refactor: extract files module to standalone crewai-files package

.pre-commit-config.yaml

@@ -19,7 +19,7 @@ repos:
         language: system
         pass_filenames: true
         types: [python]
-        exclude: ^(lib/crewai/src/crewai/cli/templates/|lib/crewai/tests/|lib/crewai-tools/tests/)
+        exclude: ^(lib/crewai/src/crewai/cli/templates/|lib/crewai/tests/|lib/crewai-tools/tests/|lib/crewai-files/tests/)
   - repo: https://github.com/astral-sh/uv-pre-commit
     rev: 0.9.3
     hooks:

conftest.py

@@ -160,7 +160,10 @@ def vcr_cassette_dir(request: Any) -> str:
     test_file = Path(request.fspath)
 
     for parent in test_file.parents:
-        if parent.name in ("crewai", "crewai-tools") and parent.parent.name == "lib":
+        if (
+            parent.name in ("crewai", "crewai-tools", "crewai-files")
+            and parent.parent.name == "lib"
+        ):
             package_root = parent
             break
     else:

lib/crewai-files/pyproject.toml

@@ -0,0 +1,25 @@
+[project]
+name = "crewai-files"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+authors = [
+    { name = "Greyson LaLonde", email = "greyson.r.lalonde@gmail.com" }
+]
+requires-python = ">=3.10, <3.14"
+dependencies = [
+    "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",
+]
+
+[project.scripts]
+crewai-files = "crewai_files:main"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

lib/crewai-files/src/crewai_files/__init__.py

@@ -1,11 +1,34 @@
 """File handling utilities for crewAI tasks."""
 
-from crewai.files.cleanup import (
+from crewai_files.cache.cleanup import (
     cleanup_expired_files,
     cleanup_provider_files,
     cleanup_uploaded_files,
 )
-from crewai.files.content_types import (
+from crewai_files.cache.upload_cache import (
+    CachedUpload,
+    UploadCache,
+    get_upload_cache,
+    reset_upload_cache,
+)
+from crewai_files.core.resolved import (
+    FileReference,
+    InlineBase64,
+    InlineBytes,
+    ResolvedFile,
+    ResolvedFileType,
+    UrlReference,
+)
+from crewai_files.core.sources import (
+    FileBytes,
+    FilePath,
+    FileSource,
+    FileSourceInput,
+    FileStream,
+    FileUrl,
+    RawFileInput,
+)
+from crewai_files.core.types import (
     AudioExtension,
     AudioFile,
     AudioMimeType,
@@ -26,16 +49,7 @@ from crewai.files.content_types import (
     VideoFile,
     VideoMimeType,
 )
-from crewai.files.file import (
+from crewai_files.processing import (
-    FileBytes,
-    FilePath,
-    FileSource,
-    FileSourceInput,
-    FileStream,
-    FileUrl,
-    RawFileInput,
-)
-from crewai.files.processing import (
     ANTHROPIC_CONSTRAINTS,
     BEDROCK_CONSTRAINTS,
     GEMINI_CONSTRAINTS,
@@ -54,27 +68,13 @@ from crewai.files.processing import (
     VideoConstraints,
     get_constraints_for_provider,
 )
-from crewai.files.resolved import (
+from crewai_files.resolution.resolver import (
-    FileReference,
-    InlineBase64,
-    InlineBytes,
-    ResolvedFile,
-    ResolvedFileType,
-    UrlReference,
-)
-from crewai.files.resolver import (
     FileResolver,
     FileResolverConfig,
     create_resolver,
 )
-from crewai.files.upload_cache import (
+from crewai_files.resolution.utils import normalize_input_files, wrap_file_source
-    CachedUpload,
+from crewai_files.uploaders import FileUploader, UploadResult, get_uploader
-    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__ = [

lib/crewai-files/src/crewai_files/cache/__init__.py

@@ -0,0 +1,14 @@
+"""Upload caching and cleanup."""
+
+from crewai_files.cache.cleanup import cleanup_uploaded_files
+from crewai_files.cache.metrics import FileOperationMetrics, measure_operation
+from crewai_files.cache.upload_cache import UploadCache, get_upload_cache
+
+
+__all__ = [
+    "FileOperationMetrics",
+    "UploadCache",
+    "cleanup_uploaded_files",
+    "get_upload_cache",
+    "measure_operation",
+]

lib/crewai-files/src/crewai_files/cache/cleanup.py

@@ -6,12 +6,13 @@ import asyncio
 import logging
 from typing import TYPE_CHECKING
 
-from crewai.files.upload_cache import CachedUpload, UploadCache
+from crewai_files.cache.upload_cache import CachedUpload, UploadCache
-from crewai.files.uploaders import get_uploader
+from crewai_files.uploaders import get_uploader
+from crewai_files.uploaders.factory import ProviderType
 
 
 if TYPE_CHECKING:
-    from crewai.files.uploaders.base import FileUploader
+    from crewai_files.uploaders.base import FileUploader
 
 logger = logging.getLogger(__name__)
 
@@ -46,7 +47,7 @@ def cleanup_uploaded_files(
     cache: UploadCache,
     *,
     delete_from_provider: bool = True,
-    providers: list[str] | None = None,
+    providers: list[ProviderType] | None = None,
 ) -> int:
     """Clean up uploaded files from the cache and optionally from providers.
 
@@ -60,7 +61,7 @@ def cleanup_uploaded_files(
     """
     cleaned = 0
 
-    provider_uploads: dict[str, list[CachedUpload]] = {}
+    provider_uploads: dict[ProviderType, list[CachedUpload]] = {}
 
     for provider in _get_providers_from_cache(cache):
         if providers is not None and provider not in providers:
@@ -126,7 +127,7 @@ def cleanup_expired_files(
 
 
 def cleanup_provider_files(
-    provider: str,
+    provider: ProviderType,
     *,
     cache: UploadCache | None = None,
     delete_all_from_provider: bool = False,
@@ -169,7 +170,7 @@ def cleanup_provider_files(
     return deleted
 
 
-def _get_providers_from_cache(cache: UploadCache) -> set[str]:
+def _get_providers_from_cache(cache: UploadCache) -> set[ProviderType]:
     """Get unique provider names from cache entries.
 
     Args:
@@ -211,7 +212,7 @@ async def acleanup_uploaded_files(
     cache: UploadCache,
     *,
     delete_from_provider: bool = True,
-    providers: list[str] | None = None,
+    providers: list[ProviderType] | None = None,
     max_concurrency: int = 10,
 ) -> int:
     """Async clean up uploaded files from the cache and optionally from providers.
@@ -227,7 +228,7 @@ async def acleanup_uploaded_files(
     """
     cleaned = 0
 
-    provider_uploads: dict[str, list[CachedUpload]] = {}
+    provider_uploads: dict[ProviderType, list[CachedUpload]] = {}
 
     for provider in _get_providers_from_cache(cache):
         if providers is not None and provider not in providers:
@@ -315,7 +316,7 @@ async def acleanup_expired_files(
 
 
 async def acleanup_provider_files(
-    provider: str,
+    provider: ProviderType,
     *,
     cache: UploadCache | None = None,
     delete_all_from_provider: bool = False,

lib/crewai-files/src/crewai_files/cache/upload_cache.py

@@ -15,11 +15,12 @@ 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
+from crewai_files.core.constants import DEFAULT_MAX_CACHE_ENTRIES, DEFAULT_TTL_SECONDS
+from crewai_files.uploaders.factory import ProviderType
 
 
 if TYPE_CHECKING:
-    from crewai.files.content_types import FileInput
+    from crewai_files.core.types import FileInput
 
 logger = logging.getLogger(__name__)
 
@@ -38,7 +39,7 @@ class CachedUpload:
     """
 
     file_id: str
-    provider: str
+    provider: ProviderType
     file_uri: str | None
     content_type: str
     uploaded_at: datetime
@@ -76,7 +77,7 @@ def _compute_file_hash(file: FileInput) -> str:
 
     Uses streaming for FilePath sources to avoid loading large files into memory.
     """
-    from crewai.files.file import FilePath
+    from crewai_files.core.sources import FilePath
 
     source = file._file_source
     if isinstance(source, FilePath):
@@ -116,7 +117,7 @@ class UploadCache:
         self.ttl = ttl
         self.namespace = namespace
         self.max_entries = max_entries
-        self._provider_keys: dict[str, set[str]] = {}
+        self._provider_keys: dict[ProviderType, set[str]] = {}
         self._key_access_order: list[str] = []
 
         if cache_type == "redis":
@@ -132,7 +133,7 @@ class UploadCache:
                 namespace=namespace,
             )
 
-    def _track_key(self, provider: str, key: str) -> None:
+    def _track_key(self, provider: ProviderType, 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()
@@ -141,7 +142,7 @@ class UploadCache:
             self._key_access_order.remove(key)
         self._key_access_order.append(key)
 
-    def _untrack_key(self, provider: str, key: str) -> None:
+    def _untrack_key(self, provider: ProviderType, key: str) -> None:
         """Remove key tracking for a provider."""
         if provider in self._provider_keys:
             self._provider_keys[provider].discard(key)
@@ -188,7 +189,9 @@ class UploadCache:
 
         return evicted
 
-    async def aget(self, file: FileInput, provider: str) -> CachedUpload | None:
+    async def aget(
+        self, file: FileInput, provider: ProviderType
+    ) -> CachedUpload | None:
         """Get a cached upload for a file.
 
         Args:
@@ -201,7 +204,9 @@ class UploadCache:
         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:
+    async def aget_by_hash(
+        self, file_hash: str, provider: ProviderType
+    ) -> CachedUpload | None:
         """Get a cached upload by file hash.
 
         Args:
@@ -227,7 +232,7 @@ class UploadCache:
     async def aset(
         self,
         file: FileInput,
-        provider: str,
+        provider: ProviderType,
         file_id: str,
         file_uri: str | None = None,
         expires_at: datetime | None = None,
@@ -258,7 +263,7 @@ class UploadCache:
         self,
         file_hash: str,
         content_type: str,
-        provider: str,
+        provider: ProviderType,
         file_id: str,
         file_uri: str | None = None,
         expires_at: datetime | None = None,
@@ -299,7 +304,7 @@ class UploadCache:
         logger.debug(f"Cached upload: {file_id} for provider {provider}")
         return cached
 
-    async def aremove(self, file: FileInput, provider: str) -> bool:
+    async def aremove(self, file: FileInput, provider: ProviderType) -> bool:
         """Remove a cached upload.
 
         Args:
@@ -318,7 +323,7 @@ class UploadCache:
             self._untrack_key(provider, key)
         return removed
 
-    async def aremove_by_file_id(self, file_id: str, provider: str) -> bool:
+    async def aremove_by_file_id(self, file_id: str, provider: ProviderType) -> bool:
         """Remove a cached upload by file ID.
 
         Args:
@@ -375,7 +380,7 @@ class UploadCache:
             logger.debug(f"Cleared {count} cache entries")
         return count
 
-    async def aget_all_for_provider(self, provider: str) -> list[CachedUpload]:
+    async def aget_all_for_provider(self, provider: ProviderType) -> list[CachedUpload]:
         """Get all cached uploads for a provider.
 
         Args:
@@ -407,12 +412,14 @@ class UploadCache:
             return future.result(timeout=30)
         return asyncio.run(coro)
 
-    def get(self, file: FileInput, provider: str) -> CachedUpload | None:
+    def get(self, file: FileInput, provider: ProviderType) -> 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:
+    def get_by_hash(
+        self, file_hash: str, provider: ProviderType
+    ) -> CachedUpload | None:
         """Sync wrapper for aget_by_hash."""
         result: CachedUpload | None = self._run_sync(
             self.aget_by_hash(file_hash, provider)
@@ -422,7 +429,7 @@ class UploadCache:
     def set(
         self,
         file: FileInput,
-        provider: str,
+        provider: ProviderType,
         file_id: str,
         file_uri: str | None = None,
         expires_at: datetime | None = None,
@@ -437,7 +444,7 @@ class UploadCache:
         self,
         file_hash: str,
         content_type: str,
-        provider: str,
+        provider: ProviderType,
         file_id: str,
         file_uri: str | None = None,
         expires_at: datetime | None = None,
@@ -450,12 +457,12 @@ class UploadCache:
         )
         return result
 
-    def remove(self, file: FileInput, provider: str) -> bool:
+    def remove(self, file: FileInput, provider: ProviderType) -> 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:
+    def remove_by_file_id(self, file_id: str, provider: ProviderType) -> bool:
         """Sync wrapper for aremove_by_file_id."""
         result: bool = self._run_sync(self.aremove_by_file_id(file_id, provider))
         return result
@@ -470,7 +477,7 @@ class UploadCache:
         result: int = self._run_sync(self.aclear())
         return result
 
-    def get_all_for_provider(self, provider: str) -> list[CachedUpload]:
+    def get_all_for_provider(self, provider: ProviderType) -> list[CachedUpload]:
         """Sync wrapper for aget_all_for_provider."""
         result: list[CachedUpload] = self._run_sync(
             self.aget_all_for_provider(provider)
@@ -481,7 +488,7 @@ class UploadCache:
         """Return the number of cached entries."""
         return sum(len(keys) for keys in self._provider_keys.values())
 
-    def get_providers(self) -> builtins.set[str]:
+    def get_providers(self) -> builtins.set[ProviderType]:
         """Get all provider names that have cached entries.
 
         Returns:
@@ -535,7 +542,7 @@ def _cleanup_on_exit() -> None:
     if _default_cache is None or len(_default_cache) == 0:
         return
 
-    from crewai.files.cleanup import cleanup_uploaded_files
+    from crewai_files.cache.cleanup import cleanup_uploaded_files
 
     try:
         cleanup_uploaded_files(_default_cache)

lib/crewai-files/src/crewai_files/core/__init__.py

@@ -0,0 +1,92 @@
+"""Core file types and sources."""
+
+from crewai_files.core.constants import (
+    BACKOFF_BASE_DELAY,
+    BACKOFF_JITTER_FACTOR,
+    BACKOFF_MAX_DELAY,
+    DEFAULT_MAX_CACHE_ENTRIES,
+    DEFAULT_MAX_FILE_SIZE_BYTES,
+    DEFAULT_TTL_SECONDS,
+    DEFAULT_UPLOAD_CHUNK_SIZE,
+    FILES_API_MAX_SIZE,
+    GEMINI_FILE_TTL,
+    MAGIC_BUFFER_SIZE,
+    MAX_CONCURRENCY,
+    MULTIPART_CHUNKSIZE,
+    MULTIPART_THRESHOLD,
+    UPLOAD_MAX_RETRIES,
+    UPLOAD_RETRY_DELAY_BASE,
+)
+from crewai_files.core.resolved import (
+    FileReference,
+    InlineBase64,
+    InlineBytes,
+    ResolvedFile,
+    UrlReference,
+)
+from crewai_files.core.sources import (
+    AsyncFileStream,
+    FileBytes,
+    FilePath,
+    FileSource,
+    FileStream,
+    FileUrl,
+)
+from crewai_files.core.types import (
+    AudioFile,
+    AudioMimeType,
+    BaseFile,
+    CoercedFileSource,
+    File,
+    FileInput,
+    FileMode,
+    ImageFile,
+    ImageMimeType,
+    PDFFile,
+    TextFile,
+    VideoFile,
+    VideoMimeType,
+)
+
+
+__all__ = [
+    "BACKOFF_BASE_DELAY",
+    "BACKOFF_JITTER_FACTOR",
+    "BACKOFF_MAX_DELAY",
+    "DEFAULT_MAX_CACHE_ENTRIES",
+    "DEFAULT_MAX_FILE_SIZE_BYTES",
+    "DEFAULT_TTL_SECONDS",
+    "DEFAULT_UPLOAD_CHUNK_SIZE",
+    "FILES_API_MAX_SIZE",
+    "GEMINI_FILE_TTL",
+    "MAGIC_BUFFER_SIZE",
+    "MAX_CONCURRENCY",
+    "MULTIPART_CHUNKSIZE",
+    "MULTIPART_THRESHOLD",
+    "UPLOAD_MAX_RETRIES",
+    "UPLOAD_RETRY_DELAY_BASE",
+    "AsyncFileStream",
+    "AudioFile",
+    "AudioMimeType",
+    "BaseFile",
+    "CoercedFileSource",
+    "File",
+    "FileBytes",
+    "FileInput",
+    "FileMode",
+    "FilePath",
+    "FileReference",
+    "FileSource",
+    "FileStream",
+    "FileUrl",
+    "ImageFile",
+    "ImageMimeType",
+    "InlineBase64",
+    "InlineBytes",
+    "PDFFile",
+    "ResolvedFile",
+    "TextFile",
+    "UrlReference",
+    "VideoFile",
+    "VideoMimeType",
+]

lib/crewai-files/src/crewai_files/core/sources.py

@@ -17,8 +17,9 @@ from pydantic import (
     model_validator,
 )
 from pydantic_core import CoreSchema, core_schema
+from typing_extensions import TypeIs
 
-from crewai.files.constants import DEFAULT_MAX_FILE_SIZE_BYTES, MAGIC_BUFFER_SIZE
+from crewai_files.core.constants import DEFAULT_MAX_FILE_SIZE_BYTES, MAGIC_BUFFER_SIZE
 
 
 @runtime_checkable
@@ -146,7 +147,7 @@ class FilePath(BaseModel):
     @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
+        from crewai_files.processing.exceptions import FileTooLargeError
 
         path_str = str(self.path)
         if ".." in path_str:
@@ -482,6 +483,11 @@ class FileUrl(BaseModel):
 FileSource = FilePath | FileBytes | FileStream | AsyncFileStream | FileUrl
 
 
+def is_file_source(v: object) -> TypeIs[FileSource]:
+    """Type guard to narrow input to FileSource."""
+    return isinstance(v, (FilePath, FileBytes, FileStream, FileUrl))
+
+
 def _normalize_source(value: Any) -> FileSource:
     """Convert raw input to appropriate source type."""
     if isinstance(value, (FilePath, FileBytes, FileStream, AsyncFileStream, FileUrl)):

lib/crewai-files/src/crewai_files/core/types.py

@@ -10,15 +10,15 @@ 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 (
+from crewai_files.core.sources import (
     AsyncFileStream,
     FileBytes,
     FilePath,
     FileSource,
     FileStream,
     FileUrl,
+    is_file_source,
 )
-from crewai.files.utils import is_file_source
 
 
 FileSourceInput = str | Path | bytes | IOBase | FileSource

lib/crewai-files/src/crewai_files/processing/__init__.py

@@ -4,7 +4,7 @@ This module provides validation, transformation, and processing utilities
 for files used in multimodal LLM interactions.
 """
 
-from crewai.files.processing.constraints import (
+from crewai_files.processing.constraints import (
     ANTHROPIC_CONSTRAINTS,
     BEDROCK_CONSTRAINTS,
     GEMINI_CONSTRAINTS,
@@ -16,16 +16,16 @@ from crewai.files.processing.constraints import (
     VideoConstraints,
     get_constraints_for_provider,
 )
-from crewai.files.processing.enums import FileHandling
+from crewai_files.processing.enums import FileHandling
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     FileProcessingError,
     FileTooLargeError,
     FileValidationError,
     ProcessingDependencyError,
     UnsupportedFileTypeError,
 )
-from crewai.files.processing.processor import FileProcessor
+from crewai_files.processing.processor import FileProcessor
-from crewai.files.processing.validators import (
+from crewai_files.processing.validators import (
     validate_audio,
     validate_file,
     validate_image,

lib/crewai-files/src/crewai_files/processing/constraints.py

@@ -4,7 +4,7 @@ from dataclasses import dataclass
 from functools import lru_cache
 from typing import Literal
 
-from crewai.files.content_types import (
+from crewai_files.core.types import (
     AudioMimeType,
     ImageMimeType,
     VideoMimeType,

lib/crewai-files/src/crewai_files/processing/processor.py

@@ -4,7 +4,7 @@ import asyncio
 from collections.abc import Sequence
 import logging
 
-from crewai.files.content_types import (
+from crewai_files.core.types import (
     AudioFile,
     File,
     FileInput,
@@ -13,18 +13,18 @@ from crewai.files.content_types import (
     TextFile,
     VideoFile,
 )
-from crewai.files.processing.constraints import (
+from crewai_files.processing.constraints import (
     ProviderConstraints,
     get_constraints_for_provider,
 )
-from crewai.files.processing.enums import FileHandling
+from crewai_files.processing.enums import FileHandling
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     FileProcessingError,
     FileTooLargeError,
     FileValidationError,
     UnsupportedFileTypeError,
 )
-from crewai.files.processing.transformers import (
+from crewai_files.processing.transformers import (
     chunk_pdf,
     chunk_text,
     get_image_dimensions,
@@ -32,7 +32,7 @@ from crewai.files.processing.transformers import (
     optimize_image,
     resize_image,
 )
-from crewai.files.processing.validators import validate_file
+from crewai_files.processing.validators import validate_file
 
 
 logger = logging.getLogger(__name__)

lib/crewai-files/src/crewai_files/processing/transformers.py

@@ -4,9 +4,9 @@ from collections.abc import Iterator
 import io
 import logging
 
-from crewai.files.content_types import ImageFile, PDFFile, TextFile
+from crewai_files.core.sources import FileBytes
-from crewai.files.file import FileBytes
+from crewai_files.core.types import ImageFile, PDFFile, TextFile
-from crewai.files.processing.exceptions import ProcessingDependencyError
+from crewai_files.processing.exceptions import ProcessingDependencyError
 
 
 logger = logging.getLogger(__name__)

lib/crewai-files/src/crewai_files/processing/validators.py

@@ -4,7 +4,7 @@ from collections.abc import Sequence
 import io
 import logging
 
-from crewai.files.content_types import (
+from crewai_files.core.types import (
     AudioFile,
     FileInput,
     ImageFile,
@@ -12,14 +12,14 @@ from crewai.files.content_types import (
     TextFile,
     VideoFile,
 )
-from crewai.files.processing.constraints import (
+from crewai_files.processing.constraints import (
     AudioConstraints,
     ImageConstraints,
     PDFConstraints,
     ProviderConstraints,
     VideoConstraints,
 )
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     FileTooLargeError,
     FileValidationError,
     UnsupportedFileTypeError,

lib/crewai-files/src/crewai_files/resolution/__init__.py

@@ -0,0 +1,16 @@
+"""File resolution logic."""
+
+from crewai_files.resolution.resolver import FileResolver
+from crewai_files.resolution.utils import (
+    is_file_source,
+    normalize_input_files,
+    wrap_file_source,
+)
+
+
+__all__ = [
+    "FileResolver",
+    "is_file_source",
+    "normalize_input_files",
+    "wrap_file_source",
+]

lib/crewai-files/src/crewai_files/resolution/resolver.py

@@ -6,11 +6,19 @@ from dataclasses import dataclass, field
 import hashlib
 import logging
 
-from crewai.files.constants import UPLOAD_MAX_RETRIES, UPLOAD_RETRY_DELAY_BASE
+from crewai_files.cache.metrics import measure_operation
-from crewai.files.content_types import FileInput
+from crewai_files.cache.upload_cache import CachedUpload, UploadCache
-from crewai.files.file import FileUrl
+from crewai_files.core.constants import UPLOAD_MAX_RETRIES, UPLOAD_RETRY_DELAY_BASE
-from crewai.files.metrics import measure_operation
+from crewai_files.core.resolved import (
-from crewai.files.processing.constraints import (
+    FileReference,
+    InlineBase64,
+    InlineBytes,
+    ResolvedFile,
+    UrlReference,
+)
+from crewai_files.core.sources import FileUrl
+from crewai_files.core.types import FileInput
+from crewai_files.processing.constraints import (
     AudioConstraints,
     ImageConstraints,
     PDFConstraints,
@@ -18,17 +26,9 @@ from crewai.files.processing.constraints import (
     VideoConstraints,
     get_constraints_for_provider,
 )
-from crewai.files.resolved import (
+from crewai_files.uploaders import UploadResult, get_uploader
-    FileReference,
+from crewai_files.uploaders.base import FileUploader
-    InlineBase64,
+from crewai_files.uploaders.factory import ProviderType
-    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__)
@@ -340,7 +340,7 @@ class FileResolver:
         """
         import time
 
-        from crewai.files.processing.exceptions import (
+        from crewai_files.processing.exceptions import (
             PermanentUploadError,
             TransientUploadError,
         )
@@ -555,7 +555,7 @@ class FileResolver:
         Returns:
             UploadResult if successful, None otherwise.
         """
-        from crewai.files.processing.exceptions import (
+        from crewai_files.processing.exceptions import (
             PermanentUploadError,
             TransientUploadError,
         )
@@ -617,7 +617,7 @@ class FileResolver:
 
         return self._uploaders.get(provider)
 
-    def get_cached_uploads(self, provider: str) -> list[CachedUpload]:
+    def get_cached_uploads(self, provider: ProviderType) -> list[CachedUpload]:
         """Get all cached uploads for a provider.
 
         Args:

lib/crewai-files/src/crewai_files/resolution/utils.py

@@ -5,19 +5,15 @@ from __future__ import annotations
 from pathlib import Path
 from typing import TYPE_CHECKING
 
-from typing_extensions import TypeIs
+from crewai_files.core.sources import is_file_source
 
 
 if TYPE_CHECKING:
-    from crewai.files.content_types import FileInput
+    from crewai_files.core.sources import FileSource, FileSourceInput
-    from crewai.files.file import FileSource, FileSourceInput
+    from crewai_files.core.types import FileInput
 
 
-def is_file_source(v: object) -> TypeIs[FileSource]:
+__all__ = ["is_file_source", "normalize_input_files", "wrap_file_source"]
-    """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:
@@ -29,7 +25,7 @@ def wrap_file_source(source: FileSource) -> FileInput:
     Returns:
         Typed FileInput wrapper based on content type.
     """
-    from crewai.files.content_types import (
+    from crewai_files.core.types import (
         AudioFile,
         ImageFile,
         PDFFile,
@@ -61,8 +57,8 @@ def normalize_input_files(
     Returns:
         Dictionary mapping names to FileInput wrappers.
     """
-    from crewai.files.content_types import BaseFile
+    from crewai_files.core.sources import FileBytes, FilePath, FileStream, FileUrl
-    from crewai.files.file import FileBytes, FilePath, FileStream, FileUrl
+    from crewai_files.core.types import BaseFile
 
     result: dict[str, FileInput] = {}
 

lib/crewai-files/src/crewai_files/uploaders/__init__.py

@@ -1,7 +1,7 @@
 """File uploader implementations for provider File APIs."""
 
-from crewai.files.uploaders.base import FileUploader, UploadResult
+from crewai_files.uploaders.base import FileUploader, UploadResult
-from crewai.files.uploaders.factory import get_uploader
+from crewai_files.uploaders.factory import get_uploader
 
 
 __all__ = [

lib/crewai-files/src/crewai_files/uploaders/anthropic.py

@@ -7,9 +7,9 @@ import logging
 import os
 from typing import Any
 
-from crewai.files.content_types import FileInput
+from crewai_files.core.types import FileInput
-from crewai.files.processing.exceptions import classify_upload_error
+from crewai_files.processing.exceptions import classify_upload_error
-from crewai.files.uploaders.base import FileUploader, UploadResult
+from crewai_files.uploaders.base import FileUploader, UploadResult
 
 
 logger = logging.getLogger(__name__)

lib/crewai-files/src/crewai_files/uploaders/base.py

@@ -6,7 +6,7 @@ from dataclasses import dataclass
 from datetime import datetime
 from typing import Any
 
-from crewai.files.content_types import FileInput
+from crewai_files.core.types import FileInput
 
 
 @dataclass

lib/crewai-files/src/crewai_files/uploaders/bedrock.py

@@ -8,18 +8,18 @@ import os
 from pathlib import Path
 from typing import Any
 
-from crewai.files.constants import (
+from crewai_files.core.constants import (
     MAX_CONCURRENCY,
     MULTIPART_CHUNKSIZE,
     MULTIPART_THRESHOLD,
 )
-from crewai.files.content_types import FileInput
+from crewai_files.core.sources import FileBytes, FilePath
-from crewai.files.file import FileBytes, FilePath
+from crewai_files.core.types import FileInput
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     PermanentUploadError,
     TransientUploadError,
 )
-from crewai.files.uploaders.base import FileUploader, UploadResult
+from crewai_files.uploaders.base import FileUploader, UploadResult
 
 
 logger = logging.getLogger(__name__)

lib/crewai-files/src/crewai_files/uploaders/factory.py

@@ -7,10 +7,10 @@ from typing import Literal, TypeAlias, TypedDict, overload
 
 from typing_extensions import NotRequired, Unpack
 
-from crewai.files.uploaders.anthropic import AnthropicFileUploader
+from crewai_files.uploaders.anthropic import AnthropicFileUploader
-from crewai.files.uploaders.bedrock import BedrockFileUploader
+from crewai_files.uploaders.bedrock import BedrockFileUploader
-from crewai.files.uploaders.gemini import GeminiFileUploader
+from crewai_files.uploaders.gemini import GeminiFileUploader
-from crewai.files.uploaders.openai import OpenAIFileUploader
+from crewai_files.uploaders.openai import OpenAIFileUploader
 
 
 logger = logging.getLogger(__name__)
@@ -25,7 +25,7 @@ FileUploaderType: TypeAlias = (
 
 GeminiProviderType = Literal["gemini", "google"]
 AnthropicProviderType = Literal["anthropic", "claude"]
-OpenAIProviderType = Literal["openai", "gpt"]
+OpenAIProviderType = Literal["openai", "gpt", "azure"]
 BedrockProviderType = Literal["bedrock", "aws"]
 
 ProviderType: TypeAlias = (
@@ -131,7 +131,7 @@ def get_uploader(
 
     if "gemini" in provider_lower or "google" in provider_lower:
         try:
-            from crewai.files.uploaders.gemini import GeminiFileUploader
+            from crewai_files.uploaders.gemini import GeminiFileUploader
 
             return GeminiFileUploader(api_key=kwargs.get("api_key"))
         except ImportError:
@@ -142,7 +142,7 @@ def get_uploader(
 
     if "anthropic" in provider_lower or "claude" in provider_lower:
         try:
-            from crewai.files.uploaders.anthropic import AnthropicFileUploader
+            from crewai_files.uploaders.anthropic import AnthropicFileUploader
 
             return AnthropicFileUploader(api_key=kwargs.get("api_key"))
         except ImportError:
@@ -151,9 +151,13 @@ def get_uploader(
             )
             raise
 
-    if "openai" in provider_lower or "gpt" in provider_lower:
+    if (
+        "openai" in provider_lower
+        or "gpt" in provider_lower
+        or "azure" in provider_lower
+    ):
         try:
-            from crewai.files.uploaders.openai import OpenAIFileUploader
+            from crewai_files.uploaders.openai import OpenAIFileUploader
 
             return OpenAIFileUploader(
                 api_key=kwargs.get("api_key"),
@@ -176,7 +180,7 @@ def get_uploader(
             )
             raise
         try:
-            from crewai.files.uploaders.bedrock import BedrockFileUploader
+            from crewai_files.uploaders.bedrock import BedrockFileUploader
 
             return BedrockFileUploader(
                 bucket_name=kwargs.get("bucket_name"),

lib/crewai-files/src/crewai_files/uploaders/gemini.py

@@ -12,20 +12,20 @@ import random
 import time
 from typing import Any
 
-from crewai.files.constants import (
+from crewai_files.core.constants import (
     BACKOFF_BASE_DELAY,
     BACKOFF_JITTER_FACTOR,
     BACKOFF_MAX_DELAY,
     GEMINI_FILE_TTL,
 )
-from crewai.files.content_types import FileInput
+from crewai_files.core.sources import FilePath
-from crewai.files.file import FilePath
+from crewai_files.core.types import FileInput
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     PermanentUploadError,
     TransientUploadError,
     classify_upload_error,
 )
-from crewai.files.uploaders.base import FileUploader, UploadResult
+from crewai_files.uploaders.base import FileUploader, UploadResult
 
 
 logger = logging.getLogger(__name__)

lib/crewai-files/src/crewai_files/uploaders/openai.py

@@ -8,15 +8,15 @@ import logging
 import os
 from typing import Any
 
-from crewai.files.constants import DEFAULT_UPLOAD_CHUNK_SIZE, FILES_API_MAX_SIZE
+from crewai_files.core.constants import DEFAULT_UPLOAD_CHUNK_SIZE, FILES_API_MAX_SIZE
-from crewai.files.content_types import FileInput
+from crewai_files.core.sources import FileBytes, FilePath, FileStream
-from crewai.files.file import FileBytes, FilePath, FileStream
+from crewai_files.core.types import FileInput
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     PermanentUploadError,
     TransientUploadError,
     classify_upload_error,
 )
-from crewai.files.uploaders.base import FileUploader, UploadResult
+from crewai_files.uploaders.base import FileUploader, UploadResult
 
 
 logger = logging.getLogger(__name__)

lib/crewai-files/tests/processing/test_constraints.py

@@ -1,8 +1,6 @@
 """Tests for provider constraints."""
 
-import pytest
+from crewai_files.processing.constraints import (
-
-from crewai.files.processing.constraints import (
     ANTHROPIC_CONSTRAINTS,
     BEDROCK_CONSTRAINTS,
     GEMINI_CONSTRAINTS,
@@ -14,6 +12,7 @@ from crewai.files.processing.constraints import (
     VideoConstraints,
     get_constraints_for_provider,
 )
+import pytest
 
 
 class TestImageConstraints:

lib/crewai-files/tests/processing/test_processor.py

@@ -1,32 +1,99 @@
 """Tests for FileProcessor class."""
 
-import pytest
+from crewai_files import FileBytes, ImageFile
-
+from crewai_files.processing.constraints import (
-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.enums import FileHandling
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     FileTooLargeError,
-    FileValidationError,
 )
-from crewai.files.processing.processor import FileProcessor
+from crewai_files.processing.processor import FileProcessor
+import pytest
 
 
 # Minimal valid PNG: 8x8 pixel RGB image (valid for PIL)
-MINIMAL_PNG = bytes([
+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,
+        0x89,
-    0x08, 0x02, 0x00, 0x00, 0x00, 0x4b, 0x6d, 0x29, 0xdc, 0x00, 0x00, 0x00,
+        0x50,
-    0x12, 0x49, 0x44, 0x41, 0x54, 0x78, 0x9c, 0x63, 0xfc, 0xcf, 0x80, 0x1d,
+        0x4E,
-    0x30, 0xe1, 0x10, 0x1f, 0xa4, 0x12, 0x00, 0xcd, 0x41, 0x01, 0x0f, 0xe8,
+        0x47,
-    0x41, 0xe2, 0x6f, 0x00, 0x00, 0x00, 0x00, 0x49, 0x45, 0x4e, 0x44, 0xae,
+        0x0D,
-    0x42, 0x60, 0x82,
+        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 = (
@@ -96,7 +163,9 @@ class TestFileProcessorValidate:
         )
         processor = FileProcessor(constraints=constraints)
         # Set mode to strict on the file
-        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+        file = ImageFile(
+            source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict"
+        )
 
         with pytest.raises(FileTooLargeError):
             processor.validate(file)
@@ -131,7 +200,9 @@ class TestFileProcessorProcess:
         )
         processor = FileProcessor(constraints=constraints)
         # Set mode to strict on the file
-        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+        file = ImageFile(
+            source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict"
+        )
 
         with pytest.raises(FileTooLargeError):
             processor.process(file)
@@ -144,7 +215,9 @@ class TestFileProcessorProcess:
         )
         processor = FileProcessor(constraints=constraints)
         # Set mode to warn on the file
-        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="warn")
+        file = ImageFile(
+            source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="warn"
+        )
 
         result = processor.process(file)
 
@@ -158,8 +231,12 @@ class TestFileProcessorProcessFiles:
         """Test processing multiple files."""
         processor = FileProcessor(constraints=ANTHROPIC_CONSTRAINTS)
         files = {
-            "image1": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png")),
+            "image1": ImageFile(
-            "image2": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test2.png")),
+                source=FileBytes(data=MINIMAL_PNG, filename="test1.png")
+            ),
+            "image2": ImageFile(
+                source=FileBytes(data=MINIMAL_PNG, filename="test2.png")
+            ),
         }
 
         result = processor.process_files(files)
@@ -198,7 +275,9 @@ class TestFileProcessorPerFileMode:
 
     def test_file_custom_mode(self):
         """Test setting custom mode on file."""
-        file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+        file = ImageFile(
+            source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict"
+        )
         assert file.mode == "strict"
 
     def test_processor_respects_file_mode(self):
@@ -210,11 +289,15 @@ class TestFileProcessorPerFileMode:
         processor = FileProcessor(constraints=constraints)
 
         # File with strict mode should raise
-        strict_file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="strict")
+        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")
+        warn_file = ImageFile(
+            source=FileBytes(data=MINIMAL_PNG, filename="test.png"), mode="warn"
+        )
         result = processor.process(warn_file)
-        assert result == warn_file
+        assert result == warn_file

lib/crewai-files/tests/processing/test_transformers.py

@@ -1,14 +1,12 @@
 """Unit tests for file transformers."""
 
 import io
-from unittest.mock import MagicMock, patch
+from unittest.mock import patch
 
-import pytest
+from crewai_files import ImageFile, PDFFile, TextFile
-
+from crewai_files.core.sources import FileBytes
-from crewai.files import ImageFile, PDFFile, TextFile
+from crewai_files.processing.exceptions import ProcessingDependencyError
-from crewai.files.file import FileBytes
+from crewai_files.processing.transformers import (
-from crewai.files.processing.exceptions import ProcessingDependencyError
-from crewai.files.processing.transformers import (
     chunk_pdf,
     chunk_text,
     get_image_dimensions,
@@ -16,6 +14,7 @@ from crewai.files.processing.transformers import (
     optimize_image,
     resize_image,
 )
+import pytest
 
 
 def create_test_png(width: int = 100, height: int = 100) -> bytes:
@@ -112,7 +111,7 @@ class TestResizeImage:
                 # Force reimport to trigger ImportError
                 import importlib
 
-                import crewai.files.processing.transformers as t
+                import crewai_files.processing.transformers as t
 
                 importlib.reload(t)
                 t.resize_image(img, 100, 100)
@@ -267,14 +266,18 @@ class TestChunkText:
         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))
+        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
+                assert (
+                    chunk_text_content.endswith("\n") or len(chunk_text_content) <= 25
+                )
 
     def test_chunk_with_overlap(self) -> None:
         """Test chunking with overlapping characters."""
@@ -321,7 +324,7 @@ class TestGetImageDimensions:
     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"))
+        ImageFile(source=FileBytes(data=png_bytes, filename="test.png"))
 
         with patch.dict("sys.modules", {"PIL": None}):
             # Can't easily test this without unloading module
@@ -356,4 +359,4 @@ class TestGetPdfPageCount:
 
         count = get_pdf_page_count(pdf)
 
-        assert count is None
+        assert count is None

lib/crewai-files/tests/processing/test_validators.py

@@ -2,10 +2,8 @@
 
 from unittest.mock import patch
 
-import pytest
+from crewai_files import AudioFile, FileBytes, ImageFile, PDFFile, TextFile, VideoFile
-
+from crewai_files.processing.constraints import (
-from crewai.files import AudioFile, FileBytes, ImageFile, PDFFile, TextFile, VideoFile
-from crewai.files.processing.constraints import (
     ANTHROPIC_CONSTRAINTS,
     AudioConstraints,
     ImageConstraints,
@@ -13,12 +11,12 @@ from crewai.files.processing.constraints import (
     ProviderConstraints,
     VideoConstraints,
 )
-from crewai.files.processing.exceptions import (
+from crewai_files.processing.exceptions import (
     FileTooLargeError,
     FileValidationError,
     UnsupportedFileTypeError,
 )
-from crewai.files.processing.validators import (
+from crewai_files.processing.validators import (
     _get_audio_duration,
     _get_video_duration,
     validate_audio,
@@ -28,18 +26,89 @@ from crewai.files.processing.validators import (
     validate_text,
     validate_video,
 )
+import pytest
 
 
 # Minimal valid PNG: 8x8 pixel RGB image (valid for PIL)
-MINIMAL_PNG = bytes([
+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,
+        0x89,
-    0x08, 0x02, 0x00, 0x00, 0x00, 0x4b, 0x6d, 0x29, 0xdc, 0x00, 0x00, 0x00,
+        0x50,
-    0x12, 0x49, 0x44, 0x41, 0x54, 0x78, 0x9c, 0x63, 0xfc, 0xcf, 0x80, 0x1d,
+        0x4E,
-    0x30, 0xe1, 0x10, 0x1f, 0xa4, 0x12, 0x00, 0xcd, 0x41, 0x01, 0x0f, 0xe8,
+        0x47,
-    0x41, 0xe2, 0x6f, 0x00, 0x00, 0x00, 0x00, 0x49, 0x45, 0x4e, 0x44, 0xae,
+        0x0D,
-    0x42, 0x60, 0x82,
+        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 = (
@@ -268,7 +337,7 @@ class TestValidateAudio:
 
         assert "not supported" in str(exc_info.value)
 
-    @patch("crewai.files.processing.validators._get_audio_duration")
+    @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
@@ -284,7 +353,7 @@ class TestValidateAudio:
         assert len(errors) == 0
         mock_get_duration.assert_called_once()
 
-    @patch("crewai.files.processing.validators._get_audio_duration")
+    @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
@@ -302,7 +371,7 @@ class TestValidateAudio:
         assert "120.5s" in str(exc_info.value)
         assert "60s" in str(exc_info.value)
 
-    @patch("crewai.files.processing.validators._get_audio_duration")
+    @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
@@ -318,7 +387,7 @@ class TestValidateAudio:
         assert len(errors) == 1
         assert "duration" in errors[0].lower()
 
-    @patch("crewai.files.processing.validators._get_audio_duration")
+    @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(
@@ -333,7 +402,7 @@ class TestValidateAudio:
         assert len(errors) == 0
         mock_get_duration.assert_not_called()
 
-    @patch("crewai.files.processing.validators._get_audio_duration")
+    @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
@@ -391,7 +460,7 @@ class TestValidateVideo:
 
         assert "not supported" in str(exc_info.value)
 
-    @patch("crewai.files.processing.validators._get_video_duration")
+    @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
@@ -407,7 +476,7 @@ class TestValidateVideo:
         assert len(errors) == 0
         mock_get_duration.assert_called_once()
 
-    @patch("crewai.files.processing.validators._get_video_duration")
+    @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
@@ -425,7 +494,7 @@ class TestValidateVideo:
         assert "180.0s" in str(exc_info.value)
         assert "60s" in str(exc_info.value)
 
-    @patch("crewai.files.processing.validators._get_video_duration")
+    @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
@@ -441,7 +510,7 @@ class TestValidateVideo:
         assert len(errors) == 1
         assert "duration" in errors[0].lower()
 
-    @patch("crewai.files.processing.validators._get_video_duration")
+    @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(
@@ -456,7 +525,7 @@ class TestValidateVideo:
         assert len(errors) == 0
         mock_get_duration.assert_not_called()
 
-    @patch("crewai.files.processing.validators._get_video_duration")
+    @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

lib/crewai-files/tests/test_file_url.py

@@ -2,13 +2,12 @@
 
 from unittest.mock import AsyncMock, MagicMock, patch
 
+from crewai_files import FileBytes, FileUrl, ImageFile
+from crewai_files.core.resolved import InlineBase64, UrlReference
+from crewai_files.core.sources import FilePath, _normalize_source
+from crewai_files.resolution.resolver import FileResolver
 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."""

lib/crewai-files/tests/test_resolved.py

@@ -2,15 +2,14 @@
 
 from datetime import datetime, timezone
 
-import pytest
+from crewai_files.core.resolved import (
-
-from crewai.files.resolved import (
     FileReference,
     InlineBase64,
     InlineBytes,
     ResolvedFile,
     UrlReference,
 )
+import pytest
 
 
 class TestInlineBase64:

lib/crewai-files/tests/test_resolver.py

@@ -1,15 +1,13 @@
 """Tests for FileResolver."""
 
-import pytest
+from crewai_files import FileBytes, ImageFile
-
+from crewai_files.cache.upload_cache import UploadCache
-from crewai.files import FileBytes, ImageFile
+from crewai_files.core.resolved import InlineBase64, InlineBytes
-from crewai.files.resolved import InlineBase64, InlineBytes
+from crewai_files.resolution.resolver import (
-from crewai.files.resolver import (
     FileResolver,
     FileResolverConfig,
     create_resolver,
 )
-from crewai.files.upload_cache import UploadCache
 
 
 # Minimal valid PNG
@@ -74,8 +72,12 @@ class TestFileResolver:
         """Test resolving multiple files."""
         resolver = FileResolver()
         files = {
-            "image1": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test1.png")),
+            "image1": ImageFile(
-            "image2": ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test2.png")),
+                source=FileBytes(data=MINIMAL_PNG, filename="test1.png")
+            ),
+            "image2": ImageFile(
+                source=FileBytes(data=MINIMAL_PNG, filename="test2.png")
+            ),
         }
 
         resolved = resolver.resolve_files(files, "openai")

lib/crewai-files/tests/test_upload_cache.py

@@ -2,10 +2,8 @@
 
 from datetime import datetime, timedelta, timezone
 
-import pytest
+from crewai_files import FileBytes, ImageFile
-
+from crewai_files.cache.upload_cache import CachedUpload, UploadCache
-from crewai.files import FileBytes, ImageFile
-from crewai.files.upload_cache import CachedUpload, UploadCache
 
 
 # Minimal valid PNG
@@ -92,7 +90,7 @@ class TestUploadCache:
         cache = UploadCache()
         file = ImageFile(source=FileBytes(data=MINIMAL_PNG, filename="test.png"))
 
-        cached = cache.set(
+        cache.set(
             file=file,
             provider="gemini",
             file_id="file-123",
@@ -160,7 +158,9 @@ class TestUploadCache:
         """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"))
+        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)
@@ -192,8 +192,12 @@ class TestUploadCache:
         """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"))
+        file2 = ImageFile(
-        file3 = ImageFile(source=FileBytes(data=MINIMAL_PNG + b"xx", filename="test3.png"))
+            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")

lib/crewai/pyproject.toml

@@ -99,13 +99,7 @@ a2a = [
      "aiocache[redis,memcached]~=0.12.3",
 ]
 file-processing = [
-    "Pillow~=10.4.0",
+    "crewai-files",
-    "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",
 ]
 
 
@@ -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]

lib/crewai/src/crewai/__init__.py

@@ -3,10 +3,7 @@ from typing import Any
 import urllib.request
 import warnings
 
-from crewai.agent.core import Agent
+from crewai_files import (
-from crewai.crew import Crew
-from crewai.crews.crew_output import CrewOutput
-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

lib/crewai/src/crewai/agents/crew_agent_executor.py

@@ -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(

lib/crewai/src/crewai/crews/utils.py

@@ -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_files import (
-from crewai.crews.crew_output import CrewOutput
-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

lib/crewai/src/crewai/llm.py

@@ -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,

lib/crewai/src/crewai/llms/base_llm.py

@@ -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

lib/crewai/src/crewai/llms/providers/anthropic/completion.py

@@ -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,

lib/crewai/src/crewai/llms/providers/azure/completion.py

@@ -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,

lib/crewai/src/crewai/llms/providers/bedrock/completion.py

@@ -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,

lib/crewai/src/crewai/llms/providers/gemini/completion.py

@@ -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,

lib/crewai/src/crewai/llms/providers/openai/completion.py

@@ -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,

lib/crewai/src/crewai/task.py

@@ -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

lib/crewai/src/crewai/tools/agent_tools/read_file_tool.py

@@ -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):

lib/crewai/src/crewai/utilities/file_store.py

@@ -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())
 

lib/crewai/src/crewai/utilities/files/__init__.py

@@ -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]

lib/crewai/src/crewai/utilities/files/__init__.pyi

@@ -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]

lib/crewai/src/crewai/utilities/types.py

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

lib/crewai/tests/files/__init__.py

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

lib/crewai/tests/files/processing/__init__.py

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

pyproject.toml

@@ -105,6 +105,7 @@ ignore-decorators = ["typing.overload"]
 [tool.ruff.lint.per-file-ignores]
 "lib/crewai/tests/**/*.py" = ["S101", "RET504", "S105", "S106"]  # Allow assert statements, unnecessary assignments, and hardcoded passwords in tests
 "lib/crewai-tools/tests/**/*.py" = ["S101", "RET504", "S105", "S106", "RUF012", "N818", "E402", "RUF043", "S110", "B017"]  # Allow various test-specific patterns
+"lib/crewai-files/tests/**/*.py" = ["S101", "RET504", "S105", "S106", "B017", "F841"]  # Allow assert statements and blind exception assertions in tests
 
 
 [tool.mypy]
@@ -117,7 +118,7 @@ warn_return_any = true
 show_error_codes = true
 warn_unused_ignores = true
 python_version = "3.12"
-exclude = "(?x)(^lib/crewai/src/crewai/cli/templates/ | ^lib/crewai/tests/ | ^lib/crewai-tools/tests/)"
+exclude = "(?x)(^lib/crewai/src/crewai/cli/templates/|^lib/crewai/tests/|^lib/crewai-tools/tests/|^lib/crewai-files/tests/)"
 plugins = ["pydantic.mypy"]
 
 
@@ -132,6 +133,7 @@ markers = [
 testpaths = [
     "lib/crewai/tests",
     "lib/crewai-tools/tests",
+    "lib/crewai-files/tests",
 ]
 asyncio_mode = "strict"
 asyncio_default_fixture_loop_scope = "function"
@@ -146,6 +148,7 @@ members = [
     "lib/crewai",
     "lib/crewai-tools",
     "lib/devtools",
+    "lib/crewai-files",
 ]
 
 
@@ -153,3 +156,4 @@ members = [
 crewai = { workspace = true }
 crewai-tools = { workspace = true }
 crewai-devtools = { workspace = true }
+crewai-files = { workspace = true }

uv.lock

@@ -32,6 +32,7 @@ resolution-markers = [
 members = [
     "crewai",
     "crewai-devtools",
+    "crewai-files",
     "crewai-tools",
 ]
 
@@ -1239,13 +1240,7 @@ embeddings = [
     { name = "tiktoken" },
 ]
 file-processing = [
-    { name = "aiocache" },
+    { name = "crewai-files" },
-    { name = "aiofiles" },
-    { name = "av" },
-    { name = "pillow" },
-    { name = "pypdf" },
-    { name = "python-magic" },
-    { name = "tinytag" },
 ]
 google-genai = [
     { name = "google-genai" },
@@ -1279,18 +1274,16 @@ watson = [
 requires-dist = [
     { name = "a2a-sdk", marker = "extra == 'a2a'", specifier = "~=0.3.10" },
     { name = "aiobotocore", marker = "extra == 'aws'", specifier = "~=2.25.2" },
-    { name = "aiocache", marker = "extra == 'file-processing'", specifier = "~=0.12.3" },
     { name = "aiocache", extras = ["memcached", "redis"], marker = "extra == 'a2a'", specifier = "~=0.12.3" },
-    { name = "aiofiles", marker = "extra == 'file-processing'", specifier = "~=24.1.0" },
     { name = "aiosqlite", specifier = "~=0.21.0" },
     { name = "anthropic", marker = "extra == 'anthropic'", specifier = "~=0.71.0" },
     { name = "appdirs", specifier = "~=1.4.4" },
-    { name = "av", marker = "extra == 'file-processing'", specifier = "~=13.0.0" },
     { name = "azure-ai-inference", marker = "extra == 'azure-ai-inference'", specifier = "~=1.0.0b9" },
     { name = "boto3", marker = "extra == 'aws'", specifier = "~=1.40.38" },
     { name = "boto3", marker = "extra == 'bedrock'", specifier = "~=1.40.45" },
     { name = "chromadb", specifier = "~=1.1.0" },
     { name = "click", specifier = "~=8.1.7" },
+    { name = "crewai-files", marker = "extra == 'file-processing'", editable = "lib/crewai-files" },
     { name = "crewai-tools", marker = "extra == 'tools'", editable = "lib/crewai-tools" },
     { name = "docling", marker = "extra == 'docling'", specifier = "~=2.63.0" },
     { name = "google-genai", marker = "extra == 'google-genai'", specifier = "~=1.49.0" },
@@ -1312,18 +1305,14 @@ requires-dist = [
     { name = "opentelemetry-sdk", specifier = "~=1.34.0" },
     { name = "pandas", marker = "extra == 'pandas'", specifier = "~=2.2.3" },
     { name = "pdfplumber", specifier = "~=0.11.4" },
-    { name = "pillow", marker = "extra == 'file-processing'", specifier = "~=10.4.0" },
     { name = "portalocker", specifier = "~=2.7.0" },
     { name = "pydantic", specifier = "~=2.11.9" },
     { name = "pydantic-settings", specifier = "~=2.10.1" },
     { name = "pyjwt", specifier = "~=2.9.0" },
-    { name = "pypdf", marker = "extra == 'file-processing'", specifier = "~=4.0.0" },
     { name = "python-dotenv", specifier = "~=1.1.1" },
-    { name = "python-magic", marker = "extra == 'file-processing'", specifier = ">=0.4.27" },
     { name = "qdrant-client", extras = ["fastembed"], marker = "extra == 'qdrant'", specifier = "~=1.14.3" },
     { name = "regex", specifier = "~=2024.9.11" },
     { name = "tiktoken", marker = "extra == 'embeddings'", specifier = "~=0.8.0" },
-    { name = "tinytag", marker = "extra == 'file-processing'", specifier = "~=1.10.0" },
     { name = "tokenizers", specifier = "~=0.20.3" },
     { name = "tomli", specifier = "~=2.0.2" },
     { name = "tomli-w", specifier = "~=1.1.0" },
@@ -1354,6 +1343,31 @@ requires-dist = [
     { name = "toml", specifier = "~=0.10.2" },
 ]
 
+[[package]]
+name = "crewai-files"
+version = "0.1.0"
+source = { editable = "lib/crewai-files" }
+dependencies = [
+    { name = "aiocache" },
+    { name = "aiofiles" },
+    { name = "av" },
+    { name = "pillow" },
+    { name = "pypdf" },
+    { name = "python-magic" },
+    { name = "tinytag" },
+]
+
+[package.metadata]
+requires-dist = [
+    { name = "aiocache", specifier = "~=0.12.3" },
+    { name = "aiofiles", specifier = "~=24.1.0" },
+    { name = "av", specifier = "~=13.0.0" },
+    { name = "pillow", specifier = "~=10.4.0" },
+    { name = "pypdf", specifier = "~=4.0.0" },
+    { name = "python-magic", specifier = ">=0.4.27" },
+    { name = "tinytag", specifier = "~=1.10.0" },
+]
+
 [[package]]
 name = "crewai-tools"
 source = { editable = "lib/crewai-tools" }