
removed = await cache.aclear_expired()
if delete_from_provider and expired_entries:
semaphore = asyncio.Semaphore(max_concurrency)
async def delete_expired(cached: CachedUpload) -> None:
"""Delete an expired file with semaphore limiting."""
async with semaphore:
file_uploader = get_uploader(cached.provider)
if file_uploader is not None:
try:
await file_uploader.adelete(cached.file_id)
except Exception as e:
logger.debug(
f"Could not delete expired file {cached.file_id}: {e}"
)
await asyncio.gather(
*[delete_expired(cached) for cached in expired_entries],
return_exceptions=True,
)
return removed
async def acleanup_provider_files(
provider: str,
*,
cache: UploadCache | None = None,
delete_all_from_provider: bool = False,
max_concurrency: int = 10,
) -> int:
"""Async clean up all files for a specific provider.
Args:
provider: Provider name to clean up.
cache: Optional upload cache to clear entries from.
delete_all_from_provider: If True, delete all files from the provider.
max_concurrency: Maximum number of concurrent delete operations.
Returns:
Number of files deleted.
"""
deleted = 0
uploader = get_uploader(provider)
if uploader is None:
logger.warning(f"No uploader available for {provider}")
return 0
semaphore = asyncio.Semaphore(max_concurrency)
async def delete_single(target_file_id: str) -> bool:
"""Delete a single file with semaphore limiting."""
async with semaphore:
return await uploader.adelete(target_file_id)
if delete_all_from_provider:
try:
files = uploader.list_files()
tasks = []
for file_info in files:
fid = file_info.get("id") or file_info.get("name")
if fid:
tasks.append(delete_single(fid))
results = await asyncio.gather(*tasks, return_exceptions=True)
deleted = sum(1 for r in results if r is True)
except Exception as e:
logger.warning(f"Error listing/deleting files from {provider}: {e}")
elif cache is not None:
uploads = await cache.aget_all_for_provider(provider)
tasks = []
for upload in uploads:
tasks.append(delete_single(upload.file_id))
results = await asyncio.gather(*tasks, return_exceptions=True)
for upload, result in zip(uploads, results, strict=False):
if result is True:
deleted += 1
await cache.aremove_by_file_id(upload.file_id, provider)
logger.info(f"Deleted {deleted} files from {provider}")
return deleted

26
lib/crewai/src/crewai/files/constants.py
View File

@@ -1,26 +0,0 @@
"""Constants for file handling utilities."""
from datetime import timedelta
from typing import Final, Literal
DEFAULT_MAX_FILE_SIZE_BYTES: Final[Literal[524_288_000]] = 524_288_000
MAGIC_BUFFER_SIZE: Final[Literal[2048]] = 2048
UPLOAD_MAX_RETRIES: Final[Literal[3]] = 3
UPLOAD_RETRY_DELAY_BASE: Final[Literal[2]] = 2
DEFAULT_TTL_SECONDS: Final[Literal[86_400]] = 86_400
DEFAULT_MAX_CACHE_ENTRIES: Final[Literal[1000]] = 1000
GEMINI_FILE_TTL: Final[timedelta] = timedelta(hours=48)
BACKOFF_BASE_DELAY: Final[float] = 1.0
BACKOFF_MAX_DELAY: Final[float] = 30.0
BACKOFF_JITTER_FACTOR: Final[float] = 0.1
FILES_API_MAX_SIZE: Final[Literal[536_870_912]] = 536_870_912
DEFAULT_UPLOAD_CHUNK_SIZE: Final[Literal[67_108_864]] = 67_108_864
MULTIPART_THRESHOLD: Final[Literal[8_388_608]] = 8_388_608
MULTIPART_CHUNKSIZE: Final[Literal[8_388_608]] = 8_388_608
MAX_CONCURRENCY: Final[Literal[10]] = 10

281
lib/crewai/src/crewai/files/content_types.py
View File

@@ -1,281 +0,0 @@
"""Content-type specific file classes."""
from __future__ import annotations
from abc import ABC
from io import IOBase
from pathlib import Path
from typing import Annotated, Any, BinaryIO, Literal, Self
from pydantic import BaseModel, Field, GetCoreSchemaHandler
from pydantic_core import CoreSchema, core_schema
from crewai.files.file import (
AsyncFileStream,
FileBytes,
FilePath,
FileSource,
FileStream,
FileUrl,
)
from crewai.files.utils import is_file_source
FileSourceInput = str | Path | bytes | IOBase | FileSource
class _FileSourceCoercer:
"""Pydantic-compatible type that coerces various inputs to FileSource."""
@classmethod
def _coerce(cls, v: Any) -> FileSource:
"""Convert raw input to appropriate FileSource type."""
if isinstance(v, (FilePath, FileBytes, FileStream, FileUrl)):
return v
if isinstance(v, str):
if v.startswith(("http://", "https://")):
return FileUrl(url=v)
return FilePath(path=Path(v))
if isinstance(v, Path):
return FilePath(path=v)
if isinstance(v, bytes):
return FileBytes(data=v)
if isinstance(v, (IOBase, BinaryIO)):
return FileStream(stream=v)
raise ValueError(f"Cannot convert {type(v).__name__} to file source")
@classmethod
def __get_pydantic_core_schema__(
cls,
_source_type: Any,
_handler: GetCoreSchemaHandler,
) -> CoreSchema:
"""Generate Pydantic core schema for FileSource coercion."""
return core_schema.no_info_plain_validator_function(
cls._coerce,
serialization=core_schema.plain_serializer_function_ser_schema(
lambda v: v,
info_arg=False,
return_schema=core_schema.any_schema(),
),
)
CoercedFileSource = Annotated[FileSourceInput, _FileSourceCoercer]
FileMode = Literal["strict", "auto", "warn", "chunk"]
ImageExtension = Literal[
".png",
".jpg",
".jpeg",
".gif",
".webp",
".bmp",
".tiff",
".tif",
".svg",
".heic",
".heif",
]
ImageMimeType = Literal[
"image/png",
"image/jpeg",
"image/gif",
"image/webp",
"image/bmp",
"image/tiff",
"image/svg+xml",
"image/heic",
"image/heif",
]
PDFExtension = Literal[".pdf"]
PDFContentType = Literal["application/pdf"]
TextExtension = Literal[
".txt",
".md",
".rst",
".csv",
".json",
".xml",
".yaml",
".yml",
".html",
".htm",
".log",
".ini",
".cfg",
".conf",
]
TextContentType = Literal[
"text/plain",
"text/markdown",
"text/csv",
"application/json",
"application/xml",
"text/xml",
"application/x-yaml",
"text/yaml",
"text/html",
]
AudioExtension = Literal[
".mp3", ".wav", ".ogg", ".flac", ".aac", ".m4a", ".wma", ".aiff", ".opus"
]
AudioMimeType = Literal[
"audio/mp3",
"audio/mpeg",
"audio/wav",
"audio/x-wav",
"audio/ogg",
"audio/flac",
"audio/aac",
"audio/m4a",
"audio/mp4",
"audio/x-ms-wma",
"audio/aiff",
"audio/opus",
]
VideoExtension = Literal[
".mp4", ".avi", ".mkv", ".mov", ".webm", ".flv", ".wmv", ".m4v", ".mpeg", ".mpg"
]
VideoMimeType = Literal[
"video/mp4",
"video/mpeg",
"video/webm",
"video/quicktime",
"video/x-msvideo",
"video/x-matroska",
"video/x-flv",
"video/x-ms-wmv",
]
class BaseFile(ABC, BaseModel):
"""Abstract base class for typed file wrappers.
Provides common functionality for all file types including:
- File source management
- Content reading
- Dict unpacking support (`**` syntax)
- Per-file mode mode
Can be unpacked with ** syntax: `{**ImageFile(source="./chart.png")}`
which unpacks to: `{"chart": <ImageFile instance>}` using filename stem as key.
Attributes:
source: The underlying file source (path, bytes, or stream).
mode: How to handle this file if it exceeds provider limits.
"""
source: CoercedFileSource = Field(description="The underlying file source.")
mode: FileMode = Field(
default="auto",
description="How to handle if file exceeds limits: strict, auto, warn, chunk.",
)
@property
def _file_source(self) -> FileSource:
"""Get source with narrowed type (always FileSource after validation)."""
if is_file_source(self.source):
return self.source
raise TypeError("source must be a FileSource after validation")
@property
def filename(self) -> str | None:
"""Get the filename from the source."""
return self._file_source.filename
@property
def content_type(self) -> str:
"""Get the content type from the source."""
return self._file_source.content_type
def read(self) -> bytes:
"""Read the file content as bytes."""
return self._file_source.read() # type: ignore[union-attr]
async def aread(self) -> bytes:
"""Async read the file content as bytes.
Raises:
TypeError: If the underlying source doesn't support async read.
"""
source = self._file_source
if isinstance(source, (FilePath, FileBytes, AsyncFileStream, FileUrl)):
return await source.aread()
raise TypeError(f"{type(source).__name__} does not support async read")
def read_text(self, encoding: str = "utf-8") -> str:
"""Read the file content as string."""
return self.read().decode(encoding)
@property
def _unpack_key(self) -> str:
"""Get the key to use when unpacking (filename stem)."""
filename = self._file_source.filename
if filename:
return Path(filename).stem
return "file"
def keys(self) -> list[str]:
"""Return keys for dict unpacking."""
return [self._unpack_key]
def __getitem__(self, key: str) -> Self:
"""Return self for dict unpacking."""
if key == self._unpack_key:
return self
raise KeyError(key)
class ImageFile(BaseFile):
"""File representing an image.
Supports common image formats: PNG, JPEG, GIF, WebP, BMP, TIFF, SVG.
"""
class PDFFile(BaseFile):
"""File representing a PDF document."""
class TextFile(BaseFile):
"""File representing a text document.
Supports common text formats: TXT, MD, RST, CSV, JSON, XML, YAML, HTML.
"""
class AudioFile(BaseFile):
"""File representing an audio file.
Supports common audio formats: MP3, WAV, OGG, FLAC, AAC, M4A, WMA.
"""
class VideoFile(BaseFile):
"""File representing a video file.
Supports common video formats: MP4, AVI, MKV, MOV, WebM, FLV, WMV.
"""
class File(BaseFile):
"""Generic file that auto-detects the appropriate type.
Use this when you don't want to specify the exact file type.
The content type is automatically detected from the file contents.
Example:
>>> pdf_file = File(source="./document.pdf")
>>> image_file = File(source="./image.png")
>>> bytes_file = File(source=b"file content")
"""
FileInput = AudioFile | File | ImageFile | PDFFile | TextFile | VideoFile

507
lib/crewai/src/crewai/files/file.py
View File

@@ -1,507 +0,0 @@
"""Base file class for handling file inputs in tasks."""
from __future__ import annotations
from collections.abc import AsyncIterator, Iterator
import mimetypes
from pathlib import Path
from typing import Annotated, Any, BinaryIO, Protocol, cast, runtime_checkable
import aiofiles
from pydantic import (
BaseModel,
BeforeValidator,
Field,
GetCoreSchemaHandler,
PrivateAttr,
model_validator,
)
from pydantic_core import CoreSchema, core_schema
from crewai.files.constants import DEFAULT_MAX_FILE_SIZE_BYTES, MAGIC_BUFFER_SIZE
@runtime_checkable
class AsyncReadable(Protocol):
"""Protocol for async readable streams."""
async def read(self, size: int = -1) -> bytes:
"""Read up to size bytes from the stream."""
...
class _AsyncReadableValidator:
"""Pydantic validator for AsyncReadable types."""
@classmethod
def __get_pydantic_core_schema__(
cls, _source_type: Any, _handler: GetCoreSchemaHandler
) -> CoreSchema:
return core_schema.no_info_plain_validator_function(
cls._validate,
serialization=core_schema.plain_serializer_function_ser_schema(
lambda x: None, info_arg=False
),
)
@staticmethod
def _validate(value: Any) -> AsyncReadable:
if isinstance(value, AsyncReadable):
return value
raise ValueError("Expected an async readable object with async read() method")
ValidatedAsyncReadable = Annotated[AsyncReadable, _AsyncReadableValidator()]
def _fallback_content_type(filename: str | None) -> str:
"""Get content type from filename extension or return default."""
if filename:
mime_type, _ = mimetypes.guess_type(filename)
if mime_type:
return mime_type
return "application/octet-stream"
def detect_content_type(data: bytes, filename: str | None = None) -> str:
"""Detect MIME type from file content.
Uses python-magic if available for accurate content-based detection,
falls back to mimetypes module using filename extension.
Args:
data: Raw bytes to analyze (only first 2048 bytes are used).
filename: Optional filename for extension-based fallback.
Returns:
The detected MIME type.
"""
try:
import magic
result: str = magic.from_buffer(data[:MAGIC_BUFFER_SIZE], mime=True)
return result
except ImportError:
return _fallback_content_type(filename)
def detect_content_type_from_path(path: Path, filename: str | None = None) -> str:
"""Detect MIME type from file path.
Uses python-magic's from_file() for accurate detection without reading
the entire file into memory.
Args:
path: Path to the file.
filename: Optional filename for extension-based fallback.
Returns:
The detected MIME type.
"""
try:
import magic
result: str = magic.from_file(str(path), mime=True)
return result
except ImportError:
return _fallback_content_type(filename or path.name)
class _BinaryIOValidator:
"""Pydantic validator for BinaryIO types."""
@classmethod
def __get_pydantic_core_schema__(
cls, _source_type: Any, _handler: GetCoreSchemaHandler
) -> CoreSchema:
return core_schema.no_info_plain_validator_function(
cls._validate,
serialization=core_schema.plain_serializer_function_ser_schema(
lambda x: None, info_arg=False
),
)
@staticmethod
def _validate(value: Any) -> BinaryIO:
if hasattr(value, "read") and hasattr(value, "seek"):
return cast(BinaryIO, value)
raise ValueError("Expected a binary file-like object with read() and seek()")
ValidatedBinaryIO = Annotated[BinaryIO, _BinaryIOValidator()]
class FilePath(BaseModel):
"""File loaded from a filesystem path."""
path: Path = Field(description="Path to the file on the filesystem.")
max_size_bytes: int = Field(
default=DEFAULT_MAX_FILE_SIZE_BYTES,
exclude=True,
description="Maximum file size in bytes.",
)
_content: bytes | None = PrivateAttr(default=None)
_content_type: str = PrivateAttr()
@model_validator(mode="after")
def _validate_file_exists(self) -> FilePath:
"""Validate that the file exists, is secure, and within size limits."""
from crewai.files.processing.exceptions import FileTooLargeError
path_str = str(self.path)
if ".." in path_str:
raise ValueError(f"Path traversal not allowed: {self.path}")
if self.path.is_symlink():
resolved = self.path.resolve()
cwd = Path.cwd().resolve()
if not str(resolved).startswith(str(cwd)):
raise ValueError(f"Symlink escapes allowed directory: {self.path}")
if not self.path.exists():
raise ValueError(f"File not found: {self.path}")
if not self.path.is_file():
raise ValueError(f"Path is not a file: {self.path}")
actual_size = self.path.stat().st_size
if actual_size > self.max_size_bytes:
raise FileTooLargeError(
f"File exceeds max size ({actual_size} > {self.max_size_bytes})",
file_name=str(self.path),
actual_size=actual_size,
max_size=self.max_size_bytes,
)
self._content_type = detect_content_type_from_path(self.path, self.path.name)
return self
@property
def filename(self) -> str:
"""Get the filename from the path."""
return self.path.name
@property
def content_type(self) -> str:
"""Get the content type."""
return self._content_type
def read(self) -> bytes:
"""Read the file content from disk."""
if self._content is None:
self._content = self.path.read_bytes()
return self._content
async def aread(self) -> bytes:
"""Async read the file content from disk."""
if self._content is None:
async with aiofiles.open(self.path, "rb") as f:
self._content = await f.read()
return self._content
def read_chunks(self, chunk_size: int = 65536) -> Iterator[bytes]:
"""Stream file content in chunks without loading entirely into memory.
Args:
chunk_size: Size of each chunk in bytes.
Yields:
Chunks of file content.
"""
with open(self.path, "rb") as f:
while chunk := f.read(chunk_size):
yield chunk
async def aread_chunks(self, chunk_size: int = 65536) -> AsyncIterator[bytes]:
"""Async streaming for non-blocking I/O.
Args:
chunk_size: Size of each chunk in bytes.
Yields:
Chunks of file content.
"""
async with aiofiles.open(self.path, "rb") as f:
while chunk := await f.read(chunk_size):
yield chunk
class FileBytes(BaseModel):
"""File created from raw bytes content."""
data: bytes = Field(description="Raw bytes content of the file.")
filename: str | None = Field(default=None, description="Optional filename.")
_content_type: str = PrivateAttr()
@model_validator(mode="after")
def _detect_content_type(self) -> FileBytes:
"""Detect and cache content type from data."""
self._content_type = detect_content_type(self.data, self.filename)
return self
@property
def content_type(self) -> str:
"""Get the content type."""
return self._content_type
def read(self) -> bytes:
"""Return the bytes content."""
return self.data
async def aread(self) -> bytes:
"""Async return the bytes content (immediate, already in memory)."""
return self.data
def read_chunks(self, chunk_size: int = 65536) -> Iterator[bytes]:
"""Stream bytes content in chunks.
Args:
chunk_size: Size of each chunk in bytes.
Yields:
Chunks of bytes content.
"""
for i in range(0, len(self.data), chunk_size):
yield self.data[i : i + chunk_size]
async def aread_chunks(self, chunk_size: int = 65536) -> AsyncIterator[bytes]:
"""Async streaming (immediate yield since already in memory).
Args:
chunk_size: Size of each chunk in bytes.
Yields:
Chunks of bytes content.
"""
for chunk in self.read_chunks(chunk_size):
yield chunk
class FileStream(BaseModel):
"""File loaded from a file-like stream."""
stream: ValidatedBinaryIO = Field(description="Binary file stream.")
filename: str | None = Field(default=None, description="Optional filename.")
_content: bytes | None = PrivateAttr(default=None)
_content_type: str = PrivateAttr()
@model_validator(mode="after")
def _initialize(self) -> FileStream:
"""Extract filename and detect content type."""
if self.filename is None:
name = getattr(self.stream, "name", None)
if name is not None:
self.filename = Path(name).name
position = self.stream.tell()
self.stream.seek(0)
header = self.stream.read(MAGIC_BUFFER_SIZE)
self.stream.seek(position)
self._content_type = detect_content_type(header, self.filename)
return self
@property
def content_type(self) -> str:
"""Get the content type."""
return self._content_type
def read(self) -> bytes:
"""Read the stream content. Content is cached after first read."""
if self._content is None:
position = self.stream.tell()
self.stream.seek(0)
self._content = self.stream.read()
self.stream.seek(position)
return self._content
def close(self) -> None:
"""Close the underlying stream."""
self.stream.close()
def __enter__(self) -> FileStream:
"""Enter context manager."""
return self
def __exit__(
self,
exc_type: type[BaseException] | None,
exc_val: BaseException | None,
exc_tb: Any,
) -> None:
"""Exit context manager and close stream."""
self.close()
def read_chunks(self, chunk_size: int = 65536) -> Iterator[bytes]:
"""Stream from underlying stream in chunks.
Args:
chunk_size: Size of each chunk in bytes.
Yields:
Chunks of stream content.
"""
position = self.stream.tell()
self.stream.seek(0)
try:
while chunk := self.stream.read(chunk_size):
yield chunk
finally:
self.stream.seek(position)
class AsyncFileStream(BaseModel):
"""File loaded from an async stream.
Use for async file handles like aiofiles objects or aiohttp response bodies.
This is an async-only type - use aread() instead of read().
Attributes:
stream: Async file-like object with async read() method.
filename: Optional filename for the stream.
"""
stream: ValidatedAsyncReadable = Field(
description="Async file stream with async read() method."
)
filename: str | None = Field(default=None, description="Optional filename.")
_content: bytes | None = PrivateAttr(default=None)
_content_type: str | None = PrivateAttr(default=None)
@property
def content_type(self) -> str:
"""Get the content type from stream content (cached). Requires aread() first."""
if self._content is None:
raise RuntimeError("Call aread() first to load content")
if self._content_type is None:
self._content_type = detect_content_type(self._content, self.filename)
return self._content_type
async def aread(self) -> bytes:
"""Async read the stream content. Content is cached after first read."""
if self._content is None:
self._content = await self.stream.read()
return self._content
async def aclose(self) -> None:
"""Async close the underlying stream."""
if hasattr(self.stream, "close"):
result = self.stream.close()
if hasattr(result, "__await__"):
await result
async def __aenter__(self) -> AsyncFileStream:
"""Async enter context manager."""
return self
async def __aexit__(
self,
exc_type: type[BaseException] | None,
exc_val: BaseException | None,
exc_tb: Any,
) -> None:
"""Async exit context manager and close stream."""
await self.aclose()
async def aread_chunks(self, chunk_size: int = 65536) -> AsyncIterator[bytes]:
"""Async stream content in chunks.
Args:
chunk_size: Size of each chunk in bytes.
Yields:
Chunks of stream content.
"""
while chunk := await self.stream.read(chunk_size):
yield chunk
class FileUrl(BaseModel):
"""File referenced by URL.
For providers that support URL references, the URL is passed directly.
For providers that don't, content is fetched on demand.
Attributes:
url: URL where the file can be accessed.
filename: Optional filename (extracted from URL if not provided).
"""
url: str = Field(description="URL where the file can be accessed.")
filename: str | None = Field(default=None, description="Optional filename.")
_content_type: str | None = PrivateAttr(default=None)
_content: bytes | None = PrivateAttr(default=None)
@model_validator(mode="after")
def _validate_url(self) -> FileUrl:
"""Validate URL format."""
if not self.url.startswith(("http://", "https://")):
raise ValueError(f"Invalid URL scheme: {self.url}")
return self
@property
def content_type(self) -> str:
"""Get the content type, guessing from URL extension if not set."""
if self._content_type is None:
self._content_type = self._guess_content_type()
return self._content_type
def _guess_content_type(self) -> str:
"""Guess content type from URL extension."""
from urllib.parse import urlparse
parsed = urlparse(self.url)
path = parsed.path
guessed, _ = mimetypes.guess_type(path)
return guessed or "application/octet-stream"
def read(self) -> bytes:
"""Fetch content from URL (for providers that don't support URL references)."""
if self._content is None:
import httpx
response = httpx.get(self.url, follow_redirects=True)
response.raise_for_status()
self._content = response.content
if "content-type" in response.headers:
self._content_type = response.headers["content-type"].split(";")[0]
return self._content
async def aread(self) -> bytes:
"""Async fetch content from URL."""
if self._content is None:
import httpx
async with httpx.AsyncClient() as client:
response = await client.get(self.url, follow_redirects=True)
response.raise_for_status()
self._content = response.content
if "content-type" in response.headers:
self._content_type = response.headers["content-type"].split(";")[0]
return self._content
FileSource = FilePath | FileBytes | FileStream | AsyncFileStream | FileUrl
def _normalize_source(value: Any) -> FileSource:
"""Convert raw input to appropriate source type."""
if isinstance(value, (FilePath, FileBytes, FileStream, AsyncFileStream, FileUrl)):
return value
if isinstance(value, str):
if value.startswith(("http://", "https://")):
return FileUrl(url=value)
return FilePath(path=Path(value))
if isinstance(value, Path):
return FilePath(path=value)
if isinstance(value, bytes):
return FileBytes(data=value)
if isinstance(value, AsyncReadable):
return AsyncFileStream(stream=value)
if hasattr(value, "read") and hasattr(value, "seek"):
return FileStream(stream=value)
raise ValueError(f"Cannot convert {type(value).__name__} to file source")
RawFileInput = str | Path | bytes
FileSourceInput = Annotated[
RawFileInput | FileSource, BeforeValidator(_normalize_source)
]

184
lib/crewai/src/crewai/files/metrics.py
View File

@@ -1,184 +0,0 @@
"""Performance metrics and structured logging for file operations."""
from __future__ import annotations
from collections.abc import Generator
from contextlib import contextmanager
from dataclasses import dataclass, field
from datetime import datetime, timezone
import logging
import time
from typing import Any
logger = logging.getLogger(__name__)
@dataclass
class FileOperationMetrics:
"""Metrics for a file operation.
Attributes:
operation: Name of the operation (e.g., "upload", "resolve", "process").
filename: Name of the file being operated on.
provider: Provider name if applicable.
duration_ms: Duration of the operation in milliseconds.
size_bytes: Size of the file in bytes.
success: Whether the operation succeeded.
error: Error message if operation failed.
timestamp: When the operation occurred.
metadata: Additional operation-specific metadata.
"""
operation: str
filename: str | None = None
provider: str | None = None
duration_ms: float = 0.0
size_bytes: int | None = None
success: bool = True
error: str | None = None
timestamp: datetime = field(default_factory=lambda: datetime.now(timezone.utc))
metadata: dict[str, Any] = field(default_factory=dict)
def to_dict(self) -> dict[str, Any]:
"""Convert metrics to dictionary for logging.
Returns:
Dictionary representation of metrics.
"""
result: dict[str, Any] = {
"operation": self.operation,
"duration_ms": round(self.duration_ms, 2),
"success": self.success,
"timestamp": self.timestamp.isoformat(),
}
if self.filename:
result["filename"] = self.filename
if self.provider:
result["provider"] = self.provider
if self.size_bytes is not None:
result["size_bytes"] = self.size_bytes
if self.error:
result["error"] = self.error
if self.metadata:
result.update(self.metadata)
return result
@contextmanager
def measure_operation(
operation: str,
*,
filename: str | None = None,
provider: str | None = None,
size_bytes: int | None = None,
log_level: int = logging.DEBUG,
**extra_metadata: Any,
) -> Generator[FileOperationMetrics, None, None]:
"""Context manager to measure and log operation performance.
Args:
operation: Name of the operation.
filename: Optional filename being operated on.
provider: Optional provider name.
size_bytes: Optional file size in bytes.
log_level: Log level for the result message.
**extra_metadata: Additional metadata to include.
Yields:
FileOperationMetrics object that will be populated with results.
Example:
with measure_operation("upload", filename="test.pdf", provider="openai") as metrics:
result = upload_file(file)
metrics.metadata["file_id"] = result.file_id
"""
metrics = FileOperationMetrics(
operation=operation,
filename=filename,
provider=provider,
size_bytes=size_bytes,
metadata=dict(extra_metadata),
)
start_time = time.perf_counter()
try:
yield metrics
metrics.success = True
except Exception as e:
metrics.success = False
metrics.error = str(e)
raise
finally:
metrics.duration_ms = (time.perf_counter() - start_time) * 1000
log_message = f"{operation}"
if filename:
log_message += f" [{filename}]"
if provider:
log_message += f" ({provider})"
if metrics.success:
log_message += f" completed in {metrics.duration_ms:.2f}ms"
else:
log_message += f" failed after {metrics.duration_ms:.2f}ms: {metrics.error}"
logger.log(log_level, log_message, extra=metrics.to_dict())
def log_file_operation(
operation: str,
*,
filename: str | None = None,
provider: str | None = None,
size_bytes: int | None = None,
duration_ms: float | None = None,
success: bool = True,
error: str | None = None,
level: int = logging.INFO,
**extra: Any,
) -> None:
"""Log a file operation with structured data.
Args:
operation: Name of the operation.
filename: Optional filename being operated on.
provider: Optional provider name.
size_bytes: Optional file size in bytes.
duration_ms: Optional duration in milliseconds.
success: Whether the operation succeeded.
error: Optional error message.
level: Log level to use.
**extra: Additional metadata to include.
"""
metrics = FileOperationMetrics(
operation=operation,
filename=filename,
provider=provider,
size_bytes=size_bytes,
duration_ms=duration_ms or 0.0,
success=success,
error=error,
metadata=dict(extra),
)
message = f"{operation}"
if filename:
message += f" [{filename}]"
if provider:
message += f" ({provider})"
if success:
if duration_ms:
message += f" completed in {duration_ms:.2f}ms"
else:
message += " completed"
else:
message += " failed"
if error:
message += f": {error}"
logger.log(level, message, extra=metrics.to_dict())

62
lib/crewai/src/crewai/files/processing/__init__.py
View File

@@ -1,62 +0,0 @@
"""File processing module for multimodal content handling.
This module provides validation, transformation, and processing utilities
for files used in multimodal LLM interactions.
"""
from crewai.files.processing.constraints import (
ANTHROPIC_CONSTRAINTS,
BEDROCK_CONSTRAINTS,
GEMINI_CONSTRAINTS,
OPENAI_CONSTRAINTS,
AudioConstraints,
ImageConstraints,
PDFConstraints,
ProviderConstraints,
VideoConstraints,
get_constraints_for_provider,
)
from crewai.files.processing.enums import FileHandling
from crewai.files.processing.exceptions import (
FileProcessingError,
FileTooLargeError,
FileValidationError,
ProcessingDependencyError,
UnsupportedFileTypeError,
)
from crewai.files.processing.processor import FileProcessor
from crewai.files.processing.validators import (
validate_audio,
validate_file,
validate_image,
validate_pdf,
validate_text,
validate_video,
)
__all__ = [
"ANTHROPIC_CONSTRAINTS",
"BEDROCK_CONSTRAINTS",
"GEMINI_CONSTRAINTS",
"OPENAI_CONSTRAINTS",
"AudioConstraints",
"FileHandling",
"FileProcessingError",
"FileProcessor",
"FileTooLargeError",
"FileValidationError",
"ImageConstraints",
"PDFConstraints",
"ProcessingDependencyError",
"ProviderConstraints",
"UnsupportedFileTypeError",
"VideoConstraints",
"get_constraints_for_provider",
"validate_audio",
"validate_file",
"validate_image",
"validate_pdf",
"validate_text",
"validate_video",
]

285
lib/crewai/src/crewai/files/processing/constraints.py
View File

@@ -1,285 +0,0 @@
"""Provider-specific file constraints for multimodal content."""
from dataclasses import dataclass
from functools import lru_cache
from typing import Literal
from crewai.files.content_types import (
AudioMimeType,
ImageMimeType,
VideoMimeType,
)
ProviderName = Literal[
"anthropic",
"openai",
"gemini",
"bedrock",
"azure",
]
DEFAULT_IMAGE_FORMATS: tuple[ImageMimeType, ...] = (
"image/png",
"image/jpeg",
"image/gif",
"image/webp",
)
GEMINI_IMAGE_FORMATS: tuple[ImageMimeType, ...] = (
"image/png",
"image/jpeg",
"image/gif",
"image/webp",
"image/heic",
"image/heif",
)
DEFAULT_AUDIO_FORMATS: tuple[AudioMimeType, ...] = (
"audio/mp3",
"audio/mpeg",
"audio/wav",
"audio/ogg",
"audio/flac",
"audio/aac",
"audio/m4a",
)
GEMINI_AUDIO_FORMATS: tuple[AudioMimeType, ...] = (
"audio/mp3",
"audio/mpeg",
"audio/wav",
"audio/ogg",
"audio/flac",
"audio/aac",
"audio/m4a",
"audio/opus",
)
DEFAULT_VIDEO_FORMATS: tuple[VideoMimeType, ...] = (
"video/mp4",
"video/mpeg",
"video/webm",
"video/quicktime",
)
GEMINI_VIDEO_FORMATS: tuple[VideoMimeType, ...] = (
"video/mp4",
"video/mpeg",
"video/webm",
"video/quicktime",
"video/x-msvideo",
"video/x-flv",
)
@dataclass(frozen=True)
class ImageConstraints:
"""Constraints for image files.
Attributes:
max_size_bytes: Maximum file size in bytes.
max_width: Maximum image width in pixels.
max_height: Maximum image height in pixels.
max_images_per_request: Maximum number of images per request.
supported_formats: Supported image MIME types.
"""
max_size_bytes: int
max_width: int | None = None
max_height: int | None = None
max_images_per_request: int | None = None
supported_formats: tuple[ImageMimeType, ...] = DEFAULT_IMAGE_FORMATS
@dataclass(frozen=True)
class PDFConstraints:
"""Constraints for PDF files.
Attributes:
max_size_bytes: Maximum file size in bytes.
max_pages: Maximum number of pages.
"""
max_size_bytes: int
max_pages: int | None = None
@dataclass(frozen=True)
class AudioConstraints:
"""Constraints for audio files.
Attributes:
max_size_bytes: Maximum file size in bytes.
max_duration_seconds: Maximum audio duration in seconds.
supported_formats: Supported audio MIME types.
"""
max_size_bytes: int
max_duration_seconds: int | None = None
supported_formats: tuple[AudioMimeType, ...] = DEFAULT_AUDIO_FORMATS
@dataclass(frozen=True)
class VideoConstraints:
"""Constraints for video files.
Attributes:
max_size_bytes: Maximum file size in bytes.
max_duration_seconds: Maximum video duration in seconds.
supported_formats: Supported video MIME types.
"""
max_size_bytes: int
max_duration_seconds: int | None = None
supported_formats: tuple[VideoMimeType, ...] = DEFAULT_VIDEO_FORMATS
@dataclass(frozen=True)
class ProviderConstraints:
"""Complete set of constraints for a provider.
Attributes:
name: Provider name identifier.
image: Image file constraints.
pdf: PDF file constraints.
audio: Audio file constraints.
video: Video file constraints.
general_max_size_bytes: Maximum size for any file type.
supports_file_upload: Whether the provider supports file upload APIs.
file_upload_threshold_bytes: Size threshold above which to use file upload.
supports_url_references: Whether the provider supports URL-based file references.
"""
name: ProviderName
image: ImageConstraints | None = None
pdf: PDFConstraints | None = None
audio: AudioConstraints | None = None
video: VideoConstraints | None = None
general_max_size_bytes: int | None = None
supports_file_upload: bool = False
file_upload_threshold_bytes: int | None = None
supports_url_references: bool = False
ANTHROPIC_CONSTRAINTS = ProviderConstraints(
name="anthropic",
image=ImageConstraints(
max_size_bytes=5_242_880, # 5 MB per image
max_width=8000,
max_height=8000,
max_images_per_request=100,
),
pdf=PDFConstraints(
max_size_bytes=33_554_432, # 32 MB request size limit
max_pages=100,
),
supports_file_upload=True,
file_upload_threshold_bytes=5_242_880,
supports_url_references=True,
)
OPENAI_CONSTRAINTS = ProviderConstraints(
name="openai",
image=ImageConstraints(
max_size_bytes=20_971_520,
max_images_per_request=10,
),
audio=AudioConstraints(
max_size_bytes=26_214_400, # 25 MB - whisper limit
max_duration_seconds=1500, # 25 minutes, arbitrary-ish, this is from the transcriptions limit
),
supports_file_upload=True,
file_upload_threshold_bytes=5_242_880,
supports_url_references=True,
)
GEMINI_CONSTRAINTS = ProviderConstraints(
name="gemini",
image=ImageConstraints(
max_size_bytes=104_857_600,
supported_formats=GEMINI_IMAGE_FORMATS,
),
pdf=PDFConstraints(
max_size_bytes=52_428_800,
),
audio=AudioConstraints(
max_size_bytes=104_857_600,
max_duration_seconds=34200, # 9.5 hours
supported_formats=GEMINI_AUDIO_FORMATS,
),
video=VideoConstraints(
max_size_bytes=2_147_483_648,
max_duration_seconds=3600, # 1 hour at default resolution
supported_formats=GEMINI_VIDEO_FORMATS,
),
supports_file_upload=True,
file_upload_threshold_bytes=20_971_520,
supports_url_references=True,
)
BEDROCK_CONSTRAINTS = ProviderConstraints(
name="bedrock",
image=ImageConstraints(
max_size_bytes=4_608_000,
max_width=8000,
max_height=8000,
),
pdf=PDFConstraints(
max_size_bytes=3_840_000,
max_pages=100,
),
)
AZURE_CONSTRAINTS = ProviderConstraints(
name="azure",
image=ImageConstraints(
max_size_bytes=20_971_520,
max_images_per_request=10,
),
audio=AudioConstraints(
max_size_bytes=26_214_400, # 25 MB - same as openai
max_duration_seconds=1500, # 25 minutes - same as openai
),
supports_url_references=True,
)
_PROVIDER_CONSTRAINTS_MAP: dict[str, ProviderConstraints] = {
"anthropic": ANTHROPIC_CONSTRAINTS,
"openai": OPENAI_CONSTRAINTS,
"gemini": GEMINI_CONSTRAINTS,
"bedrock": BEDROCK_CONSTRAINTS,
"azure": AZURE_CONSTRAINTS,
"claude": ANTHROPIC_CONSTRAINTS,
"gpt": OPENAI_CONSTRAINTS,
"google": GEMINI_CONSTRAINTS,
"aws": BEDROCK_CONSTRAINTS,
}
@lru_cache(maxsize=32)
def get_constraints_for_provider(
provider: str | ProviderConstraints,
) -> ProviderConstraints | None:
"""Get constraints for a provider by name or return if already ProviderConstraints.
Args:
provider: Provider name string or ProviderConstraints instance.
Returns:
ProviderConstraints for the provider, or None if not found.
"""
if isinstance(provider, ProviderConstraints):
return provider
provider_lower = provider.lower()
if provider_lower in _PROVIDER_CONSTRAINTS_MAP:
return _PROVIDER_CONSTRAINTS_MAP[provider_lower]
for key, constraints in _PROVIDER_CONSTRAINTS_MAP.items():
if key in provider_lower:
return constraints
return None

19
lib/crewai/src/crewai/files/processing/enums.py
View File

@@ -1,19 +0,0 @@
"""Enums for file processing configuration."""
from enum import Enum
class FileHandling(Enum):
"""Defines how files exceeding provider limits should be handled.
Attributes:
STRICT: Fail with an error if file exceeds limits.
AUTO: Automatically resize, compress, or optimize to fit limits.
WARN: Log a warning but attempt to process anyway.
CHUNK: Split large files into smaller pieces.
"""
STRICT = "strict"
AUTO = "auto"
WARN = "warn"
CHUNK = "chunk"

145
lib/crewai/src/crewai/files/processing/exceptions.py
View File

@@ -1,145 +0,0 @@
"""Exceptions for file processing operations."""
class FileProcessingError(Exception):
"""Base exception for file processing errors."""
def __init__(self, message: str, file_name: str | None = None) -> None:
"""Initialize the exception.
Args:
message: Error message describing the issue.
file_name: Optional name of the file that caused the error.
"""
self.file_name = file_name
super().__init__(message)
class FileValidationError(FileProcessingError):
"""Raised when file validation fails."""
class FileTooLargeError(FileValidationError):
"""Raised when a file exceeds the maximum allowed size."""
def __init__(
self,
message: str,
file_name: str | None = None,
actual_size: int | None = None,
max_size: int | None = None,
) -> None:
"""Initialize the exception.
Args:
message: Error message describing the issue.
file_name: Optional name of the file that caused the error.
actual_size: The actual size of the file in bytes.
max_size: The maximum allowed size in bytes.
"""
self.actual_size = actual_size
self.max_size = max_size
super().__init__(message, file_name)
class UnsupportedFileTypeError(FileValidationError):
"""Raised when a file type is not supported by the provider."""
def __init__(
self,
message: str,
file_name: str | None = None,
content_type: str | None = None,
) -> None:
"""Initialize the exception.
Args:
message: Error message describing the issue.
file_name: Optional name of the file that caused the error.
content_type: The content type that is not supported.
"""
self.content_type = content_type
super().__init__(message, file_name)
class ProcessingDependencyError(FileProcessingError):
"""Raised when a required processing dependency is not installed."""
def __init__(
self,
message: str,
dependency: str,
install_command: str | None = None,
) -> None:
"""Initialize the exception.
Args:
message: Error message describing the issue.
dependency: Name of the missing dependency.
install_command: Optional command to install the dependency.
"""
self.dependency = dependency
self.install_command = install_command
super().__init__(message)
class TransientFileError(FileProcessingError):
"""Transient error that may succeed on retry (network, timeout)."""
class PermanentFileError(FileProcessingError):
"""Permanent error that will not succeed on retry (auth, format)."""
class UploadError(FileProcessingError):
"""Base exception for upload errors."""
class TransientUploadError(UploadError, TransientFileError):
"""Upload failed but may succeed on retry (network issues, rate limits)."""
class PermanentUploadError(UploadError, PermanentFileError):
"""Upload failed permanently (auth failure, invalid file, unsupported type)."""
def classify_upload_error(e: Exception, filename: str | None = None) -> Exception:
"""Classify an exception as transient or permanent upload error.
Analyzes the exception type name and status code to determine if
the error is likely transient (retryable) or permanent.
Args:
e: The exception to classify.
filename: Optional filename for error context.
Returns:
A TransientUploadError or PermanentUploadError wrapping the original.
"""
error_type = type(e).__name__
if "RateLimit" in error_type or "APIConnection" in error_type:
return TransientUploadError(f"Transient upload error: {e}", file_name=filename)
if "Authentication" in error_type or "Permission" in error_type:
return PermanentUploadError(
f"Authentication/permission error: {e}", file_name=filename
)
if "BadRequest" in error_type or "InvalidRequest" in error_type:
return PermanentUploadError(f"Invalid request: {e}", file_name=filename)
status_code = getattr(e, "status_code", None)
if status_code is not None:
if status_code >= 500 or status_code == 429:
return TransientUploadError(
f"Server error ({status_code}): {e}", file_name=filename
)
if status_code in (401, 403):
return PermanentUploadError(
f"Auth error ({status_code}): {e}", file_name=filename
)
if status_code == 400:
return PermanentUploadError(
f"Bad request ({status_code}): {e}", file_name=filename
)
return TransientUploadError(f"Upload failed: {e}", file_name=filename)

346
lib/crewai/src/crewai/files/processing/processor.py
View File

@@ -1,346 +0,0 @@
"""FileProcessor for validating and transforming files based on provider constraints."""
import asyncio
from collections.abc import Sequence
import logging
from crewai.files.content_types import (
AudioFile,
File,
FileInput,
ImageFile,
PDFFile,
TextFile,
VideoFile,
)
from crewai.files.processing.constraints import (
ProviderConstraints,
get_constraints_for_provider,
)
from crewai.files.processing.enums import FileHandling
from crewai.files.processing.exceptions import (
FileProcessingError,
FileTooLargeError,
FileValidationError,
UnsupportedFileTypeError,
)
from crewai.files.processing.transformers import (
chunk_pdf,
chunk_text,
get_image_dimensions,
get_pdf_page_count,
optimize_image,
resize_image,
)
from crewai.files.processing.validators import validate_file
logger = logging.getLogger(__name__)
class FileProcessor:
"""Processes files according to provider constraints and per-file mode mode.
Validates files against provider-specific limits and optionally transforms
them (resize, compress, chunk) to meet those limits. Each file specifies
its own mode mode via `file.mode`.
Attributes:
constraints: Provider constraints for validation.
"""
def __init__(
self,
constraints: ProviderConstraints | str | None = None,
) -> None:
"""Initialize the FileProcessor.
Args:
constraints: Provider constraints or provider name string.
If None, validation is skipped.
"""
if isinstance(constraints, str):
resolved = get_constraints_for_provider(constraints)
if resolved is None:
logger.warning(
f"Unknown provider '{constraints}' - validation disabled"
)
self.constraints = resolved
else:
self.constraints = constraints
def validate(self, file: FileInput) -> Sequence[str]:
"""Validate a file against provider constraints.
Args:
file: The file to validate.
Returns:
List of validation error messages (empty if valid).
Raises:
FileValidationError: If file.mode is STRICT and validation fails.
"""
if self.constraints is None:
return []
mode = self._get_mode(file)
raise_on_error = mode == FileHandling.STRICT
return validate_file(file, self.constraints, raise_on_error=raise_on_error)
@staticmethod
def _get_mode(file: FileInput) -> FileHandling:
"""Get the mode mode for a file.
Args:
file: The file to get mode for.
Returns:
The file's mode mode, defaulting to AUTO.
"""
mode = getattr(file, "mode", None)
if mode is None:
return FileHandling.AUTO
if isinstance(mode, str):
return FileHandling(mode)
if isinstance(mode, FileHandling):
return mode
return FileHandling.AUTO
def process(self, file: FileInput) -> FileInput | Sequence[FileInput]:
"""Process a single file according to constraints and its mode mode.
Args:
file: The file to process.
Returns:
The processed file (possibly transformed) or a sequence of files
if the file was chunked.
Raises:
FileProcessingError: If file.mode is STRICT and processing fails.
"""
if self.constraints is None:
return file
mode = self._get_mode(file)
try:
errors = self.validate(file)
if not errors:
return file
if mode == FileHandling.STRICT:
raise FileValidationError("; ".join(errors), file_name=file.filename)
if mode == FileHandling.WARN:
for error in errors:
logger.warning(error)
return file
if mode == FileHandling.AUTO:
return self._auto_process(file)
if mode == FileHandling.CHUNK:
return self._chunk_process(file)
return file
except (FileValidationError, FileTooLargeError, UnsupportedFileTypeError):
raise
except Exception as e:
logger.error(f"Error processing file '{file.filename}': {e}")
if mode == FileHandling.STRICT:
raise FileProcessingError(str(e), file_name=file.filename) from e
return file
def process_files(
self,
files: dict[str, FileInput],
) -> dict[str, FileInput]:
"""Process multiple files according to constraints.
Args:
files: Dictionary mapping names to file inputs.
Returns:
Dictionary mapping names to processed files. If a file is chunked,
multiple entries are created with indexed names.
"""
result: dict[str, FileInput] = {}
for name, file in files.items():
processed = self.process(file)
if isinstance(processed, Sequence) and not isinstance(
processed, (str, bytes)
):
for i, chunk in enumerate(processed):
chunk_name = f"{name}_chunk_{i}"
result[chunk_name] = chunk
else:
result[name] = processed
return result
async def aprocess_files(
self,
files: dict[str, FileInput],
max_concurrency: int = 10,
) -> dict[str, FileInput]:
"""Async process multiple files in parallel.
Args:
files: Dictionary mapping names to file inputs.
max_concurrency: Maximum number of concurrent processing tasks.
Returns:
Dictionary mapping names to processed files. If a file is chunked,
multiple entries are created with indexed names.
"""
semaphore = asyncio.Semaphore(max_concurrency)
async def process_single(
key: str, input_file: FileInput
) -> tuple[str, FileInput | Sequence[FileInput]]:
"""Process a single file with semaphore limiting."""
async with semaphore:
loop = asyncio.get_running_loop()
result = await loop.run_in_executor(None, self.process, input_file)
return key, result
tasks = [process_single(n, f) for n, f in files.items()]
gather_results = await asyncio.gather(*tasks, return_exceptions=True)
output: dict[str, FileInput] = {}
for item in gather_results:
if isinstance(item, BaseException):
logger.error(f"Processing failed: {item}")
continue
entry_name, processed = item
if isinstance(processed, Sequence) and not isinstance(
processed, (str, bytes)
):
for i, chunk in enumerate(processed):
output[f"{entry_name}_chunk_{i}"] = chunk
elif isinstance(
processed, (AudioFile, File, ImageFile, PDFFile, TextFile, VideoFile)
):
output[entry_name] = processed
return output
def _auto_process(self, file: FileInput) -> FileInput:
"""Automatically resize/compress file to meet constraints.
Args:
file: The file to process.
Returns:
The processed file.
"""
if self.constraints is None:
return file
if isinstance(file, ImageFile) and self.constraints.image is not None:
return self._auto_process_image(file)
if isinstance(file, PDFFile) and self.constraints.pdf is not None:
logger.warning(
f"Cannot auto-compress PDF '{file.filename}'. "
"Consider using CHUNK mode for large PDFs."
)
return file
if isinstance(file, (AudioFile, VideoFile)):
logger.warning(
f"Auto-processing not supported for {type(file).__name__}. "
"File will be used as-is."
)
return file
return file
def _auto_process_image(self, file: ImageFile) -> ImageFile:
"""Auto-process an image file.
Args:
file: The image file to process.
Returns:
The processed image file.
"""
if self.constraints is None or self.constraints.image is None:
return file
image_constraints = self.constraints.image
processed = file
content = file.read()
current_size = len(content)
if image_constraints.max_width or image_constraints.max_height:
dimensions = get_image_dimensions(file)
if dimensions:
width, height = dimensions
max_w = image_constraints.max_width or width
max_h = image_constraints.max_height or height
if width > max_w or height > max_h:
try:
processed = resize_image(file, max_w, max_h)
content = processed.read()
current_size = len(content)
except Exception as e:
logger.warning(f"Failed to resize image: {e}")
if current_size > image_constraints.max_size_bytes:
try:
processed = optimize_image(processed, image_constraints.max_size_bytes)
except Exception as e:
logger.warning(f"Failed to optimize image: {e}")
return processed
def _chunk_process(self, file: FileInput) -> FileInput | Sequence[FileInput]:
"""Split file into chunks to meet constraints.
Args:
file: The file to chunk.
Returns:
Original file if chunking not needed, or sequence of chunked files.
"""
if self.constraints is None:
return file
if isinstance(file, PDFFile) and self.constraints.pdf is not None:
max_pages = self.constraints.pdf.max_pages
if max_pages is not None:
page_count = get_pdf_page_count(file)
if page_count is not None and page_count > max_pages:
try:
return list(chunk_pdf(file, max_pages))
except Exception as e:
logger.warning(f"Failed to chunk PDF: {e}")
return file
if isinstance(file, TextFile):
# Use general max size as character limit approximation
max_size = self.constraints.general_max_size_bytes
if max_size is not None:
content = file.read()
if len(content) > max_size:
try:
return list(chunk_text(file, max_size))
except Exception as e:
logger.warning(f"Failed to chunk text file: {e}")
return file
if isinstance(file, (ImageFile, AudioFile, VideoFile)):
logger.warning(
f"Chunking not supported for {type(file).__name__}. "
"Consider using AUTO mode for images."
)
return file

336
lib/crewai/src/crewai/files/processing/transformers.py
View File

@@ -1,336 +0,0 @@
"""File transformation functions for resizing, optimizing, and chunking."""
from collections.abc import Iterator
import io
import logging
from crewai.files.content_types import ImageFile, PDFFile, TextFile
from crewai.files.file import FileBytes
from crewai.files.processing.exceptions import ProcessingDependencyError
logger = logging.getLogger(__name__)
def resize_image(
file: ImageFile,
max_width: int,
max_height: int,
*,
preserve_aspect_ratio: bool = True,
) -> ImageFile:
"""Resize an image to fit within the specified dimensions.
Args:
file: The image file to resize.
max_width: Maximum width in pixels.
max_height: Maximum height in pixels.
preserve_aspect_ratio: If True, maintain aspect ratio while fitting within bounds.
Returns:
A new ImageFile with the resized image data.
Raises:
ProcessingDependencyError: If Pillow is not installed.
"""
try:
from PIL import Image
except ImportError as e:
raise ProcessingDependencyError(
"Pillow is required for image resizing",
dependency="Pillow",
install_command="pip install Pillow",
) from e
content = file.read()
with Image.open(io.BytesIO(content)) as img:
original_width, original_height = img.size
if original_width <= max_width and original_height <= max_height:
return file
if preserve_aspect_ratio:
width_ratio = max_width / original_width
height_ratio = max_height / original_height
scale_factor = min(width_ratio, height_ratio)
new_width = int(original_width * scale_factor)
new_height = int(original_height * scale_factor)
else:
new_width = min(original_width, max_width)
new_height = min(original_height, max_height)
resized_img = img.resize((new_width, new_height), Image.Resampling.LANCZOS)
output_format = img.format or "PNG"
if output_format.upper() == "JPEG":
if resized_img.mode in ("RGBA", "LA", "P"):
resized_img = resized_img.convert("RGB")
output_buffer = io.BytesIO()
resized_img.save(output_buffer, format=output_format)
output_bytes = output_buffer.getvalue()
logger.info(
f"Resized image '{file.filename}' from {original_width}x{original_height} "
f"to {new_width}x{new_height}"
)
return ImageFile(source=FileBytes(data=output_bytes, filename=file.filename))
def optimize_image(
file: ImageFile,
target_size_bytes: int,
*,
min_quality: int = 20,
initial_quality: int = 85,
) -> ImageFile:
"""Optimize an image to fit within a target file size.
Uses iterative quality reduction to achieve target size.
Args:
file: The image file to optimize.
target_size_bytes: Target maximum file size in bytes.
min_quality: Minimum quality to use (prevents excessive degradation).
initial_quality: Starting quality for optimization.
Returns:
A new ImageFile with the optimized image data.
Raises:
ProcessingDependencyError: If Pillow is not installed.
"""
try:
from PIL import Image
except ImportError as e:
raise ProcessingDependencyError(
"Pillow is required for image optimization",
dependency="Pillow",
install_command="pip install Pillow",
) from e
content = file.read()
current_size = len(content)
if current_size <= target_size_bytes:
return file
with Image.open(io.BytesIO(content)) as img:
if img.mode in ("RGBA", "LA", "P"):
img = img.convert("RGB")
output_format = "JPEG"
else:
output_format = img.format or "JPEG"
if output_format.upper() not in ("JPEG", "JPG"):
output_format = "JPEG"
quality = initial_quality
output_bytes = content
while len(output_bytes) > target_size_bytes and quality >= min_quality:
output_buffer = io.BytesIO()
img.save(
output_buffer, format=output_format, quality=quality, optimize=True
)
output_bytes = output_buffer.getvalue()
if len(output_bytes) > target_size_bytes:
quality -= 5
logger.info(
f"Optimized image '{file.filename}' from {current_size} bytes to "
f"{len(output_bytes)} bytes (quality={quality})"
)
filename = file.filename
if (
filename
and output_format.upper() == "JPEG"
and not filename.lower().endswith((".jpg", ".jpeg"))
):
filename = filename.rsplit(".", 1)[0] + ".jpg"
return ImageFile(source=FileBytes(data=output_bytes, filename=filename))
def chunk_pdf(
file: PDFFile,
max_pages: int,
*,
overlap_pages: int = 0,
) -> Iterator[PDFFile]:
"""Split a PDF into chunks of maximum page count.
Yields chunks one at a time to minimize memory usage.
Args:
file: The PDF file to chunk.
max_pages: Maximum pages per chunk.
overlap_pages: Number of overlapping pages between chunks (for context).
Yields:
PDFFile objects, one per chunk.
Raises:
ProcessingDependencyError: If pypdf is not installed.
"""
try:
from pypdf import PdfReader, PdfWriter
except ImportError as e:
raise ProcessingDependencyError(
"pypdf is required for PDF chunking",
dependency="pypdf",
install_command="pip install pypdf",
) from e
content = file.read()
reader = PdfReader(io.BytesIO(content))
total_pages = len(reader.pages)
if total_pages <= max_pages:
yield file
return
filename = file.filename or "document.pdf"
base_filename = filename.rsplit(".", 1)[0]
step = max_pages - overlap_pages
chunk_num = 0
start_page = 0
while start_page < total_pages:
end_page = min(start_page + max_pages, total_pages)
writer = PdfWriter()
for page_num in range(start_page, end_page):
writer.add_page(reader.pages[page_num])
output_buffer = io.BytesIO()
writer.write(output_buffer)
output_bytes = output_buffer.getvalue()
chunk_filename = f"{base_filename}_chunk_{chunk_num}.pdf"
logger.info(
f"Created PDF chunk '{chunk_filename}' with pages {start_page + 1}-{end_page}"
)
yield PDFFile(source=FileBytes(data=output_bytes, filename=chunk_filename))
start_page += step
chunk_num += 1
def chunk_text(
file: TextFile,
max_chars: int,
*,
overlap_chars: int = 200,
split_on_newlines: bool = True,
) -> Iterator[TextFile]:
"""Split a text file into chunks of maximum character count.
Yields chunks one at a time to minimize memory usage.
Args:
file: The text file to chunk.
max_chars: Maximum characters per chunk.
overlap_chars: Number of overlapping characters between chunks.
split_on_newlines: If True, prefer splitting at newline boundaries.
Yields:
TextFile objects, one per chunk.
"""
content = file.read()
text = content.decode(errors="replace")
total_chars = len(text)
if total_chars <= max_chars:
yield file
return
filename = file.filename or "text.txt"
base_filename = filename.rsplit(".", 1)[0]
extension = filename.rsplit(".", 1)[-1] if "." in filename else "txt"
chunk_num = 0
start_pos = 0
while start_pos < total_chars:
end_pos = min(start_pos + max_chars, total_chars)
if end_pos < total_chars and split_on_newlines:
last_newline = text.rfind("\n", start_pos, end_pos)
if last_newline > start_pos + max_chars // 2:
end_pos = last_newline + 1
chunk_content = text[start_pos:end_pos]
chunk_bytes = chunk_content.encode()
chunk_filename = f"{base_filename}_chunk_{chunk_num}.{extension}"
logger.info(
f"Created text chunk '{chunk_filename}' with {len(chunk_content)} characters"
)
yield TextFile(source=FileBytes(data=chunk_bytes, filename=chunk_filename))
if end_pos < total_chars:
start_pos = max(start_pos + 1, end_pos - overlap_chars)
else:
start_pos = total_chars
chunk_num += 1
def get_image_dimensions(file: ImageFile) -> tuple[int, int] | None:
"""Get the dimensions of an image file.
Args:
file: The image file to measure.
Returns:
Tuple of (width, height) in pixels, or None if dimensions cannot be determined.
"""
try:
from PIL import Image
except ImportError:
logger.warning("Pillow not installed - cannot get image dimensions")
return None
content = file.read()
try:
with Image.open(io.BytesIO(content)) as img:
width, height = img.size
return width, height
except Exception as e:
logger.warning(f"Failed to get image dimensions: {e}")
return None
def get_pdf_page_count(file: PDFFile) -> int | None:
"""Get the page count of a PDF file.
Args:
file: The PDF file to measure.
Returns:
Number of pages, or None if page count cannot be determined.
"""
try:
from pypdf import PdfReader
except ImportError:
logger.warning("pypdf not installed - cannot get PDF page count")
return None
content = file.read()
try:
reader = PdfReader(io.BytesIO(content))
return len(reader.pages)
except Exception as e:
logger.warning(f"Failed to get PDF page count: {e}")
return None

564
lib/crewai/src/crewai/files/processing/validators.py
View File

@@ -1,564 +0,0 @@
"""File validation functions for checking against provider constraints."""
from collections.abc import Sequence
import io
import logging
from crewai.files.content_types import (
AudioFile,
FileInput,
ImageFile,
PDFFile,
TextFile,
VideoFile,
)
from crewai.files.processing.constraints import (
AudioConstraints,
ImageConstraints,
PDFConstraints,
ProviderConstraints,
VideoConstraints,
)
from crewai.files.processing.exceptions import (
FileTooLargeError,
FileValidationError,
UnsupportedFileTypeError,
)
logger = logging.getLogger(__name__)
def _get_image_dimensions(content: bytes) -> tuple[int, int] | None:
"""Get image dimensions using Pillow if available.
Args:
content: Raw image bytes.
Returns:
Tuple of (width, height) or None if Pillow unavailable.
"""
try:
from PIL import Image
with Image.open(io.BytesIO(content)) as img:
width, height = img.size
return int(width), int(height)
except ImportError:
logger.warning(
"Pillow not installed - cannot validate image dimensions. "
"Install with: pip install Pillow"
)
return None
def _get_pdf_page_count(content: bytes) -> int | None:
"""Get PDF page count using pypdf if available.
Args:
content: Raw PDF bytes.
Returns:
Page count or None if pypdf unavailable.
"""
try:
from pypdf import PdfReader
reader = PdfReader(io.BytesIO(content))
return len(reader.pages)
except ImportError:
logger.warning(
"pypdf not installed - cannot validate PDF page count. "
"Install with: pip install pypdf"
)
return None
def _get_audio_duration(content: bytes, filename: str | None = None) -> float | None:
"""Get audio duration in seconds using tinytag if available.
Args:
content: Raw audio bytes.
filename: Optional filename for format detection hint.
Returns:
Duration in seconds or None if tinytag unavailable.
"""
try:
from tinytag import TinyTag # type: ignore[import-untyped]
except ImportError:
logger.warning(
"tinytag not installed - cannot validate audio duration. "
"Install with: pip install tinytag"
)
return None
try:
tag = TinyTag.get(file_obj=io.BytesIO(content), filename=filename)
duration: float | None = tag.duration
return duration
except Exception as e:
logger.debug(f"Could not determine audio duration: {e}")
return None
_VIDEO_FORMAT_MAP: dict[str, str] = {
"video/mp4": "mp4",
"video/webm": "webm",
"video/x-matroska": "matroska",
"video/quicktime": "mov",
"video/x-msvideo": "avi",
"video/x-flv": "flv",
}
def _get_video_duration(
content: bytes, content_type: str | None = None
) -> float | None:
"""Get video duration in seconds using av if available.
Args:
content: Raw video bytes.
content_type: Optional MIME type for format detection hint.
Returns:
Duration in seconds or None if av unavailable.
"""
try:
import av
except ImportError:
logger.warning(
"av (PyAV) not installed - cannot validate video duration. "
"Install with: pip install av"
)
return None
format_hint = _VIDEO_FORMAT_MAP.get(content_type) if content_type else None
try:
with av.open(io.BytesIO(content), format=format_hint) as container: # type: ignore[attr-defined]
duration: int | None = container.duration # type: ignore[union-attr]
if duration is None:
return None
return float(duration) / 1_000_000
except Exception as e:
logger.debug(f"Could not determine video duration: {e}")
return None
def _format_size(size_bytes: int) -> str:
"""Format byte size to human-readable string."""
if size_bytes >= 1024 * 1024 * 1024:
return f"{size_bytes / (1024 * 1024 * 1024):.1f}GB"
if size_bytes >= 1024 * 1024:
return f"{size_bytes / (1024 * 1024):.1f}MB"
if size_bytes >= 1024:
return f"{size_bytes / 1024:.1f}KB"
return f"{size_bytes}B"
def _validate_size(
file_type: str,
filename: str | None,
file_size: int,
max_size: int,
errors: list[str],
raise_on_error: bool,
) -> None:
"""Validate file size against maximum.
Args:
file_type: Type label for error messages (e.g., "Image", "PDF").
filename: Name of the file being validated.
file_size: Actual file size in bytes.
max_size: Maximum allowed size in bytes.
errors: List to append error messages to.
raise_on_error: If True, raise FileTooLargeError on failure.
"""
if file_size > max_size:
msg = (
f"{file_type} '{filename}' size ({_format_size(file_size)}) exceeds "
f"maximum ({_format_size(max_size)})"
)
errors.append(msg)
if raise_on_error:
raise FileTooLargeError(
msg,
file_name=filename,
actual_size=file_size,
max_size=max_size,
)
def _validate_format(
file_type: str,
filename: str | None,
content_type: str,
supported_formats: tuple[str, ...],
errors: list[str],
raise_on_error: bool,
) -> None:
"""Validate content type against supported formats.
Args:
file_type: Type label for error messages (e.g., "Image", "Audio").
filename: Name of the file being validated.
content_type: MIME type of the file.
supported_formats: Tuple of supported MIME types.
errors: List to append error messages to.
raise_on_error: If True, raise UnsupportedFileTypeError on failure.
"""
if content_type not in supported_formats:
msg = (
f"{file_type} format '{content_type}' is not supported. "
f"Supported: {', '.join(supported_formats)}"
)
errors.append(msg)
if raise_on_error:
raise UnsupportedFileTypeError(
msg, file_name=filename, content_type=content_type
)
def validate_image(
file: ImageFile,
constraints: ImageConstraints,
*,
raise_on_error: bool = True,
) -> Sequence[str]:
"""Validate an image file against constraints.
Args:
file: The image file to validate.
constraints: Image constraints to validate against.
raise_on_error: If True, raise exceptions on validation failure.
Returns:
List of validation error messages (empty if valid).
Raises:
FileTooLargeError: If the file exceeds size limits.
FileValidationError: If the file exceeds dimension limits.
UnsupportedFileTypeError: If the format is not supported.
"""
errors: list[str] = []
content = file.read()
file_size = len(content)
filename = file.filename
_validate_size(
"Image", filename, file_size, constraints.max_size_bytes, errors, raise_on_error
)
_validate_format(
"Image",
filename,
file.content_type,
constraints.supported_formats,
errors,
raise_on_error,
)
if constraints.max_width is not None or constraints.max_height is not None:
dimensions = _get_image_dimensions(content)
if dimensions is not None:
width, height = dimensions
if constraints.max_width and width > constraints.max_width:
msg = (
f"Image '{filename}' width ({width}px) exceeds "
f"maximum ({constraints.max_width}px)"
)
errors.append(msg)
if raise_on_error:
raise FileValidationError(msg, file_name=filename)
if constraints.max_height and height > constraints.max_height:
msg = (
f"Image '{filename}' height ({height}px) exceeds "
f"maximum ({constraints.max_height}px)"
)
errors.append(msg)
if raise_on_error:
raise FileValidationError(msg, file_name=filename)
return errors
def validate_pdf(
file: PDFFile,
constraints: PDFConstraints,
*,
raise_on_error: bool = True,
) -> Sequence[str]:
"""Validate a PDF file against constraints.
Args:
file: The PDF file to validate.
constraints: PDF constraints to validate against.
raise_on_error: If True, raise exceptions on validation failure.
Returns:
List of validation error messages (empty if valid).
Raises:
FileTooLargeError: If the file exceeds size limits.
FileValidationError: If the file exceeds page limits.
"""
errors: list[str] = []
content = file.read()
file_size = len(content)
filename = file.filename
_validate_size(
"PDF", filename, file_size, constraints.max_size_bytes, errors, raise_on_error
)
if constraints.max_pages is not None:
page_count = _get_pdf_page_count(content)
if page_count is not None and page_count > constraints.max_pages:
msg = (
f"PDF '{filename}' page count ({page_count}) exceeds "
f"maximum ({constraints.max_pages})"
)
errors.append(msg)
if raise_on_error:
raise FileValidationError(msg, file_name=filename)
return errors
def validate_audio(
file: AudioFile,
constraints: AudioConstraints,
*,
raise_on_error: bool = True,
) -> Sequence[str]:
"""Validate an audio file against constraints.
Args:
file: The audio file to validate.
constraints: Audio constraints to validate against.
raise_on_error: If True, raise exceptions on validation failure.
Returns:
List of validation error messages (empty if valid).
Raises:
FileTooLargeError: If the file exceeds size limits.
FileValidationError: If the file exceeds duration limits.
UnsupportedFileTypeError: If the format is not supported.
"""
errors: list[str] = []
content = file.read()
file_size = len(content)
filename = file.filename
_validate_size(
"Audio",
filename,
file_size,
constraints.max_size_bytes,
errors,
raise_on_error,
)
_validate_format(
"Audio",
filename,
file.content_type,
constraints.supported_formats,
errors,
raise_on_error,
)
if constraints.max_duration_seconds is not None:
duration = _get_audio_duration(content, filename)
if duration is not None and duration > constraints.max_duration_seconds:
msg = (
f"Audio '{filename}' duration ({duration:.1f}s) exceeds "
f"maximum ({constraints.max_duration_seconds}s)"
)
errors.append(msg)
if raise_on_error:
raise FileValidationError(msg, file_name=filename)
return errors
def validate_video(
file: VideoFile,
constraints: VideoConstraints,
*,
raise_on_error: bool = True,
) -> Sequence[str]:
"""Validate a video file against constraints.
Args:
file: The video file to validate.
constraints: Video constraints to validate against.
raise_on_error: If True, raise exceptions on validation failure.
Returns:
List of validation error messages (empty if valid).
Raises:
FileTooLargeError: If the file exceeds size limits.
FileValidationError: If the file exceeds duration limits.
UnsupportedFileTypeError: If the format is not supported.
"""
errors: list[str] = []
content = file.read()
file_size = len(content)
filename = file.filename
_validate_size(
"Video",
filename,
file_size,
constraints.max_size_bytes,
errors,
raise_on_error,
)
_validate_format(
"Video",
filename,
file.content_type,
constraints.supported_formats,
errors,
raise_on_error,
)
if constraints.max_duration_seconds is not None:
duration = _get_video_duration(content)
if duration is not None and duration > constraints.max_duration_seconds:
msg = (
f"Video '{filename}' duration ({duration:.1f}s) exceeds "
f"maximum ({constraints.max_duration_seconds}s)"
)
errors.append(msg)
if raise_on_error:
raise FileValidationError(msg, file_name=filename)
return errors
def validate_text(
file: TextFile,
constraints: ProviderConstraints,
*,
raise_on_error: bool = True,
) -> Sequence[str]:
"""Validate a text file against general constraints.
Args:
file: The text file to validate.
constraints: Provider constraints to validate against.
raise_on_error: If True, raise exceptions on validation failure.
Returns:
List of validation error messages (empty if valid).
Raises:
FileTooLargeError: If the file exceeds size limits.
"""
errors: list[str] = []
if constraints.general_max_size_bytes is None:
return errors
file_size = len(file.read())
_validate_size(
"Text file",
file.filename,
file_size,
constraints.general_max_size_bytes,
errors,
raise_on_error,
)
return errors
def _check_unsupported_type(
file: FileInput,
provider_name: str,
type_name: str,
raise_on_error: bool,
) -> Sequence[str]:
"""Check if file type is unsupported and handle error.
Args:
file: The file being validated.
provider_name: Name of the provider.
type_name: Name of the file type (e.g., "images", "PDFs").
raise_on_error: If True, raise exception instead of returning errors.
Returns:
List with error message (only returns when raise_on_error is False).
Raises:
UnsupportedFileTypeError: If raise_on_error is True.
"""
msg = f"Provider '{provider_name}' does not support {type_name}"
if raise_on_error:
raise UnsupportedFileTypeError(
msg, file_name=file.filename, content_type=file.content_type
)
return [msg]
def validate_file(
file: FileInput,
constraints: ProviderConstraints,
*,
raise_on_error: bool = True,
) -> Sequence[str]:
"""Validate a file against provider constraints.
Dispatches to the appropriate validator based on file type.
Args:
file: The file to validate.
constraints: Provider constraints to validate against.
raise_on_error: If True, raise exceptions on validation failure.
Returns:
List of validation error messages (empty if valid).
Raises:
FileTooLargeError: If the file exceeds size limits.
FileValidationError: If the file fails other validation checks.
UnsupportedFileTypeError: If the file type is not supported.
"""
if isinstance(file, ImageFile):
if constraints.image is None:
return _check_unsupported_type(
file, constraints.name, "images", raise_on_error
)
return validate_image(file, constraints.image, raise_on_error=raise_on_error)
if isinstance(file, PDFFile):
if constraints.pdf is None:
return _check_unsupported_type(
file, constraints.name, "PDFs", raise_on_error
)
return validate_pdf(file, constraints.pdf, raise_on_error=raise_on_error)
if isinstance(file, AudioFile):
if constraints.audio is None:
return _check_unsupported_type(
file, constraints.name, "audio", raise_on_error
)
return validate_audio(file, constraints.audio, raise_on_error=raise_on_error)
if isinstance(file, VideoFile):
if constraints.video is None:
return _check_unsupported_type(
file, constraints.name, "video", raise_on_error
)
return validate_video(file, constraints.video, raise_on_error=raise_on_error)
if isinstance(file, TextFile):
return validate_text(file, constraints, raise_on_error=raise_on_error)
return []

84
lib/crewai/src/crewai/files/resolved.py
View File

@@ -1,84 +0,0 @@
"""Resolved file types representing different delivery methods for file content."""
from abc import ABC
from dataclasses import dataclass
from datetime import datetime
@dataclass(frozen=True)
class ResolvedFile(ABC):
"""Base class for resolved file representations.
A ResolvedFile represents the final form of a file ready for delivery
to an LLM provider, whether inline or via reference.
Attributes:
content_type: MIME type of the file content.
"""
content_type: str
@dataclass(frozen=True)
class InlineBase64(ResolvedFile):
"""File content encoded as base64 string.
Used by most providers for inline file content in messages.
Attributes:
content_type: MIME type of the file content.
data: Base64-encoded file content.
"""
data: str
@dataclass(frozen=True)
class InlineBytes(ResolvedFile):
"""File content as raw bytes.
Used by providers like Bedrock that accept raw bytes instead of base64.
Attributes:
content_type: MIME type of the file content.
data: Raw file bytes.
"""
data: bytes
@dataclass(frozen=True)
class FileReference(ResolvedFile):
"""Reference to an uploaded file.
Used when files are uploaded via provider File APIs.
Attributes:
content_type: MIME type of the file content.
file_id: Provider-specific file identifier.
provider: Name of the provider the file was uploaded to.
expires_at: When the uploaded file expires (if applicable).
file_uri: Optional URI for accessing the file (used by Gemini).
"""
file_id: str
provider: str
expires_at: datetime | None = None
file_uri: str | None = None
@dataclass(frozen=True)
class UrlReference(ResolvedFile):
"""Reference to a file accessible via URL.
Used by providers that support fetching files from URLs.
Attributes:
content_type: MIME type of the file content.
url: URL where the file can be accessed.
"""
url: str
ResolvedFileType = InlineBase64 | InlineBytes | FileReference | UrlReference

670
lib/crewai/src/crewai/files/resolver.py
View File

@@ -1,670 +0,0 @@
"""FileResolver for deciding file delivery method and managing uploads."""
import asyncio
import base64
from dataclasses import dataclass, field
import hashlib
import logging
from crewai.files.constants import UPLOAD_MAX_RETRIES, UPLOAD_RETRY_DELAY_BASE
from crewai.files.content_types import FileInput
from crewai.files.file import FileUrl
from crewai.files.metrics import measure_operation
from crewai.files.processing.constraints import (
AudioConstraints,
ImageConstraints,
PDFConstraints,
ProviderConstraints,
VideoConstraints,
get_constraints_for_provider,
)
from crewai.files.resolved import (
FileReference,
InlineBase64,
InlineBytes,
ResolvedFile,
UrlReference,
)
from crewai.files.upload_cache import CachedUpload, UploadCache
from crewai.files.uploaders import UploadResult, get_uploader
from crewai.files.uploaders.base import FileUploader
from crewai.files.uploaders.factory import ProviderType
logger = logging.getLogger(__name__)
@dataclass
class FileContext:
"""Cached file metadata to avoid redundant reads.
Attributes:
content: Raw file bytes.
size: Size of the file in bytes.
content_hash: SHA-256 hash of the file content.
content_type: MIME type of the file.
"""
content: bytes
size: int
content_hash: str
content_type: str
@dataclass
class FileResolverConfig:
"""Configuration for FileResolver.
Attributes:
prefer_upload: If True, prefer uploading over inline for supported providers.
upload_threshold_bytes: Size threshold above which to use upload.
If None, uses provider-specific threshold.
use_bytes_for_bedrock: If True, use raw bytes instead of base64 for Bedrock.
"""
prefer_upload: bool = False
upload_threshold_bytes: int | None = None
use_bytes_for_bedrock: bool = True
@dataclass
class FileResolver:
"""Resolves files to their delivery format based on provider capabilities.
Decides whether to use inline base64, raw bytes, or file upload based on:
- Provider constraints and capabilities
- File size
- Configuration preferences
Caches uploaded files to avoid redundant uploads.
Attributes:
config: Resolver configuration.
upload_cache: Cache for tracking uploaded files.
"""
config: FileResolverConfig = field(default_factory=FileResolverConfig)
upload_cache: UploadCache | None = None
_uploaders: dict[str, FileUploader] = field(default_factory=dict)
@staticmethod
def _build_file_context(file: FileInput) -> FileContext:
"""Build context by reading file once.
Args:
file: The file to build context for.
Returns:
FileContext with cached metadata.
"""
content = file.read()
return FileContext(
content=content,
size=len(content),
content_hash=hashlib.sha256(content).hexdigest(),
content_type=file.content_type,
)
@staticmethod
def _is_url_source(file: FileInput) -> bool:
"""Check if file source is a URL.
Args:
file: The file to check.
Returns:
True if the file source is a FileUrl, False otherwise.
"""
return isinstance(file._file_source, FileUrl)
@staticmethod
def _supports_url(constraints: ProviderConstraints | None) -> bool:
"""Check if provider supports URL references.
Args:
constraints: Provider constraints.
Returns:
True if the provider supports URL references, False otherwise.
"""
return constraints is not None and constraints.supports_url_references
@staticmethod
def _resolve_as_url(file: FileInput) -> UrlReference:
"""Resolve a URL source as UrlReference.
Args:
file: The file with URL source.
Returns:
UrlReference with the URL and content type.
"""
source = file._file_source
if not isinstance(source, FileUrl):
raise TypeError(f"Expected FileUrl source, got {type(source).__name__}")
return UrlReference(
content_type=file.content_type,
url=source.url,
)
def resolve(self, file: FileInput, provider: ProviderType) -> ResolvedFile:
"""Resolve a file to its delivery format for a provider.
Args:
file: The file to resolve.
provider: Provider name (e.g., "gemini", "anthropic", "openai").
Returns:
ResolvedFile representing the appropriate delivery format.
"""
constraints = get_constraints_for_provider(provider)
if self._is_url_source(file) and self._supports_url(constraints):
return self._resolve_as_url(file)
context = self._build_file_context(file)
should_upload = self._should_upload(file, provider, constraints, context.size)
if should_upload:
resolved = self._resolve_via_upload(file, provider, context)
if resolved is not None:
return resolved
return self._resolve_inline(file, provider, context)
def resolve_files(
self,
files: dict[str, FileInput],
provider: ProviderType,
) -> dict[str, ResolvedFile]:
"""Resolve multiple files for a provider.
Args:
files: Dictionary mapping names to file inputs.
provider: Provider name.
Returns:
Dictionary mapping names to resolved files.
"""
return {name: self.resolve(file, provider) for name, file in files.items()}
@staticmethod
def _get_type_constraint(
content_type: str,
constraints: ProviderConstraints,
) -> ImageConstraints | PDFConstraints | AudioConstraints | VideoConstraints | None:
"""Get type-specific constraint based on content type.
Args:
content_type: MIME type of the file.
constraints: Provider constraints.
Returns:
Type-specific constraint or None if not found.
"""
if content_type.startswith("image/"):
return constraints.image
if content_type == "application/pdf":
return constraints.pdf
if content_type.startswith("audio/"):
return constraints.audio
if content_type.startswith("video/"):
return constraints.video
return None
def _should_upload(
self,
file: FileInput,
provider: str,
constraints: ProviderConstraints | None,
file_size: int,
) -> bool:
"""Determine if a file should be uploaded rather than inlined.
Uses type-specific constraints to make smarter decisions:
- Checks if file exceeds type-specific inline size limits
- Falls back to general threshold if no type-specific constraint
Args:
file: The file to check.
provider: Provider name.
constraints: Provider constraints.
file_size: Size of the file in bytes.
Returns:
True if the file should be uploaded, False otherwise.
"""
if constraints is None or not constraints.supports_file_upload:
return False
if self.config.prefer_upload:
return True
content_type = file.content_type
type_constraint = self._get_type_constraint(content_type, constraints)
if type_constraint is not None:
# Check if file exceeds type-specific inline limit
if file_size > type_constraint.max_size_bytes:
logger.debug(
f"File {file.filename} ({file_size}B) exceeds {content_type} "
f"inline limit ({type_constraint.max_size_bytes}B) for {provider}"
)
return True
# Fall back to general threshold
threshold = self.config.upload_threshold_bytes
if threshold is None:
threshold = constraints.file_upload_threshold_bytes
if threshold is not None and file_size > threshold:
return True
return False
def _resolve_via_upload(
self,
file: FileInput,
provider: ProviderType,
context: FileContext,
) -> ResolvedFile | None:
"""Resolve a file by uploading it.
Args:
file: The file to upload.
provider: Provider name.
context: Pre-computed file context.
Returns:
FileReference if upload succeeds, None otherwise.
"""
if self.upload_cache is not None:
cached = self.upload_cache.get_by_hash(context.content_hash, provider)
if cached is not None:
logger.debug(
f"Using cached upload for {file.filename}: {cached.file_id}"
)
return FileReference(
content_type=cached.content_type,
file_id=cached.file_id,
provider=cached.provider,
expires_at=cached.expires_at,
file_uri=cached.file_uri,
)
uploader = self._get_uploader(provider)
if uploader is None:
logger.debug(f"No uploader available for {provider}")
return None
result = self._upload_with_retry(uploader, file, provider, context.size)
if result is None:
return None
if self.upload_cache is not None:
self.upload_cache.set_by_hash(
file_hash=context.content_hash,
content_type=context.content_type,
provider=provider,
file_id=result.file_id,
file_uri=result.file_uri,
expires_at=result.expires_at,
)
return FileReference(
content_type=result.content_type,
file_id=result.file_id,
provider=result.provider,
expires_at=result.expires_at,
file_uri=result.file_uri,
)
@staticmethod
def _upload_with_retry(
uploader: FileUploader,
file: FileInput,
provider: str,
file_size: int,
) -> UploadResult | None:
"""Upload with exponential backoff retry.
Args:
uploader: The uploader to use.
file: The file to upload.
provider: Provider name for logging.
file_size: Size of the file in bytes.
Returns:
UploadResult if successful, None otherwise.
"""
import time
from crewai.files.processing.exceptions import (
PermanentUploadError,
TransientUploadError,
)
last_error: Exception | None = None
for attempt in range(UPLOAD_MAX_RETRIES):
with measure_operation(
"upload",
filename=file.filename,
provider=provider,
size_bytes=file_size,
attempt=attempt + 1,
) as metrics:
try:
result = uploader.upload(file)
metrics.metadata["file_id"] = result.file_id
return result
except PermanentUploadError as e:
metrics.metadata["error_type"] = "permanent"
logger.warning(
f"Non-retryable upload error for {file.filename}: {e}"
)
return None
except TransientUploadError as e:
metrics.metadata["error_type"] = "transient"
last_error = e
except Exception as e:
metrics.metadata["error_type"] = "unknown"
last_error = e
if attempt < UPLOAD_MAX_RETRIES - 1:
delay = UPLOAD_RETRY_DELAY_BASE**attempt
logger.debug(
f"Retrying upload for {file.filename} in {delay}s (attempt {attempt + 1})"
)
time.sleep(delay)
logger.warning(
f"Upload failed for {file.filename} to {provider} after {UPLOAD_MAX_RETRIES} attempts: {last_error}"
)
return None
def _resolve_inline(
self,
file: FileInput,
provider: str,
context: FileContext,
) -> ResolvedFile:
"""Resolve a file as inline content.
Args:
file: The file to resolve (used for logging).
provider: Provider name.
context: Pre-computed file context.
Returns:
InlineBase64 or InlineBytes depending on provider.
"""
logger.debug(f"Resolving {file.filename} as inline for {provider}")
if self.config.use_bytes_for_bedrock and "bedrock" in provider:
return InlineBytes(
content_type=context.content_type,
data=context.content,
)
encoded = base64.b64encode(context.content).decode("ascii")
return InlineBase64(
content_type=context.content_type,
data=encoded,
)
async def aresolve(self, file: FileInput, provider: ProviderType) -> ResolvedFile:
"""Async resolve a file to its delivery format for a provider.
Args:
file: The file to resolve.
provider: Provider name (e.g., "gemini", "anthropic", "openai").
Returns:
ResolvedFile representing the appropriate delivery format.
"""
constraints = get_constraints_for_provider(provider)
if self._is_url_source(file) and self._supports_url(constraints):
return self._resolve_as_url(file)
context = self._build_file_context(file)
should_upload = self._should_upload(file, provider, constraints, context.size)
if should_upload:
resolved = await self._aresolve_via_upload(file, provider, context)
if resolved is not None:
return resolved
return self._resolve_inline(file, provider, context)
async def aresolve_files(
self,
files: dict[str, FileInput],
provider: ProviderType,
max_concurrency: int = 10,
) -> dict[str, ResolvedFile]:
"""Async resolve multiple files in parallel.
Args:
files: Dictionary mapping names to file inputs.
provider: Provider name.
max_concurrency: Maximum number of concurrent resolutions.
Returns:
Dictionary mapping names to resolved files.
"""
semaphore = asyncio.Semaphore(max_concurrency)
async def resolve_single(
entry_key: str, input_file: FileInput
) -> tuple[str, ResolvedFile]:
"""Resolve a single file with semaphore limiting."""
async with semaphore:
entry_resolved = await self.aresolve(input_file, provider)
return entry_key, entry_resolved
tasks = [resolve_single(n, f) for n, f in files.items()]
gather_results = await asyncio.gather(*tasks, return_exceptions=True)
output: dict[str, ResolvedFile] = {}
for item in gather_results:
if isinstance(item, BaseException):
logger.error(f"Resolution failed: {item}")
continue
key, resolved = item
output[key] = resolved
return output
async def _aresolve_via_upload(
self,
file: FileInput,
provider: ProviderType,
context: FileContext,
) -> ResolvedFile | None:
"""Async resolve a file by uploading it.
Args:
file: The file to upload.
provider: Provider name.
context: Pre-computed file context.
Returns:
FileReference if upload succeeds, None otherwise.
"""
if self.upload_cache is not None:
cached = await self.upload_cache.aget_by_hash(
context.content_hash, provider
)
if cached is not None:
logger.debug(
f"Using cached upload for {file.filename}: {cached.file_id}"
)
return FileReference(
content_type=cached.content_type,
file_id=cached.file_id,
provider=cached.provider,
expires_at=cached.expires_at,
file_uri=cached.file_uri,
)
uploader = self._get_uploader(provider)
if uploader is None:
logger.debug(f"No uploader available for {provider}")
return None
result = await self._aupload_with_retry(uploader, file, provider, context.size)
if result is None:
return None
if self.upload_cache is not None:
await self.upload_cache.aset_by_hash(
file_hash=context.content_hash,
content_type=context.content_type,
provider=provider,
file_id=result.file_id,
file_uri=result.file_uri,
expires_at=result.expires_at,
)
return FileReference(
content_type=result.content_type,
file_id=result.file_id,
provider=result.provider,
expires_at=result.expires_at,
file_uri=result.file_uri,
)
@staticmethod
async def _aupload_with_retry(
uploader: FileUploader,
file: FileInput,
provider: str,
file_size: int,
) -> UploadResult | None:
"""Async upload with exponential backoff retry.
Args:
uploader: The uploader to use.
file: The file to upload.
provider: Provider name for logging.
file_size: Size of the file in bytes.
Returns:
UploadResult if successful, None otherwise.
"""
from crewai.files.processing.exceptions import (
PermanentUploadError,
TransientUploadError,
)
last_error: Exception | None = None
for attempt in range(UPLOAD_MAX_RETRIES):
with measure_operation(
"upload",
filename=file.filename,
provider=provider,
size_bytes=file_size,
attempt=attempt + 1,
) as metrics:
try:
result = await uploader.aupload(file)
metrics.metadata["file_id"] = result.file_id
return result
except PermanentUploadError as e:
metrics.metadata["error_type"] = "permanent"
logger.warning(
f"Non-retryable upload error for {file.filename}: {e}"
)
return None
except TransientUploadError as e:
metrics.metadata["error_type"] = "transient"
last_error = e
except Exception as e:
metrics.metadata["error_type"] = "unknown"
last_error = e
if attempt < UPLOAD_MAX_RETRIES - 1:
delay = UPLOAD_RETRY_DELAY_BASE**attempt
logger.debug(
f"Retrying upload for {file.filename} in {delay}s (attempt {attempt + 1})"
)
await asyncio.sleep(delay)
logger.warning(
f"Upload failed for {file.filename} to {provider} after {UPLOAD_MAX_RETRIES} attempts: {last_error}"
)
return None
def _get_uploader(self, provider: ProviderType) -> FileUploader | None:
"""Get or create an uploader for a provider.
Args:
provider: Provider name.
Returns:
FileUploader instance or None if not available.
"""
if provider not in self._uploaders:
uploader = get_uploader(provider)
if uploader is not None:
self._uploaders[provider] = uploader
else:
return None
return self._uploaders.get(provider)
def get_cached_uploads(self, provider: str) -> list[CachedUpload]:
"""Get all cached uploads for a provider.
Args:
provider: Provider name.
Returns:
List of cached uploads.
"""
if self.upload_cache is None:
return []
return self.upload_cache.get_all_for_provider(provider)
def clear_cache(self) -> None:
"""Clear the upload cache."""
if self.upload_cache is not None:
self.upload_cache.clear()
def create_resolver(
provider: str | None = None,
prefer_upload: bool = False,
upload_threshold_bytes: int | None = None,
enable_cache: bool = True,
) -> FileResolver:
"""Create a configured FileResolver.
Args:
provider: Optional provider name to load default threshold from constraints.
prefer_upload: Whether to prefer upload over inline.
upload_threshold_bytes: Size threshold for using upload. If None and
provider is specified, uses provider's default threshold.
enable_cache: Whether to enable upload caching.
Returns:
Configured FileResolver instance.
"""
threshold = upload_threshold_bytes
if threshold is None and provider is not None:
constraints = get_constraints_for_provider(provider)
if constraints is not None:
threshold = constraints.file_upload_threshold_bytes
config = FileResolverConfig(
prefer_upload=prefer_upload,
upload_threshold_bytes=threshold,
)
cache = UploadCache() if enable_cache else None
return FileResolver(config=config, upload_cache=cache)

546
lib/crewai/src/crewai/files/upload_cache.py
View File

@@ -1,546 +0,0 @@
"""Cache for tracking uploaded files using aiocache."""
from __future__ import annotations
import asyncio
import atexit
import builtins
from collections.abc import Iterator
from dataclasses import dataclass
from datetime import datetime, timezone
import hashlib
import logging
from typing import TYPE_CHECKING, Any
from aiocache import Cache # type: ignore[import-untyped]
from aiocache.serializers import PickleSerializer # type: ignore[import-untyped]
from crewai.files.constants import DEFAULT_MAX_CACHE_ENTRIES, DEFAULT_TTL_SECONDS
if TYPE_CHECKING:
from crewai.files.content_types import FileInput
logger = logging.getLogger(__name__)
@dataclass
class CachedUpload:
"""Represents a cached file upload.
Attributes:
file_id: Provider-specific file identifier.
provider: Name of the provider.
file_uri: Optional URI for accessing the file.
content_type: MIME type of the uploaded file.
uploaded_at: When the file was uploaded.
expires_at: When the upload expires (if applicable).
"""
file_id: str
provider: str
file_uri: str | None
content_type: str
uploaded_at: datetime
expires_at: datetime | None = None
def is_expired(self) -> bool:
"""Check if this cached upload has expired."""
if self.expires_at is None:
return False
return datetime.now(timezone.utc) >= self.expires_at
def _make_key(file_hash: str, provider: str) -> str:
"""Create a cache key from file hash and provider."""
return f"upload:{provider}:{file_hash}"
def _compute_file_hash_streaming(chunks: Iterator[bytes]) -> str:
"""Compute SHA-256 hash from streaming chunks.
Args:
chunks: Iterator of byte chunks.
Returns:
Hexadecimal hash string.
"""
hasher = hashlib.sha256()
for chunk in chunks:
hasher.update(chunk)
return hasher.hexdigest()
def _compute_file_hash(file: FileInput) -> str:
"""Compute SHA-256 hash of file content.
Uses streaming for FilePath sources to avoid loading large files into memory.
"""
from crewai.files.file import FilePath
source = file._file_source
if isinstance(source, FilePath):
return _compute_file_hash_streaming(source.read_chunks(chunk_size=1024 * 1024))
content = file.read()
return hashlib.sha256(content).hexdigest()
class UploadCache:
"""Async cache for tracking uploaded files using aiocache.
Supports in-memory caching by default, with optional Redis backend
for distributed setups.
Attributes:
ttl: Default time-to-live in seconds for cached entries.
namespace: Cache namespace for isolation.
"""
def __init__(
self,
ttl: int = DEFAULT_TTL_SECONDS,
namespace: str = "crewai_uploads",
cache_type: str = "memory",
max_entries: int | None = DEFAULT_MAX_CACHE_ENTRIES,
**cache_kwargs: Any,
) -> None:
"""Initialize the upload cache.
Args:
ttl: Default TTL in seconds.
namespace: Cache namespace.
cache_type: Backend type ("memory" or "redis").
max_entries: Maximum cache entries (None for unlimited).
**cache_kwargs: Additional args for cache backend.
"""
self.ttl = ttl
self.namespace = namespace
self.max_entries = max_entries
self._provider_keys: dict[str, set[str]] = {}
self._key_access_order: list[str] = []
if cache_type == "redis":
self._cache = Cache(
Cache.REDIS,
serializer=PickleSerializer(),
namespace=namespace,
**cache_kwargs,
)
else:
self._cache = Cache(
serializer=PickleSerializer(),
namespace=namespace,
)
def _track_key(self, provider: str, key: str) -> None:
"""Track a key for a provider (for cleanup) and access order."""
if provider not in self._provider_keys:
self._provider_keys[provider] = set()
self._provider_keys[provider].add(key)
if key in self._key_access_order:
self._key_access_order.remove(key)
self._key_access_order.append(key)
def _untrack_key(self, provider: str, key: str) -> None:
"""Remove key tracking for a provider."""
if provider in self._provider_keys:
self._provider_keys[provider].discard(key)
if key in self._key_access_order:
self._key_access_order.remove(key)
async def _evict_if_needed(self) -> int:
"""Evict oldest entries if limit exceeded.
Returns:
Number of entries evicted.
"""
if self.max_entries is None:
return 0
current_count = len(self)
if current_count < self.max_entries:
return 0
to_evict = max(1, self.max_entries // 10)
return await self._evict_oldest(to_evict)
async def _evict_oldest(self, count: int) -> int:
"""Evict the oldest entries from the cache.
Args:
count: Number of entries to evict.
Returns:
Number of entries actually evicted.
"""
evicted = 0
keys_to_evict = self._key_access_order[:count]
for key in keys_to_evict:
await self._cache.delete(key)
self._key_access_order.remove(key)
for provider_keys in self._provider_keys.values():
provider_keys.discard(key)
evicted += 1
if evicted > 0:
logger.debug(f"Evicted {evicted} oldest cache entries")
return evicted
async def aget(self, file: FileInput, provider: str) -> CachedUpload | None:
"""Get a cached upload for a file.
Args:
file: The file to look up.
provider: The provider name.
Returns:
Cached upload if found and not expired, None otherwise.
"""
file_hash = _compute_file_hash(file)
return await self.aget_by_hash(file_hash, provider)
async def aget_by_hash(self, file_hash: str, provider: str) -> CachedUpload | None:
"""Get a cached upload by file hash.
Args:
file_hash: Hash of the file content.
provider: The provider name.
Returns:
Cached upload if found and not expired, None otherwise.
"""
key = _make_key(file_hash, provider)
result = await self._cache.get(key)
if result is None:
return None
if isinstance(result, CachedUpload):
if result.is_expired():
await self._cache.delete(key)
self._untrack_key(provider, key)
return None
return result
return None
async def aset(
self,
file: FileInput,
provider: str,
file_id: str,
file_uri: str | None = None,
expires_at: datetime | None = None,
) -> CachedUpload:
"""Cache an uploaded file.
Args:
file: The file that was uploaded.
provider: The provider name.
file_id: Provider-specific file identifier.
file_uri: Optional URI for accessing the file.
expires_at: When the upload expires.
Returns:
The created cache entry.
"""
file_hash = _compute_file_hash(file)
return await self.aset_by_hash(
file_hash=file_hash,
content_type=file.content_type,
provider=provider,
file_id=file_id,
file_uri=file_uri,
expires_at=expires_at,
)
async def aset_by_hash(
self,
file_hash: str,
content_type: str,
provider: str,
file_id: str,
file_uri: str | None = None,
expires_at: datetime | None = None,
) -> CachedUpload:
"""Cache an uploaded file by hash.
Args:
file_hash: Hash of the file content.
content_type: MIME type of the file.
provider: The provider name.
file_id: Provider-specific file identifier.
file_uri: Optional URI for accessing the file.
expires_at: When the upload expires.
Returns:
The created cache entry.
"""
await self._evict_if_needed()
key = _make_key(file_hash, provider)
now = datetime.now(timezone.utc)
cached = CachedUpload(
file_id=file_id,
provider=provider,
file_uri=file_uri,
content_type=content_type,
uploaded_at=now,
expires_at=expires_at,
)
ttl = self.ttl
if expires_at is not None:
ttl = max(0, int((expires_at - now).total_seconds()))
await self._cache.set(key, cached, ttl=ttl)
self._track_key(provider, key)
logger.debug(f"Cached upload: {file_id} for provider {provider}")
return cached
async def aremove(self, file: FileInput, provider: str) -> bool:
"""Remove a cached upload.
Args:
file: The file to remove.
provider: The provider name.
Returns:
True if entry was removed, False if not found.
"""
file_hash = _compute_file_hash(file)
key = _make_key(file_hash, provider)
result = await self._cache.delete(key)
removed = bool(result > 0 if isinstance(result, int) else result)
if removed:
self._untrack_key(provider, key)
return removed
async def aremove_by_file_id(self, file_id: str, provider: str) -> bool:
"""Remove a cached upload by file ID.
Args:
file_id: The file ID to remove.
provider: The provider name.
Returns:
True if entry was removed, False if not found.
"""
if provider not in self._provider_keys:
return False
for key in list(self._provider_keys[provider]):
cached = await self._cache.get(key)
if isinstance(cached, CachedUpload) and cached.file_id == file_id:
await self._cache.delete(key)
self._untrack_key(provider, key)
return True
return False
async def aclear_expired(self) -> int:
"""Remove all expired entries from the cache.
Returns:
Number of entries removed.
"""
removed = 0
for provider, keys in list(self._provider_keys.items()):
for key in list(keys):
cached = await self._cache.get(key)
if cached is None or (
isinstance(cached, CachedUpload) and cached.is_expired()
):
await self._cache.delete(key)
self._untrack_key(provider, key)
removed += 1
if removed > 0:
logger.debug(f"Cleared {removed} expired cache entries")
return removed
async def aclear(self) -> int:
"""Clear all entries from the cache.
Returns:
Number of entries cleared.
"""
count = sum(len(keys) for keys in self._provider_keys.values())
await self._cache.clear(namespace=self.namespace)
self._provider_keys.clear()
if count > 0:
logger.debug(f"Cleared {count} cache entries")
return count
async def aget_all_for_provider(self, provider: str) -> list[CachedUpload]:
"""Get all cached uploads for a provider.
Args:
provider: The provider name.
Returns:
List of cached uploads for the provider.
"""
if provider not in self._provider_keys:
return []
results: list[CachedUpload] = []
for key in list(self._provider_keys[provider]):
cached = await self._cache.get(key)
if isinstance(cached, CachedUpload) and not cached.is_expired():
results.append(cached)
return results
@staticmethod
def _run_sync(coro: Any) -> Any:
"""Run an async coroutine from sync context without blocking event loop."""
try:
loop = asyncio.get_running_loop()
except RuntimeError:
loop = None
if loop is not None and loop.is_running():
future = asyncio.run_coroutine_threadsafe(coro, loop)
return future.result(timeout=30)
return asyncio.run(coro)
def get(self, file: FileInput, provider: str) -> CachedUpload | None:
"""Sync wrapper for aget."""
result: CachedUpload | None = self._run_sync(self.aget(file, provider))
return result
def get_by_hash(self, file_hash: str, provider: str) -> CachedUpload | None:
"""Sync wrapper for aget_by_hash."""
result: CachedUpload | None = self._run_sync(
self.aget_by_hash(file_hash, provider)
)
return result
def set(
self,
file: FileInput,
provider: str,
file_id: str,
file_uri: str | None = None,
expires_at: datetime | None = None,
) -> CachedUpload:
"""Sync wrapper for aset."""
result: CachedUpload = self._run_sync(
self.aset(file, provider, file_id, file_uri, expires_at)
)
return result
def set_by_hash(
self,
file_hash: str,
content_type: str,
provider: str,
file_id: str,
file_uri: str | None = None,
expires_at: datetime | None = None,
) -> CachedUpload:
"""Sync wrapper for aset_by_hash."""
result: CachedUpload = self._run_sync(
self.aset_by_hash(
file_hash, content_type, provider, file_id, file_uri, expires_at
)
)
return result
def remove(self, file: FileInput, provider: str) -> bool:
"""Sync wrapper for aremove."""
result: bool = self._run_sync(self.aremove(file, provider))
return result
def remove_by_file_id(self, file_id: str, provider: str) -> bool:
"""Sync wrapper for aremove_by_file_id."""
result: bool = self._run_sync(self.aremove_by_file_id(file_id, provider))
return result
def clear_expired(self) -> int:
"""Sync wrapper for aclear_expired."""
result: int = self._run_sync(self.aclear_expired())
return result
def clear(self) -> int:
"""Sync wrapper for aclear."""
result: int = self._run_sync(self.aclear())
return result
def get_all_for_provider(self, provider: str) -> list[CachedUpload]:
"""Sync wrapper for aget_all_for_provider."""
result: list[CachedUpload] = self._run_sync(
self.aget_all_for_provider(provider)
)
return result
def __len__(self) -> int:
"""Return the number of cached entries."""
return sum(len(keys) for keys in self._provider_keys.values())
def get_providers(self) -> builtins.set[str]:
"""Get all provider names that have cached entries.
Returns:
Set of provider names.
"""
return builtins.set(self._provider_keys.keys())
_default_cache: UploadCache | None = None
def get_upload_cache(
ttl: int = DEFAULT_TTL_SECONDS,
namespace: str = "crewai_uploads",
cache_type: str = "memory",
**cache_kwargs: Any,
) -> UploadCache:
"""Get or create the default upload cache.
Args:
ttl: Default TTL in seconds.
namespace: Cache namespace.
cache_type: Backend type ("memory" or "redis").
**cache_kwargs: Additional args for cache backend.
Returns:
The upload cache instance.
"""
global _default_cache
if _default_cache is None:
_default_cache = UploadCache(
ttl=ttl,
namespace=namespace,
cache_type=cache_type,
**cache_kwargs,
)
return _default_cache
def reset_upload_cache() -> None:
"""Reset the default upload cache (useful for testing)."""
global _default_cache
if _default_cache is not None:
_default_cache.clear()
_default_cache = None
def _cleanup_on_exit() -> None:
"""Clean up uploaded files on process exit."""
global _default_cache
if _default_cache is None or len(_default_cache) == 0:
return
from crewai.files.cleanup import cleanup_uploaded_files
try:
cleanup_uploaded_files(_default_cache)
except Exception as e:
logger.debug(f"Error during exit cleanup: {e}")
atexit.register(_cleanup_on_exit)

11
lib/crewai/src/crewai/files/uploaders/__init__.py
View File

@@ -1,11 +0,0 @@
"""File uploader implementations for provider File APIs."""
from crewai.files.uploaders.base import FileUploader, UploadResult
from crewai.files.uploaders.factory import get_uploader
__all__ = [
"FileUploader",
"UploadResult",
"get_uploader",
]

241
lib/crewai/src/crewai/files/uploaders/anthropic.py
View File

@@ -1,241 +0,0 @@
"""Anthropic Files API uploader implementation."""
from __future__ import annotations
import io
import logging
import os
from typing import Any
from crewai.files.content_types import FileInput
from crewai.files.processing.exceptions import classify_upload_error
from crewai.files.uploaders.base import FileUploader, UploadResult
logger = logging.getLogger(__name__)
class AnthropicFileUploader(FileUploader):
"""Uploader for Anthropic Files API.
Uses the anthropic SDK to upload files. Files are stored persistently
until explicitly deleted.
"""
def __init__(self, api_key: str | None = None) -> None:
"""Initialize the Anthropic uploader.
Args:
api_key: Optional Anthropic API key. If not provided, uses
ANTHROPIC_API_KEY environment variable.
"""
self._api_key = api_key or os.environ.get("ANTHROPIC_API_KEY")
self._client: Any = None
self._async_client: Any = None
@property
def provider_name(self) -> str:
"""Return the provider name."""
return "anthropic"
def _get_client(self) -> Any:
"""Get or create the Anthropic client."""
if self._client is None:
try:
import anthropic
self._client = anthropic.Anthropic(api_key=self._api_key)
except ImportError as e:
raise ImportError(
"anthropic is required for Anthropic file uploads. "
"Install with: pip install anthropic"
) from e
return self._client
def _get_async_client(self) -> Any:
"""Get or create the async Anthropic client."""
if self._async_client is None:
try:
import anthropic
self._async_client = anthropic.AsyncAnthropic(api_key=self._api_key)
except ImportError as e:
raise ImportError(
"anthropic is required for Anthropic file uploads. "
"Install with: pip install anthropic"
) from e
return self._async_client
def upload(self, file: FileInput, purpose: str | None = None) -> UploadResult:
"""Upload a file to Anthropic.
Args:
file: The file to upload.
purpose: Optional purpose for the file (default: "user_upload").
Returns:
UploadResult with the file ID and metadata.
Raises:
TransientUploadError: For retryable errors (network, rate limits).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
try:
client = self._get_client()
content = file.read()
file_purpose = purpose or "user_upload"
file_data = io.BytesIO(content)
logger.info(
f"Uploading file '{file.filename}' to Anthropic ({len(content)} bytes)"
)
uploaded_file = client.files.create(
file=(file.filename, file_data, file.content_type),
purpose=file_purpose,
)
logger.info(f"Uploaded to Anthropic: {uploaded_file.id}")
return UploadResult(
file_id=uploaded_file.id,
file_uri=None,
content_type=file.content_type,
expires_at=None,
provider=self.provider_name,
)
except ImportError:
raise
except Exception as e:
raise classify_upload_error(e, file.filename) from e
def delete(self, file_id: str) -> bool:
"""Delete an uploaded file from Anthropic.
Args:
file_id: The file ID to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
client = self._get_client()
client.files.delete(file_id=file_id)
logger.info(f"Deleted Anthropic file: {file_id}")
return True
except Exception as e:
logger.warning(f"Failed to delete Anthropic file {file_id}: {e}")
return False
def get_file_info(self, file_id: str) -> dict[str, Any] | None:
"""Get information about an uploaded file.
Args:
file_id: The file ID.
Returns:
Dictionary with file information, or None if not found.
"""
try:
client = self._get_client()
file_info = client.files.retrieve(file_id=file_id)
return {
"id": file_info.id,
"filename": file_info.filename,
"purpose": file_info.purpose,
"size_bytes": file_info.size_bytes,
"created_at": file_info.created_at,
}
except Exception as e:
logger.debug(f"Failed to get Anthropic file info for {file_id}: {e}")
return None
def list_files(self) -> list[dict[str, Any]]:
"""List all uploaded files.
Returns:
List of dictionaries with file information.
"""
try:
client = self._get_client()
files = client.files.list()
return [
{
"id": f.id,
"filename": f.filename,
"purpose": f.purpose,
"size_bytes": f.size_bytes,
"created_at": f.created_at,
}
for f in files.data
]
except Exception as e:
logger.warning(f"Failed to list Anthropic files: {e}")
return []
async def aupload(
self, file: FileInput, purpose: str | None = None
) -> UploadResult:
"""Async upload a file to Anthropic using native async client.
Args:
file: The file to upload.
purpose: Optional purpose for the file (default: "user_upload").
Returns:
UploadResult with the file ID and metadata.
Raises:
TransientUploadError: For retryable errors (network, rate limits).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
try:
client = self._get_async_client()
content = await file.aread()
file_purpose = purpose or "user_upload"
file_data = io.BytesIO(content)
logger.info(
f"Uploading file '{file.filename}' to Anthropic ({len(content)} bytes)"
)
uploaded_file = await client.files.create(
file=(file.filename, file_data, file.content_type),
purpose=file_purpose,
)
logger.info(f"Uploaded to Anthropic: {uploaded_file.id}")
return UploadResult(
file_id=uploaded_file.id,
file_uri=None,
content_type=file.content_type,
expires_at=None,
provider=self.provider_name,
)
except ImportError:
raise
except Exception as e:
raise classify_upload_error(e, file.filename) from e
async def adelete(self, file_id: str) -> bool:
"""Async delete an uploaded file from Anthropic.
Args:
file_id: The file ID to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
client = self._get_async_client()
await client.files.delete(file_id=file_id)
logger.info(f"Deleted Anthropic file: {file_id}")
return True
except Exception as e:
logger.warning(f"Failed to delete Anthropic file {file_id}: {e}")
return False

118
lib/crewai/src/crewai/files/uploaders/base.py
View File

@@ -1,118 +0,0 @@
"""Base class for file uploaders."""
from abc import ABC, abstractmethod
import asyncio
from dataclasses import dataclass
from datetime import datetime
from typing import Any
from crewai.files.content_types import FileInput
@dataclass
class UploadResult:
"""Result of a file upload operation.
Attributes:
file_id: Provider-specific file identifier.
file_uri: Optional URI for accessing the file.
content_type: MIME type of the uploaded file.
expires_at: When the upload expires (if applicable).
provider: Name of the provider.
"""
file_id: str
provider: str
content_type: str
file_uri: str | None = None
expires_at: datetime | None = None
class FileUploader(ABC):
"""Abstract base class for provider file uploaders.
Implementations handle uploading files to provider-specific File APIs.
"""
@property
@abstractmethod
def provider_name(self) -> str:
"""Return the provider name."""
@abstractmethod
def upload(self, file: FileInput, purpose: str | None = None) -> UploadResult:
"""Upload a file to the provider.
Args:
file: The file to upload.
purpose: Optional purpose/description for the upload.
Returns:
UploadResult with the file identifier and metadata.
Raises:
Exception: If upload fails.
"""
async def aupload(
self, file: FileInput, purpose: str | None = None
) -> UploadResult:
"""Async upload a file to the provider.
Default implementation runs sync upload in executor.
Override in subclasses for native async support.
Args:
file: The file to upload.
purpose: Optional purpose/description for the upload.
Returns:
UploadResult with the file identifier and metadata.
"""
loop = asyncio.get_running_loop()
return await loop.run_in_executor(None, self.upload, file, purpose)
@abstractmethod
def delete(self, file_id: str) -> bool:
"""Delete an uploaded file.
Args:
file_id: The file identifier to delete.
Returns:
True if deletion was successful, False otherwise.
"""
async def adelete(self, file_id: str) -> bool:
"""Async delete an uploaded file.
Default implementation runs sync delete in executor.
Override in subclasses for native async support.
Args:
file_id: The file identifier to delete.
Returns:
True if deletion was successful, False otherwise.
"""
loop = asyncio.get_running_loop()
return await loop.run_in_executor(None, self.delete, file_id)
def get_file_info(self, file_id: str) -> dict[str, Any] | None:
"""Get information about an uploaded file.
Args:
file_id: The file identifier.
Returns:
Dictionary with file information, or None if not found.
"""
return None
def list_files(self) -> list[dict[str, Any]]:
"""List all uploaded files.
Returns:
List of dictionaries with file information.
"""
return []

473
lib/crewai/src/crewai/files/uploaders/bedrock.py
View File

@@ -1,473 +0,0 @@
"""AWS Bedrock S3 file uploader implementation."""
from __future__ import annotations
import hashlib
import logging
import os
from pathlib import Path
from typing import Any
from crewai.files.constants import (
MAX_CONCURRENCY,
MULTIPART_CHUNKSIZE,
MULTIPART_THRESHOLD,
)
from crewai.files.content_types import FileInput
from crewai.files.file import FileBytes, FilePath
from crewai.files.processing.exceptions import (
PermanentUploadError,
TransientUploadError,
)
from crewai.files.uploaders.base import FileUploader, UploadResult
logger = logging.getLogger(__name__)
def _classify_s3_error(e: Exception, filename: str | None) -> Exception:
"""Classify an S3 exception as transient or permanent upload error.
Args:
e: The exception to classify.
filename: The filename for error context.
Returns:
A TransientUploadError or PermanentUploadError wrapping the original.
"""
error_type = type(e).__name__
error_code = getattr(e, "response", {}).get("Error", {}).get("Code", "")
if error_code in ("SlowDown", "ServiceUnavailable", "InternalError"):
return TransientUploadError(f"Transient S3 error: {e}", file_name=filename)
if error_code in ("AccessDenied", "InvalidAccessKeyId", "SignatureDoesNotMatch"):
return PermanentUploadError(f"S3 authentication error: {e}", file_name=filename)
if error_code in ("NoSuchBucket", "InvalidBucketName"):
return PermanentUploadError(f"S3 bucket error: {e}", file_name=filename)
if "Throttl" in error_type or "Throttl" in str(e):
return TransientUploadError(f"S3 throttling: {e}", file_name=filename)
return TransientUploadError(f"S3 upload failed: {e}", file_name=filename)
def _get_file_path(file: FileInput) -> Path | None:
"""Get the filesystem path if file source is FilePath.
Args:
file: The file input to check.
Returns:
Path if source is FilePath, None otherwise.
"""
source = file._file_source
if isinstance(source, FilePath):
return source.path
return None
def _get_file_size(file: FileInput) -> int | None:
"""Get file size without reading content if possible.
Args:
file: The file input.
Returns:
Size in bytes if determinable without reading, None otherwise.
"""
source = file._file_source
if isinstance(source, FilePath):
return source.path.stat().st_size
if isinstance(source, FileBytes):
return len(source.data)
return None
def _compute_hash_streaming(file_path: Path) -> str:
"""Compute SHA-256 hash by streaming file content.
Args:
file_path: Path to the file.
Returns:
First 16 characters of hex digest.
"""
hasher = hashlib.sha256()
with open(file_path, "rb") as f:
while chunk := f.read(1024 * 1024):
hasher.update(chunk)
return hasher.hexdigest()[:16]
class BedrockFileUploader(FileUploader):
"""Uploader for AWS Bedrock via S3.
Uploads files to S3 and returns S3 URIs that can be used with Bedrock's
Converse API s3Location source format.
"""
def __init__(
self,
bucket_name: str | None = None,
bucket_owner: str | None = None,
prefix: str = "crewai-files",
region: str | None = None,
) -> None:
"""Initialize the Bedrock S3 uploader.
Args:
bucket_name: S3 bucket name. If not provided, uses
CREWAI_BEDROCK_S3_BUCKET environment variable.
bucket_owner: Optional bucket owner account ID for cross-account access.
Uses CREWAI_BEDROCK_S3_BUCKET_OWNER environment variable if not provided.
prefix: S3 key prefix for uploaded files (default: "crewai-files").
region: AWS region. Uses AWS_REGION or AWS_DEFAULT_REGION if not provided.
"""
self._bucket_name = bucket_name or os.environ.get("CREWAI_BEDROCK_S3_BUCKET")
self._bucket_owner = bucket_owner or os.environ.get(
"CREWAI_BEDROCK_S3_BUCKET_OWNER"
)
self._prefix = prefix
self._region = region or os.environ.get(
"AWS_REGION", os.environ.get("AWS_DEFAULT_REGION")
)
self._client: Any = None
self._async_client: Any = None
@property
def provider_name(self) -> str:
"""Return the provider name."""
return "bedrock"
@property
def bucket_name(self) -> str:
"""Return the configured bucket name."""
if not self._bucket_name:
raise ValueError(
"S3 bucket name not configured. Set CREWAI_BEDROCK_S3_BUCKET "
"environment variable or pass bucket_name parameter."
)
return self._bucket_name
@property
def bucket_owner(self) -> str | None:
"""Return the configured bucket owner."""
return self._bucket_owner
def _get_client(self) -> Any:
"""Get or create the S3 client."""
if self._client is None:
try:
import boto3
self._client = boto3.client("s3", region_name=self._region)
except ImportError as e:
raise ImportError(
"boto3 is required for Bedrock S3 file uploads. "
"Install with: pip install boto3"
) from e
return self._client
def _get_async_client(self) -> Any:
"""Get or create the async S3 client."""
if self._async_client is None:
try:
import aioboto3 # type: ignore[import-not-found]
self._session = aioboto3.Session()
except ImportError as e:
raise ImportError(
"aioboto3 is required for async Bedrock S3 file uploads. "
"Install with: pip install aioboto3"
) from e
return self._session
def _generate_s3_key(self, file: FileInput, content: bytes | None = None) -> str:
"""Generate a unique S3 key for the file.
For FilePath sources with no content provided, computes hash via streaming.
Args:
file: The file being uploaded.
content: The file content bytes (optional for FilePath sources).
Returns:
S3 key string.
"""
if content is not None:
content_hash = hashlib.sha256(content).hexdigest()[:16]
else:
file_path = _get_file_path(file)
if file_path is not None:
content_hash = _compute_hash_streaming(file_path)
else:
content_hash = hashlib.sha256(file.read()).hexdigest()[:16]
filename = file.filename or "file"
safe_filename = "".join(
c if c.isalnum() or c in ".-_" else "_" for c in filename
)
return f"{self._prefix}/{content_hash}_{safe_filename}"
def _build_s3_uri(self, key: str) -> str:
"""Build an S3 URI from a key.
Args:
key: The S3 object key.
Returns:
S3 URI string.
"""
return f"s3://{self.bucket_name}/{key}"
@staticmethod
def _get_transfer_config() -> Any:
"""Get boto3 TransferConfig for multipart uploads."""
from boto3.s3.transfer import TransferConfig
return TransferConfig(
multipart_threshold=MULTIPART_THRESHOLD,
multipart_chunksize=MULTIPART_CHUNKSIZE,
max_concurrency=MAX_CONCURRENCY,
)
def upload(self, file: FileInput, purpose: str | None = None) -> UploadResult:
"""Upload a file to S3 for use with Bedrock.
Uses streaming upload with automatic multipart for large files.
For FilePath sources, streams directly from disk without loading into memory.
Args:
file: The file to upload.
purpose: Optional purpose (unused, kept for interface consistency).
Returns:
UploadResult with the S3 URI and metadata.
Raises:
TransientUploadError: For retryable errors (network, throttling).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
import io
try:
client = self._get_client()
transfer_config = self._get_transfer_config()
file_path = _get_file_path(file)
if file_path is not None:
file_size = file_path.stat().st_size
s3_key = self._generate_s3_key(file)
logger.info(
f"Uploading file '{file.filename}' to S3 bucket "
f"'{self.bucket_name}' ({file_size} bytes, streaming)"
)
with open(file_path, "rb") as f:
client.upload_fileobj(
f,
self.bucket_name,
s3_key,
ExtraArgs={"ContentType": file.content_type},
Config=transfer_config,
)
else:
content = file.read()
s3_key = self._generate_s3_key(file, content)
logger.info(
f"Uploading file '{file.filename}' to S3 bucket "
f"'{self.bucket_name}' ({len(content)} bytes)"
)
client.upload_fileobj(
io.BytesIO(content),
self.bucket_name,
s3_key,
ExtraArgs={"ContentType": file.content_type},
Config=transfer_config,
)
s3_uri = self._build_s3_uri(s3_key)
logger.info(f"Uploaded to S3: {s3_uri}")
return UploadResult(
file_id=s3_key,
file_uri=s3_uri,
content_type=file.content_type,
expires_at=None,
provider=self.provider_name,
)
except ImportError:
raise
except Exception as e:
raise _classify_s3_error(e, file.filename) from e
def delete(self, file_id: str) -> bool:
"""Delete an uploaded file from S3.
Args:
file_id: The S3 key to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
client = self._get_client()
client.delete_object(Bucket=self.bucket_name, Key=file_id)
logger.info(f"Deleted S3 object: s3://{self.bucket_name}/{file_id}")
return True
except Exception as e:
logger.warning(
f"Failed to delete S3 object s3://{self.bucket_name}/{file_id}: {e}"
)
return False
def get_file_info(self, file_id: str) -> dict[str, Any] | None:
"""Get information about an uploaded file.
Args:
file_id: The S3 key.
Returns:
Dictionary with file information, or None if not found.
"""
try:
client = self._get_client()
response = client.head_object(Bucket=self.bucket_name, Key=file_id)
return {
"id": file_id,
"uri": self._build_s3_uri(file_id),
"content_type": response.get("ContentType"),
"size": response.get("ContentLength"),
"last_modified": response.get("LastModified"),
"etag": response.get("ETag"),
}
except Exception as e:
logger.debug(f"Failed to get S3 object info for {file_id}: {e}")
return None
def list_files(self) -> list[dict[str, Any]]:
"""List all uploaded files in the configured prefix.
Returns:
List of dictionaries with file information.
"""
try:
client = self._get_client()
response = client.list_objects_v2(
Bucket=self.bucket_name,
Prefix=self._prefix,
)
return [
{
"id": obj["Key"],
"uri": self._build_s3_uri(obj["Key"]),
"size": obj.get("Size"),
"last_modified": obj.get("LastModified"),
"etag": obj.get("ETag"),
}
for obj in response.get("Contents", [])
]
except Exception as e:
logger.warning(f"Failed to list S3 objects: {e}")
return []
async def aupload(
self, file: FileInput, purpose: str | None = None
) -> UploadResult:
"""Async upload a file to S3 for use with Bedrock.
Uses streaming upload with automatic multipart for large files.
For FilePath sources, streams directly from disk without loading into memory.
Args:
file: The file to upload.
purpose: Optional purpose (unused, kept for interface consistency).
Returns:
UploadResult with the S3 URI and metadata.
Raises:
TransientUploadError: For retryable errors (network, throttling).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
import io
import aiofiles
try:
session = self._get_async_client()
transfer_config = self._get_transfer_config()
file_path = _get_file_path(file)
if file_path is not None:
file_size = file_path.stat().st_size
s3_key = self._generate_s3_key(file)
logger.info(
f"Uploading file '{file.filename}' to S3 bucket "
f"'{self.bucket_name}' ({file_size} bytes, streaming)"
)
async with session.client("s3", region_name=self._region) as client:
async with aiofiles.open(file_path, "rb") as f:
await client.upload_fileobj(
f,
self.bucket_name,
s3_key,
ExtraArgs={"ContentType": file.content_type},
Config=transfer_config,
)
else:
content = await file.aread()
s3_key = self._generate_s3_key(file, content)
logger.info(
f"Uploading file '{file.filename}' to S3 bucket "
f"'{self.bucket_name}' ({len(content)} bytes)"
)
async with session.client("s3", region_name=self._region) as client:
await client.upload_fileobj(
io.BytesIO(content),
self.bucket_name,
s3_key,
ExtraArgs={"ContentType": file.content_type},
Config=transfer_config,
)
s3_uri = self._build_s3_uri(s3_key)
logger.info(f"Uploaded to S3: {s3_uri}")
return UploadResult(
file_id=s3_key,
file_uri=s3_uri,
content_type=file.content_type,
expires_at=None,
provider=self.provider_name,
)
except ImportError:
raise
except Exception as e:
raise _classify_s3_error(e, file.filename) from e
async def adelete(self, file_id: str) -> bool:
"""Async delete an uploaded file from S3.
Args:
file_id: The S3 key to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
session = self._get_async_client()
async with session.client("s3", region_name=self._region) as client:
await client.delete_object(Bucket=self.bucket_name, Key=file_id)
logger.info(f"Deleted S3 object: s3://{self.bucket_name}/{file_id}")
return True
except Exception as e:
logger.warning(
f"Failed to delete S3 object s3://{self.bucket_name}/{file_id}: {e}"
)
return False

192
lib/crewai/src/crewai/files/uploaders/factory.py
View File

@@ -1,192 +0,0 @@
"""Factory for creating file uploaders."""
from __future__ import annotations
import logging
from typing import Literal, TypeAlias, TypedDict, overload
from typing_extensions import NotRequired, Unpack
from crewai.files.uploaders.anthropic import AnthropicFileUploader
from crewai.files.uploaders.bedrock import BedrockFileUploader
from crewai.files.uploaders.gemini import GeminiFileUploader
from crewai.files.uploaders.openai import OpenAIFileUploader
logger = logging.getLogger(__name__)
FileUploaderType: TypeAlias = (
GeminiFileUploader
| AnthropicFileUploader
| BedrockFileUploader
| OpenAIFileUploader
)
GeminiProviderType = Literal["gemini", "google"]
AnthropicProviderType = Literal["anthropic", "claude"]
OpenAIProviderType = Literal["openai", "gpt"]
BedrockProviderType = Literal["bedrock", "aws"]
ProviderType: TypeAlias = (
GeminiProviderType
| AnthropicProviderType
| OpenAIProviderType
| BedrockProviderType
)
class _BaseOpts(TypedDict):
"""Kwargs for uploader factory."""
api_key: NotRequired[str | None]
class OpenAIOpts(_BaseOpts):
"""Kwargs for openai uploader factory."""
chunk_size: NotRequired[int]
class GeminiOpts(_BaseOpts):
"""Kwargs for gemini uploader factory."""
class AnthropicOpts(_BaseOpts):
"""Kwargs for anthropic uploader factory."""
class BedrockOpts(TypedDict):
"""Kwargs for bedrock uploader factory."""
bucket_name: NotRequired[str | None]
bucket_owner: NotRequired[str | None]
prefix: NotRequired[str]
region: NotRequired[str | None]
class AllOptions(TypedDict):
"""Kwargs for uploader factory."""
api_key: NotRequired[str | None]
chunk_size: NotRequired[int]
bucket_name: NotRequired[str | None]
bucket_owner: NotRequired[str | None]
prefix: NotRequired[str]
region: NotRequired[str | None]
@overload
def get_uploader(
provider: GeminiProviderType,
**kwargs: Unpack[GeminiOpts],
) -> GeminiFileUploader:
"""Get Gemini file uploader."""
@overload
def get_uploader(
provider: AnthropicProviderType,
**kwargs: Unpack[AnthropicOpts],
) -> AnthropicFileUploader:
"""Get Anthropic file uploader."""
@overload
def get_uploader(
provider: OpenAIProviderType,
**kwargs: Unpack[OpenAIOpts],
) -> OpenAIFileUploader:
"""Get OpenAI file uploader."""
@overload
def get_uploader(
provider: BedrockProviderType,
**kwargs: Unpack[BedrockOpts],
) -> BedrockFileUploader:
"""Get Bedrock file uploader."""
@overload
def get_uploader(
provider: ProviderType, **kwargs: Unpack[AllOptions]
) -> FileUploaderType:
"""Get any file uploader."""
def get_uploader(
provider: ProviderType, **kwargs: Unpack[AllOptions]
) -> FileUploaderType:
"""Get a file uploader for a specific provider.
Args:
provider: Provider name (e.g., "gemini", "anthropic").
**kwargs: Additional arguments passed to the uploader constructor.
Returns:
FileUploader instance for the provider, or None if not supported.
"""
provider_lower = provider.lower()
if "gemini" in provider_lower or "google" in provider_lower:
try:
from crewai.files.uploaders.gemini import GeminiFileUploader
return GeminiFileUploader(api_key=kwargs.get("api_key"))
except ImportError:
logger.warning(
"google-genai not installed. Install with: pip install google-genai"
)
raise
if "anthropic" in provider_lower or "claude" in provider_lower:
try:
from crewai.files.uploaders.anthropic import AnthropicFileUploader
return AnthropicFileUploader(api_key=kwargs.get("api_key"))
except ImportError:
logger.warning(
"anthropic not installed. Install with: pip install anthropic"
)
raise
if "openai" in provider_lower or "gpt" in provider_lower:
try:
from crewai.files.uploaders.openai import OpenAIFileUploader
return OpenAIFileUploader(
api_key=kwargs.get("api_key"),
chunk_size=kwargs.get("chunk_size", 67_108_864),
)
except ImportError:
logger.warning("openai not installed. Install with: pip install openai")
raise
if "bedrock" in provider_lower or "aws" in provider_lower:
import os
if (
not os.environ.get("CREWAI_BEDROCK_S3_BUCKET")
and "bucket_name" not in kwargs
):
logger.debug(
"Bedrock S3 uploader not configured. "
"Set CREWAI_BEDROCK_S3_BUCKET environment variable to enable."
)
raise
try:
from crewai.files.uploaders.bedrock import BedrockFileUploader
return BedrockFileUploader(
bucket_name=kwargs.get("bucket_name"),
bucket_owner=kwargs.get("bucket_owner"),
prefix=kwargs.get("prefix", "crewai-files"),
region=kwargs.get("region"),
)
except ImportError:
logger.warning("boto3 not installed. Install with: pip install boto3")
raise
logger.debug(f"No file uploader available for provider: {provider}")
raise

443
lib/crewai/src/crewai/files/uploaders/gemini.py
View File

@@ -1,443 +0,0 @@
"""Gemini File API uploader implementation."""
from __future__ import annotations
import asyncio
from datetime import datetime, timezone
import io
import logging
import os
from pathlib import Path
import random
import time
from typing import Any
from crewai.files.constants import (
BACKOFF_BASE_DELAY,
BACKOFF_JITTER_FACTOR,
BACKOFF_MAX_DELAY,
GEMINI_FILE_TTL,
)
from crewai.files.content_types import FileInput
from crewai.files.file import FilePath
from crewai.files.processing.exceptions import (
PermanentUploadError,
TransientUploadError,
classify_upload_error,
)
from crewai.files.uploaders.base import FileUploader, UploadResult
logger = logging.getLogger(__name__)
def _compute_backoff_delay(attempt: int) -> float:
"""Compute exponential backoff delay with jitter.
Args:
attempt: The current attempt number (0-indexed).
Returns:
Delay in seconds with jitter applied.
"""
delay: float = min(BACKOFF_BASE_DELAY * (2**attempt), BACKOFF_MAX_DELAY)
jitter: float = random.uniform(0, delay * BACKOFF_JITTER_FACTOR) # noqa: S311
return float(delay + jitter)
def _classify_gemini_error(e: Exception, filename: str | None) -> Exception:
"""Classify a Gemini exception as transient or permanent upload error.
Checks Gemini-specific error message patterns first, then falls back
to generic status code classification.
Args:
e: The exception to classify.
filename: The filename for error context.
Returns:
A TransientUploadError or PermanentUploadError wrapping the original.
"""
error_msg = str(e).lower()
if "quota" in error_msg or "rate" in error_msg or "limit" in error_msg:
return TransientUploadError(f"Rate limit error: {e}", file_name=filename)
if "auth" in error_msg or "permission" in error_msg or "denied" in error_msg:
return PermanentUploadError(
f"Authentication/permission error: {e}", file_name=filename
)
if "invalid" in error_msg or "unsupported" in error_msg:
return PermanentUploadError(f"Invalid request: {e}", file_name=filename)
return classify_upload_error(e, filename)
def _get_file_path(file: FileInput) -> Path | None:
"""Get the filesystem path if file source is FilePath.
Args:
file: The file input to check.
Returns:
Path if source is FilePath, None otherwise.
"""
source = file._file_source
if isinstance(source, FilePath):
return source.path
return None
class GeminiFileUploader(FileUploader):
"""Uploader for Google Gemini File API.
Uses the google-genai SDK to upload files. Files are stored for 48 hours.
"""
def __init__(self, api_key: str | None = None) -> None:
"""Initialize the Gemini uploader.
Args:
api_key: Optional Google API key. If not provided, uses
GOOGLE_API_KEY environment variable.
"""
self._api_key = api_key or os.environ.get("GOOGLE_API_KEY")
self._client: Any = None
@property
def provider_name(self) -> str:
"""Return the provider name."""
return "gemini"
def _get_client(self) -> Any:
"""Get or create the Gemini client."""
if self._client is None:
try:
from google import genai
self._client = genai.Client(api_key=self._api_key)
except ImportError as e:
raise ImportError(
"google-genai is required for Gemini file uploads. "
"Install with: pip install google-genai"
) from e
return self._client
def upload(self, file: FileInput, purpose: str | None = None) -> UploadResult:
"""Upload a file to Gemini.
For FilePath sources, passes the path directly to the SDK which handles
streaming internally via resumable uploads, avoiding memory overhead.
Args:
file: The file to upload.
purpose: Optional purpose/description (used as display name).
Returns:
UploadResult with the file URI and metadata.
Raises:
TransientUploadError: For retryable errors (network, rate limits).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
try:
client = self._get_client()
display_name = purpose or file.filename
file_path = _get_file_path(file)
if file_path is not None:
file_size = file_path.stat().st_size
logger.info(
f"Uploading file '{file.filename}' to Gemini via path "
f"({file_size} bytes, streaming)"
)
uploaded_file = client.files.upload(
file=file_path,
config={
"display_name": display_name,
"mime_type": file.content_type,
},
)
else:
content = file.read()
file_data = io.BytesIO(content)
file_data.name = file.filename
logger.info(
f"Uploading file '{file.filename}' to Gemini ({len(content)} bytes)"
)
uploaded_file = client.files.upload(
file=file_data,
config={
"display_name": display_name,
"mime_type": file.content_type,
},
)
if file.content_type.startswith("video/"):
if not self.wait_for_processing(uploaded_file.name):
raise PermanentUploadError(
f"Video processing failed for {file.filename}",
file_name=file.filename,
)
expires_at = datetime.now(timezone.utc) + GEMINI_FILE_TTL
logger.info(
f"Uploaded to Gemini: {uploaded_file.name} (URI: {uploaded_file.uri})"
)
return UploadResult(
file_id=uploaded_file.name,
file_uri=uploaded_file.uri,
content_type=file.content_type,
expires_at=expires_at,
provider=self.provider_name,
)
except ImportError:
raise
except (TransientUploadError, PermanentUploadError):
raise
except Exception as e:
raise _classify_gemini_error(e, file.filename) from e
async def aupload(
self, file: FileInput, purpose: str | None = None
) -> UploadResult:
"""Async upload a file to Gemini using native async client.
For FilePath sources, passes the path directly to the SDK which handles
streaming internally via resumable uploads, avoiding memory overhead.
Args:
file: The file to upload.
purpose: Optional purpose/description (used as display name).
Returns:
UploadResult with the file URI and metadata.
Raises:
TransientUploadError: For retryable errors (network, rate limits).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
try:
client = self._get_client()
display_name = purpose or file.filename
file_path = _get_file_path(file)
if file_path is not None:
file_size = file_path.stat().st_size
logger.info(
f"Uploading file '{file.filename}' to Gemini via path "
f"({file_size} bytes, streaming)"
)
uploaded_file = await client.aio.files.upload(
file=file_path,
config={
"display_name": display_name,
"mime_type": file.content_type,
},
)
else:
content = await file.aread()
file_data = io.BytesIO(content)
file_data.name = file.filename
logger.info(
f"Uploading file '{file.filename}' to Gemini ({len(content)} bytes)"
)
uploaded_file = await client.aio.files.upload(
file=file_data,
config={
"display_name": display_name,
"mime_type": file.content_type,
},
)
if file.content_type.startswith("video/"):
if not await self.await_for_processing(uploaded_file.name):
raise PermanentUploadError(
f"Video processing failed for {file.filename}",
file_name=file.filename,
)
expires_at = datetime.now(timezone.utc) + GEMINI_FILE_TTL
logger.info(
f"Uploaded to Gemini: {uploaded_file.name} (URI: {uploaded_file.uri})"
)
return UploadResult(
file_id=uploaded_file.name,
file_uri=uploaded_file.uri,
content_type=file.content_type,
expires_at=expires_at,
provider=self.provider_name,
)
except ImportError:
raise
except (TransientUploadError, PermanentUploadError):
raise
except Exception as e:
raise _classify_gemini_error(e, file.filename) from e
def delete(self, file_id: str) -> bool:
"""Delete an uploaded file from Gemini.
Args:
file_id: The file name/ID to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
client = self._get_client()
client.files.delete(name=file_id)
logger.info(f"Deleted Gemini file: {file_id}")
return True
except Exception as e:
logger.warning(f"Failed to delete Gemini file {file_id}: {e}")
return False
async def adelete(self, file_id: str) -> bool:
"""Async delete an uploaded file from Gemini.
Args:
file_id: The file name/ID to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
client = self._get_client()
await client.aio.files.delete(name=file_id)
logger.info(f"Deleted Gemini file: {file_id}")
return True
except Exception as e:
logger.warning(f"Failed to delete Gemini file {file_id}: {e}")
return False
def get_file_info(self, file_id: str) -> dict[str, Any] | None:
"""Get information about an uploaded file.
Args:
file_id: The file name/ID.
Returns:
Dictionary with file information, or None if not found.
"""
try:
client = self._get_client()
file_info = client.files.get(name=file_id)
return {
"name": file_info.name,
"uri": file_info.uri,
"display_name": file_info.display_name,
"mime_type": file_info.mime_type,
"size_bytes": file_info.size_bytes,
"state": str(file_info.state),
"create_time": file_info.create_time,
"expiration_time": file_info.expiration_time,
}
except Exception as e:
logger.debug(f"Failed to get Gemini file info for {file_id}: {e}")
return None
def list_files(self) -> list[dict[str, Any]]:
"""List all uploaded files.
Returns:
List of dictionaries with file information.
"""
try:
client = self._get_client()
files = client.files.list()
return [
{
"name": f.name,
"uri": f.uri,
"display_name": f.display_name,
"mime_type": f.mime_type,
"size_bytes": f.size_bytes,
"state": str(f.state),
}
for f in files
]
except Exception as e:
logger.warning(f"Failed to list Gemini files: {e}")
return []
def wait_for_processing(self, file_id: str, timeout_seconds: int = 300) -> bool:
"""Wait for a file to finish processing with exponential backoff.
Some files (especially videos) need time to process after upload.
Args:
file_id: The file name/ID.
timeout_seconds: Maximum time to wait.
Returns:
True if processing completed, False if timed out or failed.
"""
try:
from google.genai.types import FileState
except ImportError:
return True
client = self._get_client()
start_time = time.time()
attempt = 0
while time.time() - start_time < timeout_seconds:
file_info = client.files.get(name=file_id)
if file_info.state == FileState.ACTIVE:
return True
if file_info.state == FileState.FAILED:
logger.error(f"Gemini file processing failed: {file_id}")
return False
time.sleep(_compute_backoff_delay(attempt))
attempt += 1
logger.warning(f"Timed out waiting for Gemini file processing: {file_id}")
return False
async def await_for_processing(
self, file_id: str, timeout_seconds: int = 300
) -> bool:
"""Async wait for a file to finish processing with exponential backoff.
Some files (especially videos) need time to process after upload.
Args:
file_id: The file name/ID.
timeout_seconds: Maximum time to wait.
Returns:
True if processing completed, False if timed out or failed.
"""
try:
from google.genai.types import FileState
except ImportError:
return True
client = self._get_client()
start_time = time.time()
attempt = 0
while time.time() - start_time < timeout_seconds:
file_info = await client.aio.files.get(name=file_id)
if file_info.state == FileState.ACTIVE:
return True
if file_info.state == FileState.FAILED:
logger.error(f"Gemini file processing failed: {file_id}")
return False
await asyncio.sleep(_compute_backoff_delay(attempt))
attempt += 1
logger.warning(f"Timed out waiting for Gemini file processing: {file_id}")
return False

669
lib/crewai/src/crewai/files/uploaders/openai.py
View File

@@ -1,669 +0,0 @@
"""OpenAI Files API uploader implementation."""
from __future__ import annotations
from collections.abc import AsyncIterator, Iterator
import io
import logging
import os
from typing import Any
from crewai.files.constants import DEFAULT_UPLOAD_CHUNK_SIZE, FILES_API_MAX_SIZE
from crewai.files.content_types import FileInput
from crewai.files.file import FileBytes, FilePath, FileStream
from crewai.files.processing.exceptions import (
PermanentUploadError,
TransientUploadError,
classify_upload_error,
)
from crewai.files.uploaders.base import FileUploader, UploadResult
logger = logging.getLogger(__name__)
def _get_file_size(file: FileInput) -> int | None:
"""Get file size without reading content if possible.
Args:
file: The file to get size for.
Returns:
File size in bytes, or None if size cannot be determined without reading.
"""
source = file._file_source
if isinstance(source, FilePath):
return source.path.stat().st_size
if isinstance(source, FileBytes):
return len(source.data)
return None
def _iter_file_chunks(file: FileInput, chunk_size: int) -> Iterator[bytes]:
"""Iterate over file content in chunks.
Args:
file: The file to read.
chunk_size: Size of each chunk in bytes.
Yields:
Chunks of file content.
"""
source = file._file_source
if isinstance(source, (FilePath, FileBytes, FileStream)):
yield from source.read_chunks(chunk_size)
else:
content = file.read()
for i in range(0, len(content), chunk_size):
yield content[i : i + chunk_size]
async def _aiter_file_chunks(
file: FileInput, chunk_size: int, content: bytes | None = None
) -> AsyncIterator[bytes]:
"""Async iterate over file content in chunks.
Args:
file: The file to read.
chunk_size: Size of each chunk in bytes.
content: Optional pre-loaded content to chunk.
Yields:
Chunks of file content.
"""
if content is not None:
for i in range(0, len(content), chunk_size):
yield content[i : i + chunk_size]
return
source = file._file_source
if isinstance(source, FilePath):
async for chunk in source.aread_chunks(chunk_size):
yield chunk
elif isinstance(source, (FileBytes, FileStream)):
for chunk in source.read_chunks(chunk_size):
yield chunk
else:
data = await file.aread()
for i in range(0, len(data), chunk_size):
yield data[i : i + chunk_size]
class OpenAIFileUploader(FileUploader):
"""Uploader for OpenAI Files and Uploads APIs.
Uses the Files API for files up to 512MB (single request).
Uses the Uploads API for files larger than 512MB (multipart chunked).
"""
def __init__(
self,
api_key: str | None = None,
chunk_size: int = DEFAULT_UPLOAD_CHUNK_SIZE,
) -> None:
"""Initialize the OpenAI uploader.
Args:
api_key: Optional OpenAI API key. If not provided, uses
OPENAI_API_KEY environment variable.
chunk_size: Chunk size in bytes for multipart uploads (default 64MB).
"""
self._api_key = api_key or os.environ.get("OPENAI_API_KEY")
self._chunk_size = chunk_size
self._client: Any = None
self._async_client: Any = None
@property
def provider_name(self) -> str:
"""Return the provider name."""
return "openai"
def _build_upload_result(self, file_id: str, content_type: str) -> UploadResult:
"""Build an UploadResult for a completed upload.
Args:
file_id: The uploaded file ID.
content_type: The file's content type.
Returns:
UploadResult with the file metadata.
"""
return UploadResult(
file_id=file_id,
file_uri=None,
content_type=content_type,
expires_at=None,
provider=self.provider_name,
)
def _get_client(self) -> Any:
"""Get or create the OpenAI client."""
if self._client is None:
try:
from openai import OpenAI
self._client = OpenAI(api_key=self._api_key)
except ImportError as e:
raise ImportError(
"openai is required for OpenAI file uploads. "
"Install with: pip install openai"
) from e
return self._client
def _get_async_client(self) -> Any:
"""Get or create the async OpenAI client."""
if self._async_client is None:
try:
from openai import AsyncOpenAI
self._async_client = AsyncOpenAI(api_key=self._api_key)
except ImportError as e:
raise ImportError(
"openai is required for OpenAI file uploads. "
"Install with: pip install openai"
) from e
return self._async_client
def upload(self, file: FileInput, purpose: str | None = None) -> UploadResult:
"""Upload a file to OpenAI.
Uses Files API for files <= 512MB, Uploads API for larger files.
For large files, streams chunks to avoid loading entire file in memory.
Args:
file: The file to upload.
purpose: Optional purpose for the file (default: "user_data").
Returns:
UploadResult with the file ID and metadata.
Raises:
TransientUploadError: For retryable errors (network, rate limits).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
try:
file_size = _get_file_size(file)
if file_size is not None and file_size > FILES_API_MAX_SIZE:
return self._upload_multipart_streaming(file, file_size, purpose)
content = file.read()
if len(content) > FILES_API_MAX_SIZE:
return self._upload_multipart(file, content, purpose)
return self._upload_simple(file, content, purpose)
except ImportError:
raise
except (TransientUploadError, PermanentUploadError):
raise
except Exception as e:
raise classify_upload_error(e, file.filename) from e
def _upload_simple(
self,
file: FileInput,
content: bytes,
purpose: str | None,
) -> UploadResult:
"""Upload using the Files API (single request, up to 512MB).
Args:
file: The file to upload.
content: File content bytes.
purpose: Optional purpose for the file.
Returns:
UploadResult with the file ID and metadata.
"""
client = self._get_client()
file_purpose = purpose or "user_data"
file_data = io.BytesIO(content)
file_data.name = file.filename or "file"
logger.info(
f"Uploading file '{file.filename}' to OpenAI Files API ({len(content)} bytes)"
)
uploaded_file = client.files.create(
file=file_data,
purpose=file_purpose,
)
logger.info(f"Uploaded to OpenAI: {uploaded_file.id}")
return self._build_upload_result(uploaded_file.id, file.content_type)
def _upload_multipart(
self,
file: FileInput,
content: bytes,
purpose: str | None,
) -> UploadResult:
"""Upload using the Uploads API with content already in memory.
Args:
file: The file to upload.
content: File content bytes (already loaded).
purpose: Optional purpose for the file.
Returns:
UploadResult with the file ID and metadata.
"""
client = self._get_client()
file_purpose = purpose or "user_data"
filename = file.filename or "file"
file_size = len(content)
logger.info(
f"Uploading file '{filename}' to OpenAI Uploads API "
f"({file_size} bytes, {self._chunk_size} byte chunks)"
)
upload = client.uploads.create(
bytes=file_size,
filename=filename,
mime_type=file.content_type,
purpose=file_purpose,
)
part_ids: list[str] = []
offset = 0
part_num = 1
try:
while offset < file_size:
chunk = content[offset : offset + self._chunk_size]
chunk_io = io.BytesIO(chunk)
logger.debug(
f"Uploading part {part_num} ({len(chunk)} bytes, offset {offset})"
)
part = client.uploads.parts.create(
upload_id=upload.id,
data=chunk_io,
)
part_ids.append(part.id)
offset += self._chunk_size
part_num += 1
completed = client.uploads.complete(
upload_id=upload.id,
part_ids=part_ids,
)
file_id = completed.file.id if completed.file else upload.id
logger.info(f"Completed multipart upload to OpenAI: {file_id}")
return self._build_upload_result(file_id, file.content_type)
except Exception:
logger.warning(f"Multipart upload failed, cancelling upload {upload.id}")
try:
client.uploads.cancel(upload_id=upload.id)
except Exception as cancel_err:
logger.debug(f"Failed to cancel upload: {cancel_err}")
raise
def _upload_multipart_streaming(
self,
file: FileInput,
file_size: int,
purpose: str | None,
) -> UploadResult:
"""Upload using the Uploads API with streaming chunks.
Streams chunks directly from the file source without loading
the entire file into memory. Used for large files.
Args:
file: The file to upload.
file_size: Total file size in bytes.
purpose: Optional purpose for the file.
Returns:
UploadResult with the file ID and metadata.
"""
client = self._get_client()
file_purpose = purpose or "user_data"
filename = file.filename or "file"
logger.info(
f"Uploading file '{filename}' to OpenAI Uploads API (streaming) "
f"({file_size} bytes, {self._chunk_size} byte chunks)"
)
upload = client.uploads.create(
bytes=file_size,
filename=filename,
mime_type=file.content_type,
purpose=file_purpose,
)
part_ids: list[str] = []
part_num = 1
try:
for chunk in _iter_file_chunks(file, self._chunk_size):
chunk_io = io.BytesIO(chunk)
logger.debug(f"Uploading part {part_num} ({len(chunk)} bytes)")
part = client.uploads.parts.create(
upload_id=upload.id,
data=chunk_io,
)
part_ids.append(part.id)
part_num += 1
completed = client.uploads.complete(
upload_id=upload.id,
part_ids=part_ids,
)
file_id = completed.file.id if completed.file else upload.id
logger.info(f"Completed streaming multipart upload to OpenAI: {file_id}")
return self._build_upload_result(file_id, file.content_type)
except Exception:
logger.warning(f"Multipart upload failed, cancelling upload {upload.id}")
try:
client.uploads.cancel(upload_id=upload.id)
except Exception as cancel_err:
logger.debug(f"Failed to cancel upload: {cancel_err}")
raise
def delete(self, file_id: str) -> bool:
"""Delete an uploaded file from OpenAI.
Args:
file_id: The file ID to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
client = self._get_client()
client.files.delete(file_id)
logger.info(f"Deleted OpenAI file: {file_id}")
return True
except Exception as e:
logger.warning(f"Failed to delete OpenAI file {file_id}: {e}")
return False
def get_file_info(self, file_id: str) -> dict[str, Any] | None:
"""Get information about an uploaded file.
Args:
file_id: The file ID.
Returns:
Dictionary with file information, or None if not found.
"""
try:
client = self._get_client()
file_info = client.files.retrieve(file_id)
return {
"id": file_info.id,
"filename": file_info.filename,
"purpose": file_info.purpose,
"bytes": file_info.bytes,
"created_at": file_info.created_at,
"status": file_info.status,
}
except Exception as e:
logger.debug(f"Failed to get OpenAI file info for {file_id}: {e}")
return None
def list_files(self) -> list[dict[str, Any]]:
"""List all uploaded files.
Returns:
List of dictionaries with file information.
"""
try:
client = self._get_client()
files = client.files.list()
return [
{
"id": f.id,
"filename": f.filename,
"purpose": f.purpose,
"bytes": f.bytes,
"created_at": f.created_at,
"status": f.status,
}
for f in files.data
]
except Exception as e:
logger.warning(f"Failed to list OpenAI files: {e}")
return []
async def aupload(
self, file: FileInput, purpose: str | None = None
) -> UploadResult:
"""Async upload a file to OpenAI using native async client.
Uses Files API for files <= 512MB, Uploads API for larger files.
For large files, streams chunks to avoid loading entire file in memory.
Args:
file: The file to upload.
purpose: Optional purpose for the file (default: "user_data").
Returns:
UploadResult with the file ID and metadata.
Raises:
TransientUploadError: For retryable errors (network, rate limits).
PermanentUploadError: For non-retryable errors (auth, validation).
"""
try:
file_size = _get_file_size(file)
if file_size is not None and file_size > FILES_API_MAX_SIZE:
return await self._aupload_multipart_streaming(file, file_size, purpose)
content = await file.aread()
if len(content) > FILES_API_MAX_SIZE:
return await self._aupload_multipart(file, content, purpose)
return await self._aupload_simple(file, content, purpose)
except ImportError:
raise
except (TransientUploadError, PermanentUploadError):
raise
except Exception as e:
raise classify_upload_error(e, file.filename) from e
async def _aupload_simple(
self,
file: FileInput,
content: bytes,
purpose: str | None,
) -> UploadResult:
"""Async upload using the Files API (single request, up to 512MB).
Args:
file: The file to upload.
content: File content bytes.
purpose: Optional purpose for the file.
Returns:
UploadResult with the file ID and metadata.
"""
client = self._get_async_client()
file_purpose = purpose or "user_data"
file_data = io.BytesIO(content)
file_data.name = file.filename or "file"
logger.info(
f"Uploading file '{file.filename}' to OpenAI Files API ({len(content)} bytes)"
)
uploaded_file = await client.files.create(
file=file_data,
purpose=file_purpose,
)
logger.info(f"Uploaded to OpenAI: {uploaded_file.id}")
return self._build_upload_result(uploaded_file.id, file.content_type)
async def _aupload_multipart(
self,
file: FileInput,
content: bytes,
purpose: str | None,
) -> UploadResult:
"""Async upload using the Uploads API (multipart chunked, up to 8GB).
Args:
file: The file to upload.
content: File content bytes.
purpose: Optional purpose for the file.
Returns:
UploadResult with the file ID and metadata.
"""
client = self._get_async_client()
file_purpose = purpose or "user_data"
filename = file.filename or "file"
file_size = len(content)
logger.info(
f"Uploading file '{filename}' to OpenAI Uploads API "
f"({file_size} bytes, {self._chunk_size} byte chunks)"
)
upload = await client.uploads.create(
bytes=file_size,
filename=filename,
mime_type=file.content_type,
purpose=file_purpose,
)
part_ids: list[str] = []
offset = 0
part_num = 1
try:
while offset < file_size:
chunk = content[offset : offset + self._chunk_size]
chunk_io = io.BytesIO(chunk)
logger.debug(
f"Uploading part {part_num} ({len(chunk)} bytes, offset {offset})"
)
part = await client.uploads.parts.create(
upload_id=upload.id,
data=chunk_io,
)
part_ids.append(part.id)
offset += self._chunk_size
part_num += 1
completed = await client.uploads.complete(
upload_id=upload.id,
part_ids=part_ids,
)
file_id = completed.file.id if completed.file else upload.id
logger.info(f"Completed multipart upload to OpenAI: {file_id}")
return self._build_upload_result(file_id, file.content_type)
except Exception:
logger.warning(f"Multipart upload failed, cancelling upload {upload.id}")
try:
await client.uploads.cancel(upload_id=upload.id)
except Exception as cancel_err:
logger.debug(f"Failed to cancel upload: {cancel_err}")
raise
async def _aupload_multipart_streaming(
self,
file: FileInput,
file_size: int,
purpose: str | None,
) -> UploadResult:
"""Async upload using the Uploads API with streaming chunks.
Streams chunks directly from the file source without loading
the entire file into memory. Used for large files.
Args:
file: The file to upload.
file_size: Total file size in bytes.
purpose: Optional purpose for the file.
Returns:
UploadResult with the file ID and metadata.
"""
client = self._get_async_client()
file_purpose = purpose or "user_data"
filename = file.filename or "file"
logger.info(
f"Uploading file '{filename}' to OpenAI Uploads API (streaming) "
f"({file_size} bytes, {self._chunk_size} byte chunks)"
)
upload = await client.uploads.create(
bytes=file_size,
filename=filename,
mime_type=file.content_type,
purpose=file_purpose,
)
part_ids: list[str] = []
part_num = 1
try:
async for chunk in _aiter_file_chunks(file, self._chunk_size):
chunk_io = io.BytesIO(chunk)
logger.debug(f"Uploading part {part_num} ({len(chunk)} bytes)")
part = await client.uploads.parts.create(
upload_id=upload.id,
data=chunk_io,
)
part_ids.append(part.id)
part_num += 1
completed = await client.uploads.complete(
upload_id=upload.id,
part_ids=part_ids,
)
file_id = completed.file.id if completed.file else upload.id
logger.info(f"Completed streaming multipart upload to OpenAI: {file_id}")
return self._build_upload_result(file_id, file.content_type)
except Exception:
logger.warning(f"Multipart upload failed, cancelling upload {upload.id}")
try:
await client.uploads.cancel(upload_id=upload.id)
except Exception as cancel_err:
logger.debug(f"Failed to cancel upload: {cancel_err}")
raise
async def adelete(self, file_id: str) -> bool:
"""Async delete an uploaded file from OpenAI.
Args:
file_id: The file ID to delete.
Returns:
True if deletion was successful, False otherwise.
"""
try:
client = self._get_async_client()
await client.files.delete(file_id)
logger.info(f"Deleted OpenAI file: {file_id}")
return True
except Exception as e:
logger.warning(f"Failed to delete OpenAI file {file_id}: {e}")
return False

95
lib/crewai/src/crewai/files/utils.py
View File

@@ -1,95 +0,0 @@
"""Utility functions for file handling."""
from __future__ import annotations
from pathlib import Path
from typing import TYPE_CHECKING
from typing_extensions import TypeIs
if TYPE_CHECKING:
from crewai.files.content_types import FileInput
from crewai.files.file import FileSource, FileSourceInput
def is_file_source(v: object) -> TypeIs[FileSource]:
"""Type guard to narrow input to FileSource."""
from crewai.files.file import FileBytes, FilePath, FileStream, FileUrl
return isinstance(v, (FilePath, FileBytes, FileStream, FileUrl))
def wrap_file_source(source: FileSource) -> FileInput:
"""Wrap a FileSource in the appropriate typed FileInput wrapper.
Args:
source: The file source to wrap.
Returns:
Typed FileInput wrapper based on content type.
"""
from crewai.files.content_types import (
AudioFile,
ImageFile,
PDFFile,
TextFile,
VideoFile,
)
content_type = source.content_type
if content_type.startswith("image/"):
return ImageFile(source=source)
if content_type.startswith("audio/"):
return AudioFile(source=source)
if content_type.startswith("video/"):
return VideoFile(source=source)
if content_type == "application/pdf":
return PDFFile(source=source)
return TextFile(source=source)
def normalize_input_files(
input_files: list[FileSourceInput | FileInput],
) -> dict[str, FileInput]:
"""Convert a list of file sources to a named dictionary of FileInputs.
Args:
input_files: List of file source inputs or File objects.
Returns:
Dictionary mapping names to FileInput wrappers.
"""
from crewai.files.content_types import BaseFile
from crewai.files.file import FileBytes, FilePath, FileStream, FileUrl
result: dict[str, FileInput] = {}
for i, item in enumerate(input_files):
if isinstance(item, BaseFile):
name = item.filename or f"file_{i}"
if "." in name:
name = name.rsplit(".", 1)[0]
result[name] = item
continue
file_source: FilePath | FileBytes | FileStream | FileUrl
if isinstance(item, (FilePath, FileBytes, FileStream, FileUrl)):
file_source = item
elif isinstance(item, Path):
file_source = FilePath(path=item)
elif isinstance(item, str):
if item.startswith(("http://", "https://")):
file_source = FileUrl(url=item)
else:
file_source = FilePath(path=Path(item))
elif isinstance(item, (bytes, memoryview)):
file_source = FileBytes(data=bytes(item))
else:
continue
name = file_source.filename or f"file_{i}"
result[name] = wrap_file_source(file_source)
return result

4
lib/crewai/src/crewai/llm.py
View File

@@ -53,6 +53,7 @@ from crewai.utilities.logger_utils import suppress_warnings
if TYPE_CHECKING:
from crewai_files import FileInput, UploadCache
from litellm.exceptions import ContextWindowExceededError
from litellm.litellm_core_utils.get_supported_openai_params import (
get_supported_openai_params,
@@ -66,7 +67,6 @@ if TYPE_CHECKING:
from litellm.utils import supports_response_schema
from crewai.agent.core import Agent
from crewai.files import FileInput, UploadCache
from crewai.llms.hooks.base import BaseInterceptor
from crewai.llms.providers.anthropic.completion import AnthropicThinkingConfig
from crewai.task import Task
@@ -2274,7 +2274,7 @@ class LLM(BaseLLM):
"""
import base64
from crewai.files import (
from crewai_files import (
FileResolver,
FileResolverConfig,
InlineBase64,

3
lib/crewai/src/crewai/llms/base_llm.py
View File

@@ -32,8 +32,9 @@ from crewai.types.usage_metrics import UsageMetrics
if TYPE_CHECKING:
from crewai_files import FileInput, UploadCache
from crewai.agent.core import Agent
from crewai.files import FileInput, UploadCache
from crewai.task import Task
from crewai.tools.base_tool import BaseTool
from crewai.utilities.types import LLMMessage

7
lib/crewai/src/crewai/llms/providers/anthropic/completion.py
View File

@@ -20,7 +20,8 @@ from crewai.utilities.types import LLMMessage
if TYPE_CHECKING:
from crewai.files import FileInput, UploadCache
from crewai_files import FileInput, UploadCache
from crewai.llms.hooks.base import BaseInterceptor
DEFAULT_CACHE_TTL = "ephemeral"
@@ -1281,7 +1282,7 @@ class AnthropicCompletion(BaseLLM):
if not self.supports_multimodal():
return []
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,
@@ -1394,7 +1395,7 @@ class AnthropicCompletion(BaseLLM):
if not self.supports_multimodal():
return []
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,

7
lib/crewai/src/crewai/llms/providers/azure/completion.py
View File

@@ -18,7 +18,8 @@ from crewai.utilities.types import LLMMessage
if TYPE_CHECKING:
from crewai.files import FileInput, UploadCache
from crewai_files import FileInput, UploadCache
from crewai.llms.hooks.base import BaseInterceptor
@@ -1060,7 +1061,7 @@ class AzureCompletion(BaseLLM):
if not self.supports_multimodal():
return []
from crewai.files import (
from crewai_files import (
FileResolver,
FileResolverConfig,
InlineBase64,
@@ -1120,7 +1121,7 @@ class AzureCompletion(BaseLLM):
if not self.supports_multimodal():
return []
from crewai.files import (
from crewai_files import (
FileResolver,
FileResolverConfig,
InlineBase64,

6
lib/crewai/src/crewai/llms/providers/bedrock/completion.py
View File

@@ -20,6 +20,7 @@ from crewai.utilities.types import LLMMessage
if TYPE_CHECKING:
from crewai_files import FileInput, UploadCache
from mypy_boto3_bedrock_runtime.type_defs import (
GuardrailConfigurationTypeDef,
GuardrailStreamConfigurationTypeDef,
@@ -32,7 +33,6 @@ if TYPE_CHECKING:
ToolTypeDef,
)
from crewai.files import FileInput, UploadCache
from crewai.llms.hooks.base import BaseInterceptor
@@ -1586,7 +1586,7 @@ class BedrockCompletion(BaseLLM):
import os
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,
@@ -1714,7 +1714,7 @@ class BedrockCompletion(BaseLLM):
import os
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,

7
lib/crewai/src/crewai/llms/providers/gemini/completion.py
View File

@@ -19,10 +19,11 @@ from crewai.utilities.types import LLMMessage
if TYPE_CHECKING:
from crewai.files import (
from crewai_files import (
FileInput,
UploadCache,
)
from crewai.llms.hooks.base import BaseInterceptor
@@ -1113,7 +1114,7 @@ class GeminiCompletion(BaseLLM):
Returns:
List of content blocks in Gemini's expected format.
"""
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,
@@ -1183,7 +1184,7 @@ class GeminiCompletion(BaseLLM):
Returns:
List of content blocks in Gemini's expected format.
"""
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,

7
lib/crewai/src/crewai/llms/providers/openai/completion.py
View File

@@ -27,8 +27,9 @@ from crewai.utilities.types import LLMMessage
if TYPE_CHECKING:
from crewai_files import FileInput, UploadCache
from crewai.agent.core import Agent
from crewai.files import FileInput, UploadCache
from crewai.llms.hooks.base import BaseInterceptor
from crewai.task import Task
from crewai.tools.base_tool import BaseTool
@@ -1100,7 +1101,7 @@ class OpenAICompletion(BaseLLM):
if not self.supports_multimodal():
return []
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,
@@ -1168,7 +1169,7 @@ class OpenAICompletion(BaseLLM):
if not self.supports_multimodal():
return []
from crewai.files import (
from crewai_files import (
FileReference,
FileResolver,
FileResolverConfig,

12
lib/crewai/src/crewai/task.py
View File

@@ -19,6 +19,12 @@ from typing import (
import uuid
import warnings
from crewai_files import (
FileInput,
FilePath,
FileSourceInput,
normalize_input_files,
)
from pydantic import (
UUID4,
BaseModel,
@@ -37,12 +43,6 @@ from crewai.events.types.task_events import (
TaskFailedEvent,
TaskStartedEvent,
)
from crewai.files import (
FileInput,
FilePath,
FileSourceInput,
normalize_input_files,
)
from crewai.security import Fingerprint, SecurityConfig
from crewai.tasks.output_format import OutputFormat
from crewai.tasks.task_output import TaskOutput

2
lib/crewai/src/crewai/tools/agent_tools/read_file_tool.py
View File

@@ -11,7 +11,7 @@ from crewai.tools.base_tool import BaseTool
if TYPE_CHECKING:
from crewai.files import FileInput
from crewai_files import FileInput
class ReadFileToolSchema(BaseModel):

2
lib/crewai/src/crewai/utilities/file_store.py
View File

@@ -13,7 +13,7 @@ from aiocache.serializers import PickleSerializer # type: ignore[import-untyped
if TYPE_CHECKING:
from crewai.files import FileInput
from crewai_files import FileInput
_file_store = Cache(Cache.MEMORY, serializer=PickleSerializer())

25
lib/crewai/src/crewai/utilities/files/__init__.py
View File

@@ -1,25 +0,0 @@
"""Backwards compatibility re-exports from crewai.files.
Deprecated: Import from crewai.files instead.
"""
import sys
from typing import Any
from typing_extensions import deprecated
import crewai.files as _files
@deprecated("crewai.utilities.files is deprecated. Import from crewai.files instead.")
class _DeprecatedModule:
"""Deprecated module wrapper."""
def __getattr__(self, name: str) -> Any:
return getattr(_files, name)
def __dir__(self) -> list[str]:
return list(_files.__all__)
sys.modules[__name__] = _DeprecatedModule() # type: ignore[assignment]

258
lib/crewai/src/crewai/utilities/files/__init__.pyi
View File

@@ -1,258 +0,0 @@
"""Type stubs for backwards compatibility re-exports from crewai.files.
.. deprecated::
Import from crewai.files instead.
"""
from collections.abc import Callable
from datetime import datetime
from pathlib import Path
from typing import Any, Literal
from typing_extensions import deprecated
import crewai.files as _files
FileMode = Literal["strict", "auto", "warn", "chunk"]
ImageExtension = _files.ImageExtension
ImageContentType = _files.ImageContentType
PDFExtension = _files.PDFExtension
PDFContentType = _files.PDFContentType
TextExtension = _files.TextExtension
TextContentType = _files.TextContentType
AudioExtension = _files.AudioExtension
AudioContentType = _files.AudioContentType
VideoExtension = _files.VideoExtension
VideoContentType = _files.VideoContentType
FileInput = _files.FileInput
FileSource = _files.FileSource
FileSourceInput = _files.FileSourceInput
RawFileInput = _files.RawFileInput
ResolvedFileType = _files.ResolvedFileType
FileHandling = _files.FileHandling
# Deprecated classes
@deprecated("Import from crewai.files instead")
class BaseFile(_files.BaseFile):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class ImageFile(_files.ImageFile):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class PDFFile(_files.PDFFile):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class TextFile(_files.TextFile):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class AudioFile(_files.AudioFile):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class VideoFile(_files.VideoFile):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class File(_files.File):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FilePath(_files.FilePath):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileBytes(_files.FileBytes):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileStream(_files.FileStream):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileResolver(_files.FileResolver):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileResolverConfig(_files.FileResolverConfig):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileProcessor(_files.FileProcessor):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileUploader(_files.FileUploader):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class UploadCache(_files.UploadCache):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class CachedUpload(_files.CachedUpload):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class UploadResult(_files.UploadResult):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class ResolvedFile(_files.ResolvedFile):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileReference(_files.FileReference):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class UrlReference(_files.UrlReference):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class InlineBase64(_files.InlineBase64):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class InlineBytes(_files.InlineBytes):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class ProviderConstraints(_files.ProviderConstraints):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class ImageConstraints(_files.ImageConstraints):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class AudioConstraints(_files.AudioConstraints):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class VideoConstraints(_files.VideoConstraints):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class PDFConstraints(_files.PDFConstraints):
""".. deprecated:: Import from crewai.files instead."""
...
# Exceptions
@deprecated("Import from crewai.files instead")
class FileProcessingError(_files.FileProcessingError):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileValidationError(_files.FileValidationError):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class FileTooLargeError(_files.FileTooLargeError):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class UnsupportedFileTypeError(_files.UnsupportedFileTypeError):
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
class ProcessingDependencyError(_files.ProcessingDependencyError):
""".. deprecated:: Import from crewai.files instead."""
...
# Constants
OPENAI_CONSTRAINTS: _files.ProviderConstraints
ANTHROPIC_CONSTRAINTS: _files.ProviderConstraints
GEMINI_CONSTRAINTS: _files.ProviderConstraints
BEDROCK_CONSTRAINTS: _files.ProviderConstraints
# Deprecated functions
@deprecated("Import from crewai.files instead")
def create_resolver(
provider: str,
config: FileResolverConfig | None = None,
) -> FileResolver:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def get_uploader(provider: str, **kwargs: Any) -> FileUploader | None:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def get_upload_cache() -> UploadCache:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def reset_upload_cache() -> None:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def get_constraints_for_provider(provider: str) -> ProviderConstraints:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def cleanup_uploaded_files(provider: str | None = None) -> int:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def cleanup_expired_files() -> int:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def cleanup_provider_files(provider: str) -> int:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def normalize_input_files(
input_files: list[FileSourceInput | FileInput],
) -> dict[str, FileInput]:
""".. deprecated:: Import from crewai.files instead."""
...
@deprecated("Import from crewai.files instead")
def wrap_file_source(source: FileSource) -> FileInput:
""".. deprecated:: Import from crewai.files instead."""
...
__all__: list[str]

2
lib/crewai/src/crewai/utilities/types.py
View File

@@ -2,7 +2,7 @@
from typing import Any, Literal, TypedDict
from crewai.files import FileInput
from crewai_files import FileInput
class LLMMessage(TypedDict):

1
lib/crewai/tests/files/__init__.py
View File

@@ -1 +0,0 @@
"""Tests for file processing utilities."""

1
lib/crewai/tests/files/processing/__init__.py
View File

@@ -1 +0,0 @@
"""Tests for file processing module."""

226
lib/crewai/tests/files/processing/test_constraints.py
View File

@@ -1,226 +0,0 @@
"""Tests for provider constraints."""
import pytest
from crewai.files.processing.constraints import (
ANTHROPIC_CONSTRAINTS,
BEDROCK_CONSTRAINTS,
GEMINI_CONSTRAINTS,
OPENAI_CONSTRAINTS,
AudioConstraints,
ImageConstraints,
PDFConstraints,
ProviderConstraints,
VideoConstraints,
get_constraints_for_provider,
)
class TestImageConstraints:
"""Tests for ImageConstraints dataclass."""
def test_image_constraints_creation(self):
"""Test creating image constraints with all fields."""
constraints = ImageConstraints(
max_size_bytes=5 * 1024 * 1024,
max_width=8000,
max_height=8000,
max_images_per_request=10,
)
assert constraints.max_size_bytes == 5 * 1024 * 1024
assert constraints.max_width == 8000
assert constraints.max_height == 8000
assert constraints.max_images_per_request == 10
def test_image_constraints_defaults(self):
"""Test image constraints with default values."""
constraints = ImageConstraints(max_size_bytes=1000)
assert constraints.max_size_bytes == 1000
assert constraints.max_width is None
assert constraints.max_height is None
assert constraints.max_images_per_request is None
assert "image/png" in constraints.supported_formats
def test_image_constraints_frozen(self):
"""Test that image constraints are immutable."""
constraints = ImageConstraints(max_size_bytes=1000)
with pytest.raises(Exception):
constraints.max_size_bytes = 2000
class TestPDFConstraints:
"""Tests for PDFConstraints dataclass."""
def test_pdf_constraints_creation(self):
"""Test creating PDF constraints."""
constraints = PDFConstraints(
max_size_bytes=30 * 1024 * 1024,
max_pages=100,
)
assert constraints.max_size_bytes == 30 * 1024 * 1024
assert constraints.max_pages == 100
def test_pdf_constraints_defaults(self):
"""Test PDF constraints with default values."""
constraints = PDFConstraints(max_size_bytes=1000)
assert constraints.max_size_bytes == 1000
assert constraints.max_pages is None
class TestAudioConstraints:
"""Tests for AudioConstraints dataclass."""
def test_audio_constraints_creation(self):
"""Test creating audio constraints."""
constraints = AudioConstraints(
max_size_bytes=100 * 1024 * 1024,
max_duration_seconds=3600,
)
assert constraints.max_size_bytes == 100 * 1024 * 1024
assert constraints.max_duration_seconds == 3600
assert "audio/mp3" in constraints.supported_formats
class TestVideoConstraints:
"""Tests for VideoConstraints dataclass."""
def test_video_constraints_creation(self):
"""Test creating video constraints."""
constraints = VideoConstraints(
max_size_bytes=2 * 1024 * 1024 * 1024,
max_duration_seconds=7200,
)
assert constraints.max_size_bytes == 2 * 1024 * 1024 * 1024
assert constraints.max_duration_seconds == 7200
assert "video/mp4" in constraints.supported_formats
class TestProviderConstraints:
"""Tests for ProviderConstraints dataclass."""
def test_provider_constraints_creation(self):
"""Test creating full provider constraints."""
constraints = ProviderConstraints(
name="test-provider",
image=ImageConstraints(max_size_bytes=5 * 1024 * 1024),
pdf=PDFConstraints(max_size_bytes=30 * 1024 * 1024),
supports_file_upload=True,
file_upload_threshold_bytes=10 * 1024 * 1024,
)
assert constraints.name == "test-provider"
assert constraints.image is not None
assert constraints.pdf is not None
assert constraints.supports_file_upload is True
def test_provider_constraints_defaults(self):
"""Test provider constraints with default values."""
constraints = ProviderConstraints(name="test")
assert constraints.name == "test"
assert constraints.image is None
assert constraints.pdf is None
assert constraints.audio is None
assert constraints.video is None
assert constraints.supports_file_upload is False
class TestPredefinedConstraints:
"""Tests for predefined provider constraints."""
def test_anthropic_constraints(self):
"""Test Anthropic constraints are properly defined."""
assert ANTHROPIC_CONSTRAINTS.name == "anthropic"
assert ANTHROPIC_CONSTRAINTS.image is not None
assert ANTHROPIC_CONSTRAINTS.image.max_size_bytes == 5 * 1024 * 1024
assert ANTHROPIC_CONSTRAINTS.image.max_width == 8000
assert ANTHROPIC_CONSTRAINTS.pdf is not None
assert ANTHROPIC_CONSTRAINTS.pdf.max_pages == 100
assert ANTHROPIC_CONSTRAINTS.supports_file_upload is True
def test_openai_constraints(self):
"""Test OpenAI constraints are properly defined."""
assert OPENAI_CONSTRAINTS.name == "openai"
assert OPENAI_CONSTRAINTS.image is not None
assert OPENAI_CONSTRAINTS.image.max_size_bytes == 20 * 1024 * 1024
assert OPENAI_CONSTRAINTS.pdf is None # OpenAI doesn't support PDFs
def test_gemini_constraints(self):
"""Test Gemini constraints are properly defined."""
assert GEMINI_CONSTRAINTS.name == "gemini"
assert GEMINI_CONSTRAINTS.image is not None
assert GEMINI_CONSTRAINTS.pdf is not None
assert GEMINI_CONSTRAINTS.audio is not None
assert GEMINI_CONSTRAINTS.video is not None
assert GEMINI_CONSTRAINTS.supports_file_upload is True
def test_bedrock_constraints(self):
"""Test Bedrock constraints are properly defined."""
assert BEDROCK_CONSTRAINTS.name == "bedrock"
assert BEDROCK_CONSTRAINTS.image is not None
assert BEDROCK_CONSTRAINTS.image.max_size_bytes == 4_608_000
assert BEDROCK_CONSTRAINTS.pdf is not None
assert BEDROCK_CONSTRAINTS.supports_file_upload is False
class TestGetConstraintsForProvider:
"""Tests for get_constraints_for_provider function."""
def test_get_by_exact_name(self):
"""Test getting constraints by exact provider name."""
result = get_constraints_for_provider("anthropic")
assert result == ANTHROPIC_CONSTRAINTS
result = get_constraints_for_provider("openai")
assert result == OPENAI_CONSTRAINTS
result = get_constraints_for_provider("gemini")
assert result == GEMINI_CONSTRAINTS
def test_get_by_alias(self):
"""Test getting constraints by alias name."""
result = get_constraints_for_provider("claude")
assert result == ANTHROPIC_CONSTRAINTS
result = get_constraints_for_provider("gpt")
assert result == OPENAI_CONSTRAINTS
result = get_constraints_for_provider("google")
assert result == GEMINI_CONSTRAINTS
def test_get_case_insensitive(self):
"""Test case-insensitive lookup."""
result = get_constraints_for_provider("ANTHROPIC")
assert result == ANTHROPIC_CONSTRAINTS
result = get_constraints_for_provider("OpenAI")
assert result == OPENAI_CONSTRAINTS
def test_get_with_provider_constraints_object(self):
"""Test passing ProviderConstraints object returns it unchanged."""
custom = ProviderConstraints(name="custom")
result = get_constraints_for_provider(custom)
assert result is custom
def test_get_unknown_provider(self):
"""Test unknown provider returns None."""
result = get_constraints_for_provider("unknown-provider")
assert result is None
def test_get_by_partial_match(self):
"""Test partial match in provider string."""
result = get_constraints_for_provider("claude-3-sonnet")
assert result == ANTHROPIC_CONSTRAINTS
result = get_constraints_for_provider("gpt-4o")
assert result == OPENAI_CONSTRAINTS
result = get_constraints_for_provider("gemini-pro")
assert result == GEMINI_CONSTRAINTS

220
lib/crewai/tests/files/processing/test_processor.py
View File

@@ -1,220 +0,0 @@
"""Tests for FileProcessor class."""
import pytest
from crewai.files import FileBytes, ImageFile, PDFFile, TextFile
from crewai.files.processing.constraints import (
ANTHROPIC_CONSTRAINTS,
ImageConstraints,
PDFConstraints,
ProviderConstraints,
)
from crewai.files.processing.enums import FileHandling
from crewai.files.processing.exceptions import (
FileTooLargeError,
FileValidationError,
)
from crewai.files.processing.processor import FileProcessor
# Minimal valid PNG: 8x8 pixel RGB image (valid for PIL)
MINIMAL_PNG = bytes([
0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a, 0x00, 0x00, 0x00, 0x0d,
0x49, 0x48, 0x44, 0x52, 0x00, 0x00, 0x00, 0x08, 0x00, 0x00, 0x00, 0x08,
0x08, 0x02, 0x00, 0x00, 0x00, 0x4b, 0x6d, 0x29, 0xdc, 0x00, 0x00, 0x00,
0x12, 0x49, 0x44, 0x41, 0x54, 0x78, 0x9c, 0x63, 0xfc, 0xcf, 0x80, 0x1d,
0x30, 0xe1, 0x10, 0x1f, 0xa4, 0x12, 0x00, 0xcd, 0x41, 0x01, 0x0f, 0xe8,
0x41, 0xe2, 0x6f, 0x00, 0x00, 0x00, 0x00, 0x49, 0x45, 0x4e, 0x44, 0xae,
0x42, 0x60, 0x82,
])
# Minimal valid PDF
MINIMAL_PDF = (
b"%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj "
b"2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj "
b"3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Parent 2 0 R>>endobj "
b"xref\n0 4\n0000000000 65535 f \n0000000009 00000 n \n"
b"0000000052 00000 n \n0000000101 00000 n \n"
b"trailer<</Size 4/Root 1 0 R>>\nstartxref\n178\n%%EOF"
)
class TestFileProcessorInit:
"""Tests for FileProcessor initialization."""
def test_init_with_constraints(self):
"""Test initialization with ProviderConstraints."""
processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
assert processor.constraints == ANTHROPIC_CONSTRAINTS
def test_init_with_provider_string(self):
"""Test initialization with provider name string."""
processor = FileProcessor(constraints="anthropic")
assert processor.constraints == ANTHROPIC_CONSTRAINTS
def test_init_with_unknown_provider(self):
"""Test initialization with unknown provider sets constraints to None."""
processor = FileProcessor(constraints="unknown")
assert processor.constraints is None
def test_init_with_none_constraints(self):
"""Test initialization with None constraints."""
processor = FileProcessor(constraints=None)
assert processor.constraints is None
class TestFileProcessorValidate:
"""Tests for FileProcessor.validate method."""
def test_validate_valid_file(self):
"""Test validating a valid file returns no errors."""
processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
errors = processor.validate(file)
assert len(errors) == 0
def test_validate_without_constraints(self):
"""Test validating without constraints returns empty list."""
processor = FileProcessor(constraints=None)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
errors = processor.validate(file)
assert len(errors) == 0
def test_validate_strict_raises_on_error(self):
"""Test STRICT mode raises on validation error."""
constraints = ProviderConstraints(
name="test",
image=ImageConstraints(max_size_bytes=10),
)
processor = FileProcessor(constraints=constraints)
# Set mode to strict on the file
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
with pytest.raises(FileTooLargeError):
processor.validate(file)
class TestFileProcessorProcess:
"""Tests for FileProcessor.process method."""
def test_process_valid_file(self):
"""Test processing a valid file returns it unchanged."""
processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
result = processor.process(file)
assert result == file
def test_process_without_constraints(self):
"""Test processing without constraints returns file unchanged."""
processor = FileProcessor(constraints=None)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
result = processor.process(file)
assert result == file
def test_process_strict_raises_on_error(self):
"""Test STRICT mode raises on processing error."""
constraints = ProviderConstraints(
name="test",
image=ImageConstraints(max_size_bytes=10),
)
processor = FileProcessor(constraints=constraints)
# Set mode to strict on the file
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
with pytest.raises(FileTooLargeError):
processor.process(file)
def test_process_warn_returns_file(self):
"""Test WARN mode returns file with warning."""
constraints = ProviderConstraints(
name="test",
image=ImageConstraints(max_size_bytes=10),
)
processor = FileProcessor(constraints=constraints)
# Set mode to warn on the file
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="warn")
result = processor.process(file)
assert result == file
class TestFileProcessorProcessFiles:
"""Tests for FileProcessor.process_files method."""
def test_process_files_multiple(self):
"""Test processing multiple files."""
processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
files = {
"image1": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png")),
"image2": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test2.png")),
}
result = processor.process_files(files)
assert len(result) == 2
assert "image1" in result
assert "image2" in result
def test_process_files_empty(self):
"""Test processing empty files dict."""
processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
result = processor.process_files({})
assert result == {}
class TestFileHandlingEnum:
"""Tests for FileHandling enum."""
def test_enum_values(self):
"""Test all enum values are accessible."""
assert FileHandling.STRICT.value == "strict"
assert FileHandling.AUTO.value == "auto"
assert FileHandling.WARN.value == "warn"
assert FileHandling.CHUNK.value == "chunk"
class TestFileProcessorPerFileMode:
"""Tests for per-file mode handling."""
def test_file_default_mode_is_auto(self):
"""Test that files default to auto mode."""
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
assert file.mode == "auto"
def test_file_custom_mode(self):
"""Test setting custom mode on file."""
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
assert file.mode == "strict"
def test_processor_respects_file_mode(self):
"""Test processor uses each file's mode setting."""
constraints = ProviderConstraints(
name="test",
image=ImageConstraints(max_size_bytes=10),
)
processor = FileProcessor(constraints=constraints)
# File with strict mode should raise
strict_file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
with pytest.raises(FileTooLargeError):
processor.process(strict_file)
# File with warn mode should not raise
warn_file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="warn")
result = processor.process(warn_file)
assert result == warn_file

359
lib/crewai/tests/files/processing/test_transformers.py
View File

@@ -1,359 +0,0 @@
"""Unit tests for file transformers."""
import io
from unittest.mock import MagicMock, patch
import pytest
from crewai.files import ImageFile, PDFFile, TextFile
from crewai.files.file import FileBytes
from crewai.files.processing.exceptions import ProcessingDependencyError
from crewai.files.processing.transformers import (
chunk_pdf,
chunk_text,
get_image_dimensions,
get_pdf_page_count,
optimize_image,
resize_image,
)
def create_test_png(width: int = 100, height: int = 100) -> bytes:
"""Create a minimal valid PNG for testing."""
from PIL import Image
img = Image.new("RGB", (width, height), color="red")
buffer = io.BytesIO()
img.save(buffer, format="PNG")
return buffer.getvalue()
def create_test_pdf(num_pages: int = 1) -> bytes:
"""Create a minimal valid PDF for testing."""
from pypdf import PdfWriter
writer = PdfWriter()
for _ in range(num_pages):
writer.add_blank_page(width=612, height=792)
buffer = io.BytesIO()
writer.write(buffer)
return buffer.getvalue()
class TestResizeImage:
"""Tests for resize_image function."""
def test_resize_larger_image(self) -> None:
"""Test resizing an image larger than max dimensions."""
png_bytes = create_test_png(200, 150)
img = ImageFile(source=FileBytes(data=png_bytes, filename="test.png"))
result = resize_image(img, max_width=100, max_height=100)
dims = get_image_dimensions(result)
assert dims is not None
width, height = dims
assert width <= 100
assert height <= 100
def test_no_resize_if_within_bounds(self) -> None:
"""Test that small images are returned unchanged."""
png_bytes = create_test_png(50, 50)
img = ImageFile(source=FileBytes(data=png_bytes, filename="small.png"))
result = resize_image(img, max_width=100, max_height=100)
assert result is img
def test_preserve_aspect_ratio(self) -> None:
"""Test that aspect ratio is preserved during resize."""
png_bytes = create_test_png(200, 100)
img = ImageFile(source=FileBytes(data=png_bytes, filename="wide.png"))
result = resize_image(img, max_width=100, max_height=100)
dims = get_image_dimensions(result)
assert dims is not None
width, height = dims
assert width == 100
assert height == 50
def test_resize_without_aspect_ratio(self) -> None:
"""Test resizing without preserving aspect ratio."""
png_bytes = create_test_png(200, 100)
img = ImageFile(source=FileBytes(data=png_bytes, filename="wide.png"))
result = resize_image(
img, max_width=50, max_height=50, preserve_aspect_ratio=False
)
dims = get_image_dimensions(result)
assert dims is not None
width, height = dims
assert width == 50
assert height == 50
def test_resize_returns_image_file(self) -> None:
"""Test that resize returns an ImageFile instance."""
png_bytes = create_test_png(200, 200)
img = ImageFile(source=FileBytes(data=png_bytes, filename="test.png"))
result = resize_image(img, max_width=100, max_height=100)
assert isinstance(result, ImageFile)
def test_raises_without_pillow(self) -> None:
"""Test that ProcessingDependencyError is raised without Pillow."""
img = ImageFile(source=FileBytes(data=b"fake", filename="test.png"))
with patch.dict("sys.modules", {"PIL": None, "PIL.Image": None}):
with pytest.raises(ProcessingDependencyError) as exc_info:
# Force reimport to trigger ImportError
import importlib
import crewai.files.processing.transformers as t
importlib.reload(t)
t.resize_image(img, 100, 100)
assert "Pillow" in str(exc_info.value)
class TestOptimizeImage:
"""Tests for optimize_image function."""
def test_optimize_reduces_size(self) -> None:
"""Test that optimization reduces file size."""
png_bytes = create_test_png(500, 500)
original_size = len(png_bytes)
img = ImageFile(source=FileBytes(data=png_bytes, filename="large.png"))
result = optimize_image(img, target_size_bytes=original_size // 2)
result_size = len(result.read())
assert result_size < original_size
def test_no_optimize_if_under_target(self) -> None:
"""Test that small images are returned unchanged."""
png_bytes = create_test_png(50, 50)
img = ImageFile(source=FileBytes(data=png_bytes, filename="small.png"))
result = optimize_image(img, target_size_bytes=1024 * 1024)
assert result is img
def test_optimize_returns_image_file(self) -> None:
"""Test that optimize returns an ImageFile instance."""
png_bytes = create_test_png(200, 200)
img = ImageFile(source=FileBytes(data=png_bytes, filename="test.png"))
result = optimize_image(img, target_size_bytes=100)
assert isinstance(result, ImageFile)
def test_optimize_respects_min_quality(self) -> None:
"""Test that optimization stops at minimum quality."""
png_bytes = create_test_png(100, 100)
img = ImageFile(source=FileBytes(data=png_bytes, filename="test.png"))
# Request impossibly small size - should stop at min quality
result = optimize_image(img, target_size_bytes=10, min_quality=50)
assert isinstance(result, ImageFile)
assert len(result.read()) > 10
class TestChunkPdf:
"""Tests for chunk_pdf function."""
def test_chunk_splits_large_pdf(self) -> None:
"""Test that large PDFs are split into chunks."""
pdf_bytes = create_test_pdf(num_pages=10)
pdf = PDFFile(source=FileBytes(data=pdf_bytes, filename="large.pdf"))
result = list(chunk_pdf(pdf, max_pages=3))
assert len(result) == 4
assert all(isinstance(chunk, PDFFile) for chunk in result)
def test_no_chunk_if_within_limit(self) -> None:
"""Test that small PDFs are returned unchanged."""
pdf_bytes = create_test_pdf(num_pages=3)
pdf = PDFFile(source=FileBytes(data=pdf_bytes, filename="small.pdf"))
result = list(chunk_pdf(pdf, max_pages=5))
assert len(result) == 1
assert result[0] is pdf
def test_chunk_filenames(self) -> None:
"""Test that chunked files have indexed filenames."""
pdf_bytes = create_test_pdf(num_pages=6)
pdf = PDFFile(source=FileBytes(data=pdf_bytes, filename="document.pdf"))
result = list(chunk_pdf(pdf, max_pages=2))
assert result[0].filename == "document_chunk_0.pdf"
assert result[1].filename == "document_chunk_1.pdf"
assert result[2].filename == "document_chunk_2.pdf"
def test_chunk_with_overlap(self) -> None:
"""Test chunking with overlapping pages."""
pdf_bytes = create_test_pdf(num_pages=10)
pdf = PDFFile(source=FileBytes(data=pdf_bytes, filename="doc.pdf"))
result = list(chunk_pdf(pdf, max_pages=4, overlap_pages=1))
# With overlap, we get more chunks
assert len(result) >= 3
def test_chunk_page_counts(self) -> None:
"""Test that each chunk has correct page count."""
pdf_bytes = create_test_pdf(num_pages=7)
pdf = PDFFile(source=FileBytes(data=pdf_bytes, filename="doc.pdf"))
result = list(chunk_pdf(pdf, max_pages=3))
page_counts = [get_pdf_page_count(chunk) for chunk in result]
assert page_counts == [3, 3, 1]
class TestChunkText:
"""Tests for chunk_text function."""
def test_chunk_splits_large_text(self) -> None:
"""Test that large text files are split into chunks."""
content = "Hello world. " * 100
text = TextFile(source=content.encode(), filename="large.txt")
result = list(chunk_text(text, max_chars=200, overlap_chars=0))
assert len(result) > 1
assert all(isinstance(chunk, TextFile) for chunk in result)
def test_no_chunk_if_within_limit(self) -> None:
"""Test that small text files are returned unchanged."""
content = "Short text"
text = TextFile(source=content.encode(), filename="small.txt")
result = list(chunk_text(text, max_chars=1000, overlap_chars=0))
assert len(result) == 1
assert result[0] is text
def test_chunk_filenames(self) -> None:
"""Test that chunked files have indexed filenames."""
content = "A" * 500
text = TextFile(source=FileBytes(data=content.encode(), filename="data.txt"))
result = list(chunk_text(text, max_chars=200, overlap_chars=0))
assert result[0].filename == "data_chunk_0.txt"
assert result[1].filename == "data_chunk_1.txt"
assert len(result) == 3
def test_chunk_preserves_extension(self) -> None:
"""Test that file extension is preserved in chunks."""
content = "A" * 500
text = TextFile(source=FileBytes(data=content.encode(), filename="script.py"))
result = list(chunk_text(text, max_chars=200, overlap_chars=0))
assert all(chunk.filename.endswith(".py") for chunk in result)
def test_chunk_prefers_newline_boundaries(self) -> None:
"""Test that chunking prefers to split at newlines."""
content = "Line one\nLine two\nLine three\nLine four\nLine five"
text = TextFile(source=content.encode(), filename="lines.txt")
result = list(chunk_text(text, max_chars=25, overlap_chars=0, split_on_newlines=True))
# Should split at newline boundaries
for chunk in result:
chunk_text_content = chunk.read().decode()
# Chunks should end at newlines (except possibly the last)
if chunk != result[-1]:
assert chunk_text_content.endswith("\n") or len(chunk_text_content) <= 25
def test_chunk_with_overlap(self) -> None:
"""Test chunking with overlapping characters."""
content = "ABCDEFGHIJ" * 10
text = TextFile(source=content.encode(), filename="data.txt")
result = list(chunk_text(text, max_chars=30, overlap_chars=5))
# With overlap, chunks should share some content
assert len(result) >= 3
def test_chunk_overlap_larger_than_max_chars(self) -> None:
"""Test that overlap > max_chars doesn't cause infinite loop."""
content = "A" * 100
text = TextFile(source=content.encode(), filename="data.txt")
# overlap_chars > max_chars should still work (just with max overlap)
result = list(chunk_text(text, max_chars=20, overlap_chars=50))
assert len(result) > 1
# Should still complete without hanging
class TestGetImageDimensions:
"""Tests for get_image_dimensions function."""
def test_get_dimensions(self) -> None:
"""Test getting image dimensions."""
png_bytes = create_test_png(150, 100)
img = ImageFile(source=FileBytes(data=png_bytes, filename="test.png"))
dims = get_image_dimensions(img)
assert dims == (150, 100)
def test_returns_none_for_invalid_image(self) -> None:
"""Test that None is returned for invalid image data."""
img = ImageFile(source=FileBytes(data=b"not an image", filename="bad.png"))
dims = get_image_dimensions(img)
assert dims is None
def test_returns_none_without_pillow(self) -> None:
"""Test that None is returned when Pillow is not installed."""
png_bytes = create_test_png(100, 100)
img = ImageFile(source=FileBytes(data=png_bytes, filename="test.png"))
with patch.dict("sys.modules", {"PIL": None}):
# Can't easily test this without unloading module
# Just verify the function handles the case gracefully
pass
class TestGetPdfPageCount:
"""Tests for get_pdf_page_count function."""
def test_get_page_count(self) -> None:
"""Test getting PDF page count."""
pdf_bytes = create_test_pdf(num_pages=5)
pdf = PDFFile(source=FileBytes(data=pdf_bytes, filename="test.pdf"))
count = get_pdf_page_count(pdf)
assert count == 5
def test_single_page(self) -> None:
"""Test page count for single page PDF."""
pdf_bytes = create_test_pdf(num_pages=1)
pdf = PDFFile(source=FileBytes(data=pdf_bytes, filename="single.pdf"))
count = get_pdf_page_count(pdf)
assert count == 1
def test_returns_none_for_invalid_pdf(self) -> None:
"""Test that None is returned for invalid PDF data."""
pdf = PDFFile(source=FileBytes(data=b"not a pdf", filename="bad.pdf"))
count = get_pdf_page_count(pdf)
assert count is None

575
lib/crewai/tests/files/processing/test_validators.py
View File

@@ -1,575 +0,0 @@
"""Tests for file validators."""
from unittest.mock import patch
import pytest
from crewai.files import AudioFile, FileBytes, ImageFile, PDFFile, TextFile, VideoFile
from crewai.files.processing.constraints import (
ANTHROPIC_CONSTRAINTS,
AudioConstraints,
ImageConstraints,
PDFConstraints,
ProviderConstraints,
VideoConstraints,
)
from crewai.files.processing.exceptions import (
FileTooLargeError,
FileValidationError,
UnsupportedFileTypeError,
)
from crewai.files.processing.validators import (
_get_audio_duration,
_get_video_duration,
validate_audio,
validate_file,
validate_image,
validate_pdf,
validate_text,
validate_video,
)
# Minimal valid PNG: 8x8 pixel RGB image (valid for PIL)
MINIMAL_PNG = bytes([
0x89, 0x50, 0x4e, 0x47, 0x0d, 0x0a, 0x1a, 0x0a, 0x00, 0x00, 0x00, 0x0d,
0x49, 0x48, 0x44, 0x52, 0x00, 0x00, 0x00, 0x08, 0x00, 0x00, 0x00, 0x08,
0x08, 0x02, 0x00, 0x00, 0x00, 0x4b, 0x6d, 0x29, 0xdc, 0x00, 0x00, 0x00,
0x12, 0x49, 0x44, 0x41, 0x54, 0x78, 0x9c, 0x63, 0xfc, 0xcf, 0x80, 0x1d,
0x30, 0xe1, 0x10, 0x1f, 0xa4, 0x12, 0x00, 0xcd, 0x41, 0x01, 0x0f, 0xe8,
0x41, 0xe2, 0x6f, 0x00, 0x00, 0x00, 0x00, 0x49, 0x45, 0x4e, 0x44, 0xae,
0x42, 0x60, 0x82,
])
# Minimal valid PDF
MINIMAL_PDF = (
b"%PDF-1.4\n1 0 obj<</Type/Catalog/Pages 2 0 R>>endobj "
b"2 0 obj<</Type/Pages/Kids[3 0 R]/Count 1>>endobj "
b"3 0 obj<</Type/Page/MediaBox[0 0 612 792]/Parent 2 0 R>>endobj "
b"xref\n0 4\n0000000000 65535 f \n0000000009 00000 n \n"
b"0000000052 00000 n \n0000000101 00000 n \n"
b"trailer<</Size 4/Root 1 0 R>>\nstartxref\n178\n%%EOF"
)
class TestValidateImage:
"""Tests for validate_image function."""
def test_validate_valid_image(self):
"""Test validating a valid image within constraints."""
constraints = ImageConstraints(
max_size_bytes=10 * 1024 * 1024,
supported_formats=("image/png",),
)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
errors = validate_image(file, constraints, raise_on_error=False)
assert len(errors) == 0
def test_validate_image_too_large(self):
"""Test validating an image that exceeds size limit."""
constraints = ImageConstraints(
max_size_bytes=10, # Very small limit
supported_formats=("image/png",),
)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
with pytest.raises(FileTooLargeError) as exc_info:
validate_image(file, constraints)
assert "exceeds" in str(exc_info.value)
assert exc_info.value.file_name == "test.png"
def test_validate_image_unsupported_format(self):
"""Test validating an image with unsupported format."""
constraints = ImageConstraints(
max_size_bytes=10 * 1024 * 1024,
supported_formats=("image/jpeg",), # Only JPEG
)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
with pytest.raises(UnsupportedFileTypeError) as exc_info:
validate_image(file, constraints)
assert "not supported" in str(exc_info.value)
def test_validate_image_no_raise(self):
"""Test validating with raise_on_error=False returns errors list."""
constraints = ImageConstraints(
max_size_bytes=10,
supported_formats=("image/jpeg",),
)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
errors = validate_image(file, constraints, raise_on_error=False)
assert len(errors) == 2 # Size error and format error
class TestValidatePDF:
"""Tests for validate_pdf function."""
def test_validate_valid_pdf(self):
"""Test validating a valid PDF within constraints."""
constraints = PDFConstraints(
max_size_bytes=10 * 1024 * 1024,
)
file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
errors = validate_pdf(file, constraints, raise_on_error=False)
assert len(errors) == 0
def test_validate_pdf_too_large(self):
"""Test validating a PDF that exceeds size limit."""
constraints = PDFConstraints(
max_size_bytes=10, # Very small limit
)
file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
with pytest.raises(FileTooLargeError) as exc_info:
validate_pdf(file, constraints)
assert "exceeds" in str(exc_info.value)
class TestValidateText:
"""Tests for validate_text function."""
def test_validate_valid_text(self):
"""Test validating a valid text file."""
constraints = ProviderConstraints(
name="test",
general_max_size_bytes=10 * 1024 * 1024,
)
file = TextFile(source=FileBytes(data=b"Hello, World!", filename="test.txt"))
errors = validate_text(file, constraints, raise_on_error=False)
assert len(errors) == 0
def test_validate_text_too_large(self):
"""Test validating text that exceeds size limit."""
constraints = ProviderConstraints(
name="test",
general_max_size_bytes=5,
)
file = TextFile(source=FileBytes(data=b"Hello, World!", filename="test.txt"))
with pytest.raises(FileTooLargeError):
validate_text(file, constraints)
def test_validate_text_no_limit(self):
"""Test validating text with no size limit."""
constraints = ProviderConstraints(name="test")
file = TextFile(source=FileBytes(data=b"Hello, World!", filename="test.txt"))
errors = validate_text(file, constraints, raise_on_error=False)
assert len(errors) == 0
class TestValidateFile:
"""Tests for validate_file function."""
def test_validate_file_dispatches_to_image(self):
"""Test validate_file dispatches to image validator."""
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
errors = validate_file(file, ANTHROPIC_CONSTRAINTS, raise_on_error=False)
assert len(errors) == 0
def test_validate_file_dispatches_to_pdf(self):
"""Test validate_file dispatches to PDF validator."""
file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
errors = validate_file(file, ANTHROPIC_CONSTRAINTS, raise_on_error=False)
assert len(errors) == 0
def test_validate_file_unsupported_type(self):
"""Test validating a file type not supported by provider."""
constraints = ProviderConstraints(
name="test",
image=None, # No image support
)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
with pytest.raises(UnsupportedFileTypeError) as exc_info:
validate_file(file, constraints)
assert "does not support images" in str(exc_info.value)
def test_validate_file_pdf_not_supported(self):
"""Test validating PDF when provider doesn't support it."""
constraints = ProviderConstraints(
name="test",
pdf=None, # No PDF support
)
file = PDFFile(source=FileBytes(data=MINIMAL_PDF, filename="test.pdf"))
with pytest.raises(UnsupportedFileTypeError) as exc_info:
validate_file(file, constraints)
assert "does not support PDFs" in str(exc_info.value)
# Minimal audio bytes for testing (not a valid audio file, used for mocked tests)
MINIMAL_AUDIO = b"\x00" * 100
# Minimal video bytes for testing (not a valid video file, used for mocked tests)
MINIMAL_VIDEO = b"\x00" * 100
# Fallback content type when python-magic cannot detect
FALLBACK_CONTENT_TYPE = "application/octet-stream"
class TestValidateAudio:
"""Tests for validate_audio function and audio duration validation."""
def test_validate_valid_audio(self):
"""Test validating a valid audio file within constraints."""
constraints = AudioConstraints(
max_size_bytes=10 * 1024 * 1024,
supported_formats=("audio/mp3", "audio/mpeg", FALLBACK_CONTENT_TYPE),
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
errors = validate_audio(file, constraints, raise_on_error=False)
assert len(errors) == 0
def test_validate_audio_too_large(self):
"""Test validating an audio file that exceeds size limit."""
constraints = AudioConstraints(
max_size_bytes=10, # Very small limit
supported_formats=("audio/mp3", "audio/mpeg", FALLBACK_CONTENT_TYPE),
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
with pytest.raises(FileTooLargeError) as exc_info:
validate_audio(file, constraints)
assert "exceeds" in str(exc_info.value)
assert exc_info.value.file_name == "test.mp3"
def test_validate_audio_unsupported_format(self):
"""Test validating an audio file with unsupported format."""
constraints = AudioConstraints(
max_size_bytes=10 * 1024 * 1024,
supported_formats=("audio/wav",), # Only WAV
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
with pytest.raises(UnsupportedFileTypeError) as exc_info:
validate_audio(file, constraints)
assert "not supported" in str(exc_info.value)
@patch("crewai.files.processing.validators._get_audio_duration")
def test_validate_audio_duration_passes(self, mock_get_duration):
"""Test validating audio when duration is under limit."""
mock_get_duration.return_value = 30.0
constraints = AudioConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("audio/mp3", "audio/mpeg", FALLBACK_CONTENT_TYPE),
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
errors = validate_audio(file, constraints, raise_on_error=False)
assert len(errors) == 0
mock_get_duration.assert_called_once()
@patch("crewai.files.processing.validators._get_audio_duration")
def test_validate_audio_duration_fails(self, mock_get_duration):
"""Test validating audio when duration exceeds limit."""
mock_get_duration.return_value = 120.5
constraints = AudioConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("audio/mp3", "audio/mpeg", FALLBACK_CONTENT_TYPE),
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
with pytest.raises(FileValidationError) as exc_info:
validate_audio(file, constraints)
assert "duration" in str(exc_info.value).lower()
assert "120.5s" in str(exc_info.value)
assert "60s" in str(exc_info.value)
@patch("crewai.files.processing.validators._get_audio_duration")
def test_validate_audio_duration_no_raise(self, mock_get_duration):
"""Test audio duration validation with raise_on_error=False."""
mock_get_duration.return_value = 120.5
constraints = AudioConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("audio/mp3", "audio/mpeg", FALLBACK_CONTENT_TYPE),
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
errors = validate_audio(file, constraints, raise_on_error=False)
assert len(errors) == 1
assert "duration" in errors[0].lower()
@patch("crewai.files.processing.validators._get_audio_duration")
def test_validate_audio_duration_none_skips(self, mock_get_duration):
"""Test that duration validation is skipped when max_duration_seconds is None."""
constraints = AudioConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=None,
supported_formats=("audio/mp3", "audio/mpeg", FALLBACK_CONTENT_TYPE),
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
errors = validate_audio(file, constraints, raise_on_error=False)
assert len(errors) == 0
mock_get_duration.assert_not_called()
@patch("crewai.files.processing.validators._get_audio_duration")
def test_validate_audio_duration_detection_returns_none(self, mock_get_duration):
"""Test that validation passes when duration detection returns None."""
mock_get_duration.return_value = None
constraints = AudioConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("audio/mp3", "audio/mpeg", FALLBACK_CONTENT_TYPE),
)
file = AudioFile(source=FileBytes(data=MINIMAL_AUDIO, filename="test.mp3"))
errors = validate_audio(file, constraints, raise_on_error=False)
assert len(errors) == 0
class TestValidateVideo:
"""Tests for validate_video function and video duration validation."""
def test_validate_valid_video(self):
"""Test validating a valid video file within constraints."""
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
supported_formats=("video/mp4", FALLBACK_CONTENT_TYPE),
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
errors = validate_video(file, constraints, raise_on_error=False)
assert len(errors) == 0
def test_validate_video_too_large(self):
"""Test validating a video file that exceeds size limit."""
constraints = VideoConstraints(
max_size_bytes=10, # Very small limit
supported_formats=("video/mp4", FALLBACK_CONTENT_TYPE),
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
with pytest.raises(FileTooLargeError) as exc_info:
validate_video(file, constraints)
assert "exceeds" in str(exc_info.value)
assert exc_info.value.file_name == "test.mp4"
def test_validate_video_unsupported_format(self):
"""Test validating a video file with unsupported format."""
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
supported_formats=("video/webm",), # Only WebM
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
with pytest.raises(UnsupportedFileTypeError) as exc_info:
validate_video(file, constraints)
assert "not supported" in str(exc_info.value)
@patch("crewai.files.processing.validators._get_video_duration")
def test_validate_video_duration_passes(self, mock_get_duration):
"""Test validating video when duration is under limit."""
mock_get_duration.return_value = 30.0
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("video/mp4", FALLBACK_CONTENT_TYPE),
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
errors = validate_video(file, constraints, raise_on_error=False)
assert len(errors) == 0
mock_get_duration.assert_called_once()
@patch("crewai.files.processing.validators._get_video_duration")
def test_validate_video_duration_fails(self, mock_get_duration):
"""Test validating video when duration exceeds limit."""
mock_get_duration.return_value = 180.0
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("video/mp4", FALLBACK_CONTENT_TYPE),
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
with pytest.raises(FileValidationError) as exc_info:
validate_video(file, constraints)
assert "duration" in str(exc_info.value).lower()
assert "180.0s" in str(exc_info.value)
assert "60s" in str(exc_info.value)
@patch("crewai.files.processing.validators._get_video_duration")
def test_validate_video_duration_no_raise(self, mock_get_duration):
"""Test video duration validation with raise_on_error=False."""
mock_get_duration.return_value = 180.0
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("video/mp4", FALLBACK_CONTENT_TYPE),
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
errors = validate_video(file, constraints, raise_on_error=False)
assert len(errors) == 1
assert "duration" in errors[0].lower()
@patch("crewai.files.processing.validators._get_video_duration")
def test_validate_video_duration_none_skips(self, mock_get_duration):
"""Test that duration validation is skipped when max_duration_seconds is None."""
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=None,
supported_formats=("video/mp4", FALLBACK_CONTENT_TYPE),
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
errors = validate_video(file, constraints, raise_on_error=False)
assert len(errors) == 0
mock_get_duration.assert_not_called()
@patch("crewai.files.processing.validators._get_video_duration")
def test_validate_video_duration_detection_returns_none(self, mock_get_duration):
"""Test that validation passes when duration detection returns None."""
mock_get_duration.return_value = None
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("video/mp4", FALLBACK_CONTENT_TYPE),
)
file = VideoFile(source=FileBytes(data=MINIMAL_VIDEO, filename="test.mp4"))
errors = validate_video(file, constraints, raise_on_error=False)
assert len(errors) == 0
class TestGetAudioDuration:
"""Tests for _get_audio_duration helper function."""
def test_get_audio_duration_corrupt_file(self):
"""Test handling of corrupt audio data."""
corrupt_data = b"not valid audio data at all"
result = _get_audio_duration(corrupt_data)
assert result is None
class TestGetVideoDuration:
"""Tests for _get_video_duration helper function."""
def test_get_video_duration_corrupt_file(self):
"""Test handling of corrupt video data."""
corrupt_data = b"not valid video data at all"
result = _get_video_duration(corrupt_data)
assert result is None
class TestRealVideoFile:
"""Tests using real video fixture file."""
@pytest.fixture
def sample_video_path(self):
"""Path to sample video fixture."""
from pathlib import Path
path = Path(__file__).parent.parent.parent / "fixtures" / "sample_video.mp4"
if not path.exists():
pytest.skip("sample_video.mp4 fixture not found")
return path
@pytest.fixture
def sample_video_content(self, sample_video_path):
"""Read sample video content."""
return sample_video_path.read_bytes()
def test_get_video_duration_real_file(self, sample_video_content):
"""Test duration detection with real video file."""
try:
import av # noqa: F401
except ImportError:
pytest.skip("PyAV not installed")
duration = _get_video_duration(sample_video_content, "video/mp4")
assert duration is not None
assert 4.5 <= duration <= 5.5 # ~5 seconds with tolerance
def test_get_video_duration_real_file_no_format_hint(self, sample_video_content):
"""Test duration detection without format hint."""
try:
import av # noqa: F401
except ImportError:
pytest.skip("PyAV not installed")
duration = _get_video_duration(sample_video_content)
assert duration is not None
assert 4.5 <= duration <= 5.5
def test_validate_video_real_file_passes(self, sample_video_path):
"""Test validating real video file within constraints."""
try:
import av # noqa: F401
except ImportError:
pytest.skip("PyAV not installed")
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=60,
supported_formats=("video/mp4",),
)
file = VideoFile(source=str(sample_video_path))
errors = validate_video(file, constraints, raise_on_error=False)
assert len(errors) == 0
def test_validate_video_real_file_duration_exceeded(self, sample_video_path):
"""Test validating real video file that exceeds duration limit."""
try:
import av # noqa: F401
except ImportError:
pytest.skip("PyAV not installed")
constraints = VideoConstraints(
max_size_bytes=10 * 1024 * 1024,
max_duration_seconds=2, # Video is ~5 seconds
supported_formats=("video/mp4",),
)
file = VideoFile(source=str(sample_video_path))
with pytest.raises(FileValidationError) as exc_info:
validate_video(file, constraints)
assert "duration" in str(exc_info.value).lower()
assert "2s" in str(exc_info.value)

312
lib/crewai/tests/files/test_file_url.py
View File

@@ -1,312 +0,0 @@
"""Tests for FileUrl source type and URL resolution."""
from unittest.mock import AsyncMock, MagicMock, patch
import pytest
from crewai.files import FileBytes, FileUrl, ImageFile
from crewai.files.file import _normalize_source, FilePath
from crewai.files.resolved import InlineBase64, UrlReference
from crewai.files.resolver import FileResolver
class TestFileUrl:
"""Tests for FileUrl source type."""
def test_create_file_url(self):
"""Test creating FileUrl with valid URL."""
url = FileUrl(url="https://example.com/image.png")
assert url.url == "https://example.com/image.png"
assert url.filename is None
def test_create_file_url_with_filename(self):
"""Test creating FileUrl with custom filename."""
url = FileUrl(url="https://example.com/image.png", filename="custom.png")
assert url.url == "https://example.com/image.png"
assert url.filename == "custom.png"
def test_invalid_url_scheme_raises(self):
"""Test that non-http(s) URLs raise ValueError."""
with pytest.raises(ValueError, match="Invalid URL scheme"):
FileUrl(url="ftp://example.com/file.txt")
def test_invalid_url_scheme_file_raises(self):
"""Test that file:// URLs raise ValueError."""
with pytest.raises(ValueError, match="Invalid URL scheme"):
FileUrl(url="file:///path/to/file.txt")
def test_http_url_valid(self):
"""Test that HTTP URLs are valid."""
url = FileUrl(url="http://example.com/image.jpg")
assert url.url == "http://example.com/image.jpg"
def test_https_url_valid(self):
"""Test that HTTPS URLs are valid."""
url = FileUrl(url="https://example.com/image.jpg")
assert url.url == "https://example.com/image.jpg"
def test_content_type_guessing_png(self):
"""Test content type guessing for PNG files."""
url = FileUrl(url="https://example.com/image.png")
assert url.content_type == "image/png"
def test_content_type_guessing_jpeg(self):
"""Test content type guessing for JPEG files."""
url = FileUrl(url="https://example.com/photo.jpg")
assert url.content_type == "image/jpeg"
def test_content_type_guessing_pdf(self):
"""Test content type guessing for PDF files."""
url = FileUrl(url="https://example.com/document.pdf")
assert url.content_type == "application/pdf"
def test_content_type_guessing_with_query_params(self):
"""Test content type guessing with URL query parameters."""
url = FileUrl(url="https://example.com/image.png?v=123&token=abc")
assert url.content_type == "image/png"
def test_content_type_fallback_unknown(self):
"""Test content type falls back to octet-stream for unknown extensions."""
url = FileUrl(url="https://example.com/file.unknownext123")
assert url.content_type == "application/octet-stream"
def test_content_type_no_extension(self):
"""Test content type for URL without extension."""
url = FileUrl(url="https://example.com/file")
assert url.content_type == "application/octet-stream"
def test_read_fetches_content(self):
"""Test that read() fetches content from URL."""
url = FileUrl(url="https://example.com/image.png")
mock_response = MagicMock()
mock_response.content = b"fake image content"
mock_response.headers = {"content-type": "image/png"}
with patch("httpx.get", return_value=mock_response) as mock_get:
content = url.read()
mock_get.assert_called_once_with(
"https://example.com/image.png", follow_redirects=True
)
assert content == b"fake image content"
def test_read_caches_content(self):
"""Test that read() caches content."""
url = FileUrl(url="https://example.com/image.png")
mock_response = MagicMock()
mock_response.content = b"fake content"
mock_response.headers = {}
with patch("httpx.get", return_value=mock_response) as mock_get:
content1 = url.read()
content2 = url.read()
mock_get.assert_called_once()
assert content1 == content2
def test_read_updates_content_type_from_response(self):
"""Test that read() updates content type from response headers."""
url = FileUrl(url="https://example.com/file")
mock_response = MagicMock()
mock_response.content = b"fake content"
mock_response.headers = {"content-type": "image/webp; charset=utf-8"}
with patch("httpx.get", return_value=mock_response):
url.read()
assert url.content_type == "image/webp"
@pytest.mark.asyncio
async def test_aread_fetches_content(self):
"""Test that aread() fetches content from URL asynchronously."""
url = FileUrl(url="https://example.com/image.png")
mock_response = MagicMock()
mock_response.content = b"async fake content"
mock_response.headers = {"content-type": "image/png"}
mock_response.raise_for_status = MagicMock()
mock_client = MagicMock()
mock_client.get = AsyncMock(return_value=mock_response)
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
mock_client.__aexit__ = AsyncMock(return_value=None)
with patch("httpx.AsyncClient", return_value=mock_client):
content = await url.aread()
assert content == b"async fake content"
@pytest.mark.asyncio
async def test_aread_caches_content(self):
"""Test that aread() caches content."""
url = FileUrl(url="https://example.com/image.png")
mock_response = MagicMock()
mock_response.content = b"cached content"
mock_response.headers = {}
mock_response.raise_for_status = MagicMock()
mock_client = MagicMock()
mock_client.get = AsyncMock(return_value=mock_response)
mock_client.__aenter__ = AsyncMock(return_value=mock_client)
mock_client.__aexit__ = AsyncMock(return_value=None)
with patch("httpx.AsyncClient", return_value=mock_client):
content1 = await url.aread()
content2 = await url.aread()
mock_client.get.assert_called_once()
assert content1 == content2
class TestNormalizeSource:
"""Tests for _normalize_source with URL detection."""
def test_normalize_url_string(self):
"""Test that URL strings are converted to FileUrl."""
result = _normalize_source("https://example.com/image.png")
assert isinstance(result, FileUrl)
assert result.url == "https://example.com/image.png"
def test_normalize_http_url_string(self):
"""Test that HTTP URL strings are converted to FileUrl."""
result = _normalize_source("http://example.com/file.pdf")
assert isinstance(result, FileUrl)
assert result.url == "http://example.com/file.pdf"
def test_normalize_file_path_string(self, tmp_path):
"""Test that file path strings are converted to FilePath."""
test_file = tmp_path / "test.png"
test_file.write_bytes(b"test content")
result = _normalize_source(str(test_file))
assert isinstance(result, FilePath)
def test_normalize_relative_path_is_not_url(self):
"""Test that relative path strings are not treated as URLs."""
result = _normalize_source("https://example.com/file.png")
assert isinstance(result, FileUrl)
assert not isinstance(result, FilePath)
def test_normalize_file_url_passthrough(self):
"""Test that FileUrl instances pass through unchanged."""
original = FileUrl(url="https://example.com/image.png")
result = _normalize_source(original)
assert result is original
class TestResolverUrlHandling:
"""Tests for FileResolver URL handling."""
def test_resolve_url_source_for_supported_provider(self):
"""Test URL source resolves to UrlReference for supported providers."""
resolver = FileResolver()
file = ImageFile(source=FileUrl(url="https://example.com/image.png"))
resolved = resolver.resolve(file, "anthropic")
assert isinstance(resolved, UrlReference)
assert resolved.url == "https://example.com/image.png"
assert resolved.content_type == "image/png"
def test_resolve_url_source_openai(self):
"""Test URL source resolves to UrlReference for OpenAI."""
resolver = FileResolver()
file = ImageFile(source=FileUrl(url="https://example.com/photo.jpg"))
resolved = resolver.resolve(file, "openai")
assert isinstance(resolved, UrlReference)
assert resolved.url == "https://example.com/photo.jpg"
def test_resolve_url_source_gemini(self):
"""Test URL source resolves to UrlReference for Gemini."""
resolver = FileResolver()
file = ImageFile(source=FileUrl(url="https://example.com/image.webp"))
resolved = resolver.resolve(file, "gemini")
assert isinstance(resolved, UrlReference)
assert resolved.url == "https://example.com/image.webp"
def test_resolve_url_source_azure(self):
"""Test URL source resolves to UrlReference for Azure."""
resolver = FileResolver()
file = ImageFile(source=FileUrl(url="https://example.com/image.gif"))
resolved = resolver.resolve(file, "azure")
assert isinstance(resolved, UrlReference)
assert resolved.url == "https://example.com/image.gif"
def test_resolve_url_source_bedrock_fetches_content(self):
"""Test URL source fetches content for Bedrock (unsupported URLs)."""
resolver = FileResolver()
file_url = FileUrl(url="https://example.com/image.png")
file = ImageFile(source=file_url)
mock_response = MagicMock()
mock_response.content = b"\x89PNG\r\n\x1a\n" + b"\x00" * 50
mock_response.headers = {"content-type": "image/png"}
with patch("httpx.get", return_value=mock_response):
resolved = resolver.resolve(file, "bedrock")
assert not isinstance(resolved, UrlReference)
def test_resolve_bytes_source_still_works(self):
"""Test that bytes source still resolves normally."""
resolver = FileResolver()
minimal_png = (
b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x08\x00\x00\x00\x08"
b"\x01\x00\x00\x00\x00\xf9Y\xab\xcd\x00\x00\x00\nIDATx\x9cc`\x00\x00"
b"\x00\x02\x00\x01\xe2!\xbc3\x00\x00\x00\x00IEND\xaeB`\x82"
)
file = ImageFile(source=FileBytes(data=minimal_png, filename="test.png"))
resolved = resolver.resolve(file, "anthropic")
assert isinstance(resolved, InlineBase64)
@pytest.mark.asyncio
async def test_aresolve_url_source(self):
"""Test async URL resolution for supported provider."""
resolver = FileResolver()
file = ImageFile(source=FileUrl(url="https://example.com/image.png"))
resolved = await resolver.aresolve(file, "anthropic")
assert isinstance(resolved, UrlReference)
assert resolved.url == "https://example.com/image.png"
class TestImageFileWithUrl:
"""Tests for creating ImageFile with URL source."""
def test_image_file_from_url_string(self):
"""Test creating ImageFile from URL string."""
file = ImageFile(source="https://example.com/image.png")
assert isinstance(file.source, FileUrl)
assert file.source.url == "https://example.com/image.png"
def test_image_file_from_file_url(self):
"""Test creating ImageFile from FileUrl instance."""
url = FileUrl(url="https://example.com/photo.jpg")
file = ImageFile(source=url)
assert file.source is url
assert file.content_type == "image/jpeg"

135
lib/crewai/tests/files/test_resolved.py
View File

@@ -1,135 +0,0 @@
"""Tests for resolved file types."""
from datetime import datetime, timezone
import pytest
from crewai.files.resolved import (
FileReference,
InlineBase64,
InlineBytes,
ResolvedFile,
UrlReference,
)
class TestInlineBase64:
"""Tests for InlineBase64 resolved type."""
def test_create_inline_base64(self):
"""Test creating InlineBase64 instance."""
resolved = InlineBase64(
content_type="image/png",
data="iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==",
)
assert resolved.content_type == "image/png"
assert len(resolved.data) > 0
def test_inline_base64_is_resolved_file(self):
"""Test InlineBase64 is a ResolvedFile."""
resolved = InlineBase64(content_type="image/png", data="abc123")
assert isinstance(resolved, ResolvedFile)
def test_inline_base64_frozen(self):
"""Test InlineBase64 is immutable."""
resolved = InlineBase64(content_type="image/png", data="abc123")
with pytest.raises(Exception):
resolved.data = "xyz789"
class TestInlineBytes:
"""Tests for InlineBytes resolved type."""
def test_create_inline_bytes(self):
"""Test creating InlineBytes instance."""
data = b"\x89PNG\r\n\x1a\n"
resolved = InlineBytes(
content_type="image/png",
data=data,
)
assert resolved.content_type == "image/png"
assert resolved.data == data
def test_inline_bytes_is_resolved_file(self):
"""Test InlineBytes is a ResolvedFile."""
resolved = InlineBytes(content_type="image/png", data=b"test")
assert isinstance(resolved, ResolvedFile)
class TestFileReference:
"""Tests for FileReference resolved type."""
def test_create_file_reference(self):
"""Test creating FileReference instance."""
resolved = FileReference(
content_type="image/png",
file_id="file-abc123",
provider="gemini",
)
assert resolved.content_type == "image/png"
assert resolved.file_id == "file-abc123"
assert resolved.provider == "gemini"
assert resolved.expires_at is None
assert resolved.file_uri is None
def test_file_reference_with_expiry(self):
"""Test FileReference with expiry time."""
expiry = datetime.now(timezone.utc)
resolved = FileReference(
content_type="application/pdf",
file_id="file-xyz789",
provider="gemini",
expires_at=expiry,
)
assert resolved.expires_at == expiry
def test_file_reference_with_uri(self):
"""Test FileReference with URI."""
resolved = FileReference(
content_type="video/mp4",
file_id="file-video123",
provider="gemini",
file_uri="https://generativelanguage.googleapis.com/v1/files/file-video123",
)
assert resolved.file_uri is not None
def test_file_reference_is_resolved_file(self):
"""Test FileReference is a ResolvedFile."""
resolved = FileReference(
content_type="image/png",
file_id="file-123",
provider="anthropic",
)
assert isinstance(resolved, ResolvedFile)
class TestUrlReference:
"""Tests for UrlReference resolved type."""
def test_create_url_reference(self):
"""Test creating UrlReference instance."""
resolved = UrlReference(
content_type="image/png",
url="https://storage.googleapis.com/bucket/image.png",
)
assert resolved.content_type == "image/png"
assert resolved.url == "https://storage.googleapis.com/bucket/image.png"
def test_url_reference_is_resolved_file(self):
"""Test UrlReference is a ResolvedFile."""
resolved = UrlReference(
content_type="image/jpeg",
url="https://example.com/photo.jpg",
)
assert isinstance(resolved, ResolvedFile)

174
lib/crewai/tests/files/test_resolver.py
View File

@@ -1,174 +0,0 @@
"""Tests for FileResolver."""
import pytest
from crewai.files import FileBytes, ImageFile
from crewai.files.resolved import InlineBase64, InlineBytes
from crewai.files.resolver import (
FileResolver,
FileResolverConfig,
create_resolver,
)
from crewai.files.upload_cache import UploadCache
# Minimal valid PNG
MINIMAL_PNG = (
b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x08\x00\x00\x00\x08"
b"\x01\x00\x00\x00\x00\xf9Y\xab\xcd\x00\x00\x00\nIDATx\x9cc`\x00\x00"
b"\x00\x02\x00\x01\xe2!\xbc3\x00\x00\x00\x00IEND\xaeB`\x82"
)
class TestFileResolverConfig:
"""Tests for FileResolverConfig."""
def test_default_config(self):
"""Test default configuration values."""
config = FileResolverConfig()
assert config.prefer_upload is False
assert config.upload_threshold_bytes is None
assert config.use_bytes_for_bedrock is True
def test_custom_config(self):
"""Test custom configuration values."""
config = FileResolverConfig(
prefer_upload=True,
upload_threshold_bytes=1024 * 1024,
use_bytes_for_bedrock=False,
)
assert config.prefer_upload is True
assert config.upload_threshold_bytes == 1024 * 1024
assert config.use_bytes_for_bedrock is False
class TestFileResolver:
"""Tests for FileResolver class."""
def test_resolve_inline_base64(self):
"""Test resolving file as inline base64."""
resolver = FileResolver()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
resolved = resolver.resolve(file, "openai")
assert isinstance(resolved, InlineBase64)
assert resolved.content_type == "image/png"
assert len(resolved.data) > 0
def test_resolve_inline_bytes_for_bedrock(self):
"""Test resolving file as inline bytes for Bedrock."""
config = FileResolverConfig(use_bytes_for_bedrock=True)
resolver = FileResolver(config=config)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
resolved = resolver.resolve(file, "bedrock")
assert isinstance(resolved, InlineBytes)
assert resolved.content_type == "image/png"
assert resolved.data == MINIMAL_PNG
def test_resolve_files_multiple(self):
"""Test resolving multiple files."""
resolver = FileResolver()
files = {
"image1": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png")),
"image2": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test2.png")),
}
resolved = resolver.resolve_files(files, "openai")
assert len(resolved) == 2
assert "image1" in resolved
assert "image2" in resolved
assert all(isinstance(r, InlineBase64) for r in resolved.values())
def test_resolve_with_cache(self):
"""Test resolver uses cache."""
cache = UploadCache()
resolver = FileResolver(upload_cache=cache)
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
# First resolution
resolved1 = resolver.resolve(file, "openai")
# Second resolution (should use same base64 encoding)
resolved2 = resolver.resolve(file, "openai")
assert isinstance(resolved1, InlineBase64)
assert isinstance(resolved2, InlineBase64)
# Data should be identical
assert resolved1.data == resolved2.data
def test_clear_cache(self):
"""Test clearing resolver cache."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
# Add something to cache manually
cache.set(file=file, provider="gemini", file_id="test")
resolver = FileResolver(upload_cache=cache)
resolver.clear_cache()
assert len(cache) == 0
def test_get_cached_uploads(self):
"""Test getting cached uploads from resolver."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
cache.set(file=file, provider="gemini", file_id="test-1")
cache.set(file=file, provider="anthropic", file_id="test-2")
resolver = FileResolver(upload_cache=cache)
gemini_uploads = resolver.get_cached_uploads("gemini")
anthropic_uploads = resolver.get_cached_uploads("anthropic")
assert len(gemini_uploads) == 1
assert len(anthropic_uploads) == 1
def test_get_cached_uploads_empty(self):
"""Test getting cached uploads when no cache."""
resolver = FileResolver() # No cache
uploads = resolver.get_cached_uploads("gemini")
assert uploads == []
class TestCreateResolver:
"""Tests for create_resolver factory function."""
def test_create_default_resolver(self):
"""Test creating resolver with default settings."""
resolver = create_resolver()
assert resolver.config.prefer_upload is False
assert resolver.upload_cache is not None
def test_create_resolver_with_options(self):
"""Test creating resolver with custom options."""
resolver = create_resolver(
prefer_upload=True,
upload_threshold_bytes=5 * 1024 * 1024,
enable_cache=False,
)
assert resolver.config.prefer_upload is True
assert resolver.config.upload_threshold_bytes == 5 * 1024 * 1024
assert resolver.upload_cache is None
def test_create_resolver_cache_enabled(self):
"""Test resolver has cache when enabled."""
resolver = create_resolver(enable_cache=True)
assert resolver.upload_cache is not None
def test_create_resolver_cache_disabled(self):
"""Test resolver has no cache when disabled."""
resolver = create_resolver(enable_cache=False)
assert resolver.upload_cache is None

206
lib/crewai/tests/files/test_upload_cache.py
View File

@@ -1,206 +0,0 @@
"""Tests for upload cache."""
from datetime import datetime, timedelta, timezone
import pytest
from crewai.files import FileBytes, ImageFile
from crewai.files.upload_cache import CachedUpload, UploadCache
# Minimal valid PNG
MINIMAL_PNG = (
b"\x89PNG\r\n\x1a\n\x00\x00\x00\rIHDR\x00\x00\x00\x08\x00\x00\x00\x08"
b"\x01\x00\x00\x00\x00\xf9Y\xab\xcd\x00\x00\x00\nIDATx\x9cc`\x00\x00"
b"\x00\x02\x00\x01\xe2!\xbc3\x00\x00\x00\x00IEND\xaeB`\x82"
)
class TestCachedUpload:
"""Tests for CachedUpload dataclass."""
def test_cached_upload_creation(self):
"""Test creating a cached upload."""
now = datetime.now(timezone.utc)
cached = CachedUpload(
file_id="file-123",
provider="gemini",
file_uri="files/file-123",
content_type="image/png",
uploaded_at=now,
expires_at=now + timedelta(hours=48),
)
assert cached.file_id == "file-123"
assert cached.provider == "gemini"
assert cached.file_uri == "files/file-123"
assert cached.content_type == "image/png"
def test_is_expired_false(self):
"""Test is_expired returns False for non-expired upload."""
future = datetime.now(timezone.utc) + timedelta(hours=24)
cached = CachedUpload(
file_id="file-123",
provider="gemini",
file_uri=None,
content_type="image/png",
uploaded_at=datetime.now(timezone.utc),
expires_at=future,
)
assert cached.is_expired() is False
def test_is_expired_true(self):
"""Test is_expired returns True for expired upload."""
past = datetime.now(timezone.utc) - timedelta(hours=1)
cached = CachedUpload(
file_id="file-123",
provider="gemini",
file_uri=None,
content_type="image/png",
uploaded_at=datetime.now(timezone.utc) - timedelta(hours=2),
expires_at=past,
)
assert cached.is_expired() is True
def test_is_expired_no_expiry(self):
"""Test is_expired returns False when no expiry set."""
cached = CachedUpload(
file_id="file-123",
provider="anthropic",
file_uri=None,
content_type="image/png",
uploaded_at=datetime.now(timezone.utc),
expires_at=None,
)
assert cached.is_expired() is False
class TestUploadCache:
"""Tests for UploadCache class."""
def test_cache_creation(self):
"""Test creating an empty cache."""
cache = UploadCache()
assert len(cache) == 0
def test_set_and_get(self):
"""Test setting and getting cached uploads."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
cached = cache.set(
file=file,
provider="gemini",
file_id="file-123",
file_uri="files/file-123",
)
result = cache.get(file, "gemini")
assert result is not None
assert result.file_id == "file-123"
assert result.provider == "gemini"
def test_get_missing(self):
"""Test getting non-existent entry returns None."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
result = cache.get(file, "gemini")
assert result is None
def test_get_different_provider(self):
"""Test getting with different provider returns None."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
cache.set(file=file, provider="gemini", file_id="file-123")
result = cache.get(file, "anthropic") # Different provider
assert result is None
def test_remove(self):
"""Test removing cached entry."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
cache.set(file=file, provider="gemini", file_id="file-123")
removed = cache.remove(file, "gemini")
assert removed is True
assert cache.get(file, "gemini") is None
def test_remove_missing(self):
"""Test removing non-existent entry returns False."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
removed = cache.remove(file, "gemini")
assert removed is False
def test_remove_by_file_id(self):
"""Test removing by file ID."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
cache.set(file=file, provider="gemini", file_id="file-123")
removed = cache.remove_by_file_id("file-123", "gemini")
assert removed is True
assert len(cache) == 0
def test_clear_expired(self):
"""Test clearing expired entries."""
cache = UploadCache()
file1 = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png"))
file2 = ImageFile(source=FileBytes(data=MINIMAL_PNG + b"x", filename="test2.png"))
# Add one expired and one valid entry
past = datetime.now(timezone.utc) - timedelta(hours=1)
future = datetime.now(timezone.utc) + timedelta(hours=24)
cache.set(file=file1, provider="gemini", file_id="expired", expires_at=past)
cache.set(file=file2, provider="gemini", file_id="valid", expires_at=future)
removed = cache.clear_expired()
assert removed == 1
assert len(cache) == 1
assert cache.get(file2, "gemini") is not None
def test_clear(self):
"""Test clearing all entries."""
cache = UploadCache()
file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
cache.set(file=file, provider="gemini", file_id="file-123")
cache.set(file=file, provider="anthropic", file_id="file-456")
cleared = cache.clear()
assert cleared == 2
assert len(cache) == 0
def test_get_all_for_provider(self):
"""Test getting all cached uploads for a provider."""
cache = UploadCache()
file1 = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png"))
file2 = ImageFile(source=FileBytes(data=MINIMAL_PNG + b"x", filename="test2.png"))
file3 = ImageFile(source=FileBytes(data=MINIMAL_PNG + b"xx", filename="test3.png"))
cache.set(file=file1, provider="gemini", file_id="file-1")
cache.set(file=file2, provider="gemini", file_id="file-2")
cache.set(file=file3, provider="anthropic", file_id="file-3")
gemini_uploads = cache.get_all_for_provider("gemini")
anthropic_uploads = cache.get_all_for_provider("anthropic")
assert len(gemini_uploads) == 2
assert len(anthropic_uploads) == 1