andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-07-08 00:15:12 +00:00
Code Issues Actions 6 Packages Projects Releases Wiki Activity

Merge branch 'main' into devin/1773669058-fix-trained-agents-data-file

Browse Source
This commit is contained in:
Lorenze Jay
2026-04-09 13:19:44 -07:00
committed by GitHub
parent 79013a6dc2 84b1b0a0b0
commit d79c4a62a1
790 changed files with 106013 additions and 9056 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
lib/crewai-files/pyproject.toml
View File

@@ -9,14 +9,17 @@ authors = [
requires-python = ">=3.10, <3.14"
dependencies = [
"Pillow~=12.1.1",
"pypdf~=6.7.5",
"pypdf~=6.9.1",
"python-magic>=0.4.27",
"aiocache~=0.12.3",
"aiofiles~=24.1.0",
"tinytag~=1.10.0",
"tinytag~=2.2.1",
"av~=13.0.0",
]
[tool.uv]
exclude-newer = "3 days"
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

2
lib/crewai-files/src/crewai_files/__init__.py
View File

@@ -152,4 +152,4 @@ __all__ = [
"wrap_file_source",
]
__version__ = "1.11.0rc1"
__version__ = "1.14.2a1"

4
lib/crewai-files/src/crewai_files/formatting/api.py
View File

@@ -122,7 +122,7 @@ def format_multimodal_content(
return content_blocks
# Use API-specific constraints for OpenAI
constraints_key = provider_type
constraints_key: str = provider_type
if api == "responses" and "openai" in provider_type.lower():
constraints_key = "openai_responses"
@@ -187,7 +187,7 @@ async def aformat_multimodal_content(
return content_blocks
# Use API-specific constraints for OpenAI
constraints_key = provider_type
constraints_key: str = provider_type
if api == "responses" and "openai" in provider_type.lower():
constraints_key = "openai_responses"

1
lib/crewai-files/src/crewai_files/processing/constraints.py
View File

@@ -15,6 +15,7 @@ from crewai_files.core.types import (
ProviderName = Literal[
"anthropic",
"openai",
"openai_responses",
"gemini",
"bedrock",
"azure",

2
lib/crewai-files/src/crewai_files/processing/transformers.py
View File

@@ -120,7 +120,7 @@ def optimize_image(
with Image.open(io.BytesIO(content)) as img:
if img.mode in ("RGBA", "LA", "P"):
img = img.convert("RGB")
img = img.convert("RGB") # type: ignore[assignment]
output_format = "JPEG"
else:
output_format = img.format or "JPEG"

2
lib/crewai-files/src/crewai_files/processing/validators.py
View File

@@ -85,7 +85,7 @@ def _get_audio_duration(content: bytes, filename: str | None = None) -> float |
Duration in seconds or None if tinytag unavailable.
"""
try:
from tinytag import TinyTag # type: ignore[import-untyped]
from tinytag import TinyTag
except ImportError:
logger.warning(
"tinytag not installed - cannot validate audio duration. "

335
lib/crewai-tools/BUILDING_TOOLS.md
View File

@@ -1,335 +0,0 @@
## Building CrewAI Tools
This guide shows you how to build high‑quality CrewAI tools that match the patterns in this repository and are ready to be merged. It focuses on: architecture, conventions, environment variables, dependencies, testing, documentation, and a complete example.
### Who this is for
- Contributors creating new tools under `crewai_tools/tools/*`
- Maintainers reviewing PRs for consistency and DX
---
## Quick‑start checklist
1. Create a new folder under `crewai_tools/tools/<your_tool_name>/` with a `README.md` and a `<your_tool_name>.py`.
2. Implement a class that ends with `Tool` and subclasses `BaseTool` (or `RagTool` when appropriate).
3. Define a Pydantic `args_schema` with explicit field descriptions and validation.
4. Declare `env_vars` and `package_dependencies` in the class when needed.
5. Lazily initialize clients in `__init__` or `_run` and handle missing credentials with clear errors.
6. Implement `_run(...) -> str | dict` and, if needed, `_arun(...)`.
7. Add tests under `tests/tools/` (unit, no real network calls; mock or record safely).
8. Add a concise tool `README.md` with usage and required env vars.
9. If you add optional dependencies, register them in `pyproject.toml` under `[project.optional-dependencies]` and reference that extra in your tool docs.
10. Run `uv run pytest` and `pre-commit run -a` locally; ensure green.
---
## Tool anatomy and conventions
### BaseTool pattern
All tools follow this structure:
```python
from typing import Any, List, Optional, Type
import os
from pydantic import BaseModel, Field
from crewai.tools import BaseTool, EnvVar
class MyToolInput(BaseModel):
"""Input schema for MyTool."""
query: str = Field(..., description="Your input description here")
limit: int = Field(5, ge=1, le=50, description="Max items to return")
class MyTool(BaseTool):
name: str = "My Tool"
description: str = "Explain succinctly what this tool does and when to use it."
args_schema: Type[BaseModel] = MyToolInput
# Only include when applicable
env_vars: List[EnvVar] = [
EnvVar(name="MY_API_KEY", description="API key for My service", required=True),
]
package_dependencies: List[str] = ["my-sdk"]
def __init__(self, **kwargs: Any) -> None:
super().__init__(**kwargs)
# Lazy import to keep base install light
try:
import my_sdk # noqa: F401
except Exception as exc:
raise ImportError(
"Missing optional dependency 'my-sdk'. Install with: \n"
" uv add crewai-tools --extra my-sdk\n"
"or\n"
" pip install my-sdk\n"
) from exc
if "MY_API_KEY" not in os.environ:
raise ValueError("Environment variable MY_API_KEY is required for MyTool")
def _run(self, query: str, limit: int = 5, **_: Any) -> str:
"""Synchronous execution. Return a concise string or JSON string."""
# Implement your logic here; do not print. Return the content.
# Handle errors gracefully, return clear messages.
return f"Processed {query} with limit={limit}"
async def _arun(self, *args: Any, **kwargs: Any) -> str:
"""Optional async counterpart if your client supports it."""
# Prefer delegating to _run when the client is thread-safe
return self._run(*args, **kwargs)
```
Key points:
- Class name must end with `Tool` to be auto‑discovered by our tooling.
- Use `args_schema` for inputs; always include `description` and validation.
- Validate env vars early and fail with actionable errors.
- Keep outputs deterministic and compact; favor `str` (possibly JSON‑encoded) or small dicts converted to strings.
- Avoid printing; return the final string.
### Error handling
- Wrap network and I/O with try/except and return a helpful message. See `BraveSearchTool` and others for patterns.
- Validate required inputs and environment configuration with clear messages.
- Keep exceptions user‑friendly; do not leak stack traces.
### Rate limiting and retries
- If the upstream API enforces request pacing, implement minimal rate limiting (see `BraveSearchTool`).
- Consider idempotency and backoff for transient errors where appropriate.
### Async support
- Implement `_arun` only if your library has a true async client or your sync calls are thread‑safe.
- Otherwise, delegate `_arun` to `_run` as in multiple existing tools.
### Returning values
- Return a string (or JSON string) that’s ready to display in an agent transcript.
- If returning structured data, keep it small and human‑readable. Use stable keys and ordering.
---
## RAG tools and adapters
If your tool is a knowledge source, consider extending `RagTool` and/or creating an adapter.
- `RagTool` exposes `add(...)` and a `query(question: str) -> str` contract through an `Adapter`.
- See `crewai_tools/tools/rag/rag_tool.py` and adapters like `embedchain_adapter.py` and `lancedb_adapter.py`.
Minimal adapter example:
```python
from typing import Any
from pydantic import BaseModel
from crewai_tools.tools.rag.rag_tool import Adapter, RagTool
class MemoryAdapter(Adapter):
store: list[str] = []
def add(self, text: str, **_: Any) -> None:
self.store.append(text)
def query(self, question: str) -> str:
# naive demo: return all text containing any word from the question
tokens = set(question.lower().split())
hits = [t for t in self.store if tokens & set(t.lower().split())]
return "\n".join(hits) if hits else "No relevant content found."
class MemoryRagTool(RagTool):
name: str = "In‑memory RAG"
description: str = "Toy RAG that stores text in memory and returns matches."
adapter: Adapter = MemoryAdapter()
```
When using external vector DBs (MongoDB, Qdrant, Weaviate), study the existing tools to follow indexing, embedding, and query configuration patterns closely.
---
## Toolkits (multiple related tools)
Some integrations expose a toolkit (a group of tools) rather than a single class. See Bedrock `browser_toolkit.py` and `code_interpreter_toolkit.py`.
Guidelines:
- Provide small, focused `BaseTool` classes for each operation (e.g., `navigate`, `click`, `extract_text`).
- Offer a helper `create_<name>_toolkit(...) -> Tuple[ToolkitClass, List[BaseTool]]` to create tools and manage resources.
- If you open external resources (browsers, interpreters), support cleanup methods and optionally context manager usage.
---
## Environment variables and dependencies
### env_vars
- Declare as `env_vars: List[EnvVar]` with `name`, `description`, `required`, and optional `default`.
- Validate presence in `__init__` or on first `_run` call.
### Dependencies
- List runtime packages in `package_dependencies` on the class.
- If they are genuinely optional, add an extra under `[project.optional-dependencies]` in `pyproject.toml` (e.g., `tavily-python`, `serpapi`, `scrapfly-sdk`).
- Use lazy imports to avoid hard deps for users who don’t need the tool.
---
## Testing
Place tests under `tests/tools/` and follow these rules:
- Do not hit real external services in CI. Use mocks, fakes, or recorded fixtures where allowed.
- Validate input validation, env var handling, error messages, and happy path output formatting.
- Keep tests fast and deterministic.
Example skeleton (`tests/tools/my_tool_test.py`):
```python
import os
import pytest
from crewai_tools.tools.my_tool.my_tool import MyTool
def test_requires_env_var(monkeypatch):
monkeypatch.delenv("MY_API_KEY", raising=False)
with pytest.raises(ValueError):
MyTool()
def test_happy_path(monkeypatch):
monkeypatch.setenv("MY_API_KEY", "test")
tool = MyTool()
result = tool.run(query="hello", limit=2)
assert "hello" in result
```
Run locally:
```bash
uv run pytest
pre-commit run -a
```
---
## Documentation
Each tool must include a `README.md` in its folder with:
- What it does and when to use it
- Required env vars and optional extras (with install snippet)
- Minimal usage example
Update the root `README.md` only if the tool introduces a new category or notable capability.
---
## Discovery and specs
Our internal tooling discovers classes whose names end with `Tool`. Keep your class exported from the module path under `crewai_tools/tools/...` to be picked up by scripts like `crewai_tools.generate_tool_specs.py`.
---
## Full example: “Weather Search Tool”
This example demonstrates: `args_schema`, `env_vars`, `package_dependencies`, lazy imports, validation, and robust error handling.
```python
# file: crewai_tools/tools/weather_tool/weather_tool.py
from typing import Any, List, Optional, Type
import os
import requests
from pydantic import BaseModel, Field
from crewai.tools import BaseTool, EnvVar
class WeatherToolInput(BaseModel):
"""Input schema for WeatherTool."""
city: str = Field(..., description="City name, e.g., 'Berlin'")
country: Optional[str] = Field(None, description="ISO country code, e.g., 'DE'")
units: str = Field(
default="metric",
description="Units system: 'metric' or 'imperial'",
pattern=r"^(metric|imperial)$",
)
class WeatherTool(BaseTool):
name: str = "Weather Search"
description: str = (
"Look up current weather for a city using a public weather API."
)
args_schema: Type[BaseModel] = WeatherToolInput
env_vars: List[EnvVar] = [
EnvVar(
name="WEATHER_API_KEY",
description="API key for the weather service",
required=True,
),
]
package_dependencies: List[str] = ["requests"]
base_url: str = "https://api.openweathermap.org/data/2.5/weather"
def __init__(self, **kwargs: Any) -> None:
super().__init__(**kwargs)
if "WEATHER_API_KEY" not in os.environ:
raise ValueError("WEATHER_API_KEY is required for WeatherTool")
def _run(self, city: str, country: Optional[str] = None, units: str = "metric") -> str:
try:
q = f"{city},{country}" if country else city
params = {
"q": q,
"units": units,
"appid": os.environ["WEATHER_API_KEY"],
}
resp = requests.get(self.base_url, params=params, timeout=10)
resp.raise_for_status()
data = resp.json()
main = data.get("weather", [{}])[0].get("main", "Unknown")
desc = data.get("weather", [{}])[0].get("description", "")
temp = data.get("main", {}).get("temp")
feels = data.get("main", {}).get("feels_like")
city_name = data.get("name", city)
return (
f"Weather in {city_name}: {main} ({desc}). "
f"Temperature: {temp}°, feels like {feels}°."
)
except requests.Timeout:
return "Weather service timed out. Please try again later."
except requests.HTTPError as e:
return f"Weather service error: {e.response.status_code} {e.response.text[:120]}"
except Exception as e:
return f"Unexpected error fetching weather: {e}"
```
Folder layout:
```
crewai_tools/tools/weather_tool/
├─ weather_tool.py
└─ README.md
```
And `README.md` should document env vars and usage.
---
## PR checklist
- [ ] Tool lives under `crewai_tools/tools/<name>/`
- [ ] Class ends with `Tool` and subclasses `BaseTool` (or `RagTool`)
- [ ] Precise `args_schema` with descriptions and validation
- [ ] `env_vars` declared (if any) and validated
- [ ] `package_dependencies` and optional extras added in `pyproject.toml` (if any)
- [ ] Clear error handling; no prints
- [ ] Unit tests added (`tests/tools/`), fast and deterministic
- [ ] Tool `README.md` with usage and env vars
- [ ] `pre-commit` and `pytest` pass locally
---
## Tips for great DX
- Keep responses short and useful—agents quote your tool output directly.
- Validate early; fail fast with actionable guidance.
- Prefer lazy imports; minimize default install surface.
- Mirror patterns from similar tools in this repo for a consistent developer experience.
Happy building!

6
lib/crewai-tools/pyproject.toml
View File

@@ -10,8 +10,7 @@ requires-python = ">=3.10, <3.14"
dependencies = [
"pytube~=15.0.0",
"requests~=2.32.5",
"docker~=7.1.0",
"crewai==1.11.0rc1",
"crewai==1.14.2a1",
"tiktoken~=0.8.0",
"beautifulsoup4~=4.13.4",
"python-docx~=1.2.0",
@@ -142,6 +141,9 @@ contextual = [
]
[tool.uv]
exclude-newer = "3 days"
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"

6
lib/crewai-tools/src/crewai_tools/__init__.py
View File

@@ -35,9 +35,6 @@ from crewai_tools.tools.browserbase_load_tool.browserbase_load_tool import (
from crewai_tools.tools.code_docs_search_tool.code_docs_search_tool import (
CodeDocsSearchTool,
)
from crewai_tools.tools.code_interpreter_tool.code_interpreter_tool import (
CodeInterpreterTool,
)
from crewai_tools.tools.composio_tool.composio_tool import ComposioTool
from crewai_tools.tools.contextualai_create_agent_tool.contextual_create_agent_tool import (
ContextualAICreateAgentTool,
@@ -225,7 +222,6 @@ __all__ = [
"BrowserbaseLoadTool",
"CSVSearchTool",
"CodeDocsSearchTool",
"CodeInterpreterTool",
"ComposioTool",
"ContextualAICreateAgentTool",
"ContextualAIParseTool",
@@ -309,4 +305,4 @@ __all__ = [
"ZapierActionTools",
]
__version__ = "1.11.0rc1"
__version__ = "1.14.2a1"

37
lib/crewai-tools/src/crewai_tools/adapters/enterprise_adapter.py
View File

@@ -136,7 +136,7 @@ class EnterpriseActionTool(BaseTool):
enum_values = schema["enum"]
if not enum_values:
return self._map_json_type_to_python(json_type)
return Literal[tuple(enum_values)] # type: ignore[return-value]
return Literal[tuple(enum_values)]
if json_type == "array":
items_schema = schema.get("items", {"type": "string"})
@@ -155,7 +155,7 @@ class EnterpriseActionTool(BaseTool):
full_model_name = f"{self._base_name}{model_name}"
if full_model_name in self._model_registry:
return self._model_registry[full_model_name]
return cast(type[Any], self._model_registry[full_model_name])
properties = schema.get("properties", {})
required_fields = schema.get("required", [])
@@ -178,19 +178,19 @@ class EnterpriseActionTool(BaseTool):
field_definitions[prop_name] = self._create_field_definition(
prop_type,
is_required,
prop_desc, # type: ignore[arg-type]
prop_desc,
)
try:
nested_model = create_model(full_model_name, **field_definitions) # type: ignore[call-overload]
self._model_registry[full_model_name] = nested_model
return nested_model
return cast(type[Any], nested_model)
except Exception:
return dict
def _create_field_definition(
self, field_type: type[Any] | _SpecialForm, is_required: bool, description: str
) -> tuple:
) -> tuple[type[Any] | _SpecialForm, Any]:
"""Create Pydantic field definition based on type and requirement."""
if is_required:
return (field_type, Field(description=description))
@@ -232,7 +232,7 @@ class EnterpriseActionTool(BaseTool):
return any(t.get("type") == "null" for t in schema["anyOf"])
return schema.get("type") == "null"
def _run(self, **kwargs) -> str:
def _run(self, **kwargs: Any) -> str:
"""Execute the specific enterprise action with validated parameters."""
try:
cleaned_kwargs = {}
@@ -280,8 +280,8 @@ class EnterpriseActionKitToolAdapter:
):
"""Initialize the adapter with an enterprise action token."""
self._set_enterprise_action_token(enterprise_action_token)
self._actions_schema = {} # type: ignore[var-annotated]
self._tools = None
self._actions_schema: dict[str, Any] = {}
self._tools: list[BaseTool] | None = None
self.enterprise_api_base_url = (
enterprise_api_base_url or get_enterprise_api_base_url()
)
@@ -293,7 +293,7 @@ class EnterpriseActionKitToolAdapter:
self._create_tools()
return self._tools or []
def _fetch_actions(self):
def _fetch_actions(self) -> None:
"""Fetch available actions from the API."""
try:
actions_url = f"{self.enterprise_api_base_url}/actions"
@@ -379,9 +379,9 @@ class EnterpriseActionKitToolAdapter:
return descriptions
def _create_tools(self):
def _create_tools(self) -> None:
"""Create BaseTool instances for each action."""
tools = []
tools: list[BaseTool] = []
for action_name, action_schema in self._actions_schema.items():
function_details = action_schema.get("function", {})
@@ -403,7 +403,7 @@ class EnterpriseActionKitToolAdapter:
description=full_description,
action_name=action_name,
action_schema=action_schema,
enterprise_action_token=self.enterprise_action_token,
enterprise_action_token=self.enterprise_action_token or "",
enterprise_api_base_url=self.enterprise_api_base_url,
)
@@ -411,7 +411,7 @@ class EnterpriseActionKitToolAdapter:
self._tools = tools
def _set_enterprise_action_token(self, enterprise_action_token: str | None):
def _set_enterprise_action_token(self, enterprise_action_token: str | None) -> None:
if enterprise_action_token and not enterprise_action_token.startswith("PK_"):
warnings.warn(
"Legacy token detected, please consider using the new Enterprise Action Auth token. Check out our docs for more information https://docs.crewai.com/en/enterprise/features/integrations.",
@@ -423,10 +423,15 @@ class EnterpriseActionKitToolAdapter:
"CREWAI_ENTERPRISE_TOOLS_TOKEN"
)
self.enterprise_action_token = token
self.enterprise_action_token: str | None = token
def __enter__(self):
def __enter__(self) -> list[BaseTool]:
return self.tools()
def __exit__(self, exc_type, exc_val, exc_tb):
def __exit__(
self,
exc_type: type[BaseException] | None,
exc_val: BaseException | None,
exc_tb: Any,
) -> None:
pass

15
lib/crewai-tools/src/crewai_tools/adapters/lancedb_adapter.py
View File

@@ -5,20 +5,19 @@ from typing import Any
from crewai.utilities.lock_store import lock as store_lock
from lancedb import ( # type: ignore[import-untyped]
DBConnection as LanceDBConnection,
connect as lancedb_connect,
)
from lancedb.table import Table as LanceDBTable # type: ignore[import-untyped]
from openai import Client as OpenAIClient
from pydantic import Field, PrivateAttr
from crewai_tools.tools.rag.rag_tool import Adapter
def _default_embedding_function():
def _default_embedding_function() -> Callable[[list[str]], list[list[float]]]:
"""Create a default embedding function using OpenAI."""
client = OpenAIClient()
def _embedding_function(input):
def _embedding_function(input: list[str]) -> list[list[float]]:
rs = client.embeddings.create(input=input, model="text-embedding-ada-002")
return [record.embedding for record in rs.data]
@@ -28,13 +27,15 @@ def _default_embedding_function():
class LanceDBAdapter(Adapter):
uri: str | Path
table_name: str
embedding_function: Callable = Field(default_factory=_default_embedding_function)
embedding_function: Callable[[list[str]], list[list[float]]] = Field(
default_factory=_default_embedding_function
)
top_k: int = 3
vector_column_name: str = "vector"
text_column_name: str = "text"
_db: LanceDBConnection = PrivateAttr()
_table: LanceDBTable = PrivateAttr()
_db: Any = PrivateAttr()
_table: Any = PrivateAttr()
_lock_name: str = PrivateAttr(default="")
def model_post_init(self, __context: Any) -> None:

2
lib/crewai-tools/src/crewai_tools/adapters/rag_adapter.py
View File

@@ -12,7 +12,7 @@ class RAGAdapter(Adapter):
embedding_model: str = "text-embedding-3-small",
top_k: int = 5,
embedding_api_key: str | None = None,
**embedding_kwargs,
**embedding_kwargs: Any,
):
super().__init__()

7
lib/crewai-tools/src/crewai_tools/adapters/tool_collection.py
View File

@@ -9,7 +9,7 @@ from crewai.tools import BaseTool
T = TypeVar("T", bound=BaseTool)
class ToolCollection(list, Generic[T]):
class ToolCollection(list[T], Generic[T]):
"""A collection of tools that can be accessed by index or name.
This class extends the built-in list to provide dictionary-like
@@ -34,7 +34,8 @@ class ToolCollection(list, Generic[T]):
def __getitem__(self, key: int | str) -> T: # type: ignore[override]
if isinstance(key, str):
return self._name_cache[key.lower()]
return super().__getitem__(key)
result: T = super().__getitem__(key)
return result
def append(self, tool: T) -> None:
super().append(tool)
@@ -54,7 +55,7 @@ class ToolCollection(list, Generic[T]):
del self._name_cache[tool.name.lower()]
def pop(self, index: int = -1) -> T: # type: ignore[override]
tool = super().pop(index)
tool: T = super().pop(index)
if tool.name.lower() in self._name_cache:
del self._name_cache[tool.name.lower()]
return tool

8
lib/crewai-tools/src/crewai_tools/adapters/zapier_adapter.py
View File

@@ -1,6 +1,6 @@
import logging
import os
from typing import Final, Literal
from typing import Any, Final, Literal
from crewai.tools import BaseTool
from pydantic import Field, create_model
@@ -22,7 +22,7 @@ class ZapierActionTool(BaseTool):
action_id: str = Field(description="Zapier action ID")
api_key: str = Field(description="Zapier API key")
def _run(self, **kwargs) -> str:
def _run(self, **kwargs: Any) -> Any:
"""Execute the Zapier action."""
headers = {"x-api-key": self.api_key, "Content-Type": "application/json"}
@@ -64,9 +64,9 @@ class ZapierActionsAdapter:
logger.error("Zapier Actions API key is required")
raise ValueError("Zapier Actions API key is required")
def get_zapier_actions(self):
def get_zapier_actions(self) -> Any:
headers = {
"x-api-key": self.api_key,
"x-api-key": self.api_key or "",
}
response = requests.request(
"GET",

19
lib/crewai-tools/src/crewai_tools/aws/bedrock/agents/invoke_agent_tool.py
View File

@@ -2,6 +2,7 @@ from datetime import datetime, timezone
import json
import os
import time
from typing import Any
from crewai.tools import BaseTool
from dotenv import load_dotenv
@@ -42,17 +43,17 @@ class BedrockInvokeAgentTool(BaseTool):
enable_trace: bool = False,
end_session: bool = False,
description: str | None = None,
**kwargs,
):
**kwargs: Any,
) -> None:
"""Initialize the BedrockInvokeAgentTool with agent configuration.
Args:
agent_id (str): The unique identifier of the Bedrock agent
agent_alias_id (str): The unique identifier of the agent alias
session_id (str): The unique identifier of the session
enable_trace (bool): Whether to enable trace for the agent invocation
end_session (bool): Whether to end the session with the agent
description (Optional[str]): Custom description for the tool
agent_id: The unique identifier of the Bedrock agent.
agent_alias_id: The unique identifier of the agent alias.
session_id: The unique identifier of the session.
enable_trace: Whether to enable trace for the agent invocation.
end_session: Whether to end the session with the agent.
description: Custom description for the tool.
"""
super().__init__(**kwargs)
@@ -72,7 +73,7 @@ class BedrockInvokeAgentTool(BaseTool):
# Validate parameters
self._validate_parameters()
def _validate_parameters(self):
def _validate_parameters(self) -> None:
"""Validate the parameters according to AWS API requirements."""
try:
# Validate agent_id

62
lib/crewai-tools/src/crewai_tools/aws/bedrock/browser/browser_toolkit.py
View File

@@ -3,7 +3,7 @@
import asyncio
import json
import logging
from typing import Any
from typing import Any, cast
from urllib.parse import urlparse
from crewai.tools import BaseTool
@@ -82,7 +82,7 @@ class CurrentWebPageToolInput(BaseModel):
class BrowserBaseTool(BaseTool):
"""Base class for browser tools."""
def __init__(self, session_manager: BrowserSessionManager): # type: ignore[call-arg]
def __init__(self, session_manager: BrowserSessionManager) -> None:
"""Initialize with a session manager."""
super().__init__() # type: ignore[call-arg]
self._session_manager = session_manager
@@ -90,16 +90,16 @@ class BrowserBaseTool(BaseTool):
if self._is_in_asyncio_loop() and hasattr(self, "_arun"):
self._original_run = self._run
# Override _run to use _arun when in an asyncio loop
def patched_run(*args, **kwargs):
def patched_run(*args: Any, **kwargs: Any) -> str:
try:
import nest_asyncio # type: ignore[import-untyped]
loop = asyncio.get_event_loop()
nest_asyncio.apply(loop)
return asyncio.get_event_loop().run_until_complete(
result: str = asyncio.get_event_loop().run_until_complete(
self._arun(*args, **kwargs)
)
return result
except Exception as e:
return f"Error in patched _run: {e!s}"
@@ -132,7 +132,7 @@ class NavigateTool(BrowserBaseTool):
description: str = "Navigate a browser to the specified URL"
args_schema: type[BaseModel] = NavigateToolInput
def _run(self, url: str, thread_id: str = "default", **kwargs) -> str:
def _run(self, url: str, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the sync tool."""
try:
# Get page for this thread
@@ -150,7 +150,7 @@ class NavigateTool(BrowserBaseTool):
except Exception as e:
return f"Error navigating to {url}: {e!s}"
async def _arun(self, url: str, thread_id: str = "default", **kwargs) -> str:
async def _arun(self, url: str, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the async tool."""
try:
# Get page for this thread
@@ -188,7 +188,7 @@ class ClickTool(BrowserBaseTool):
return selector
return f"{selector} >> visible=1"
def _run(self, selector: str, thread_id: str = "default", **kwargs) -> str:
def _run(self, selector: str, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the sync tool."""
try:
# Get the current page
@@ -213,7 +213,9 @@ class ClickTool(BrowserBaseTool):
except Exception as e:
return f"Error clicking on element: {e!s}"
async def _arun(self, selector: str, thread_id: str = "default", **kwargs) -> str:
async def _arun(
self, selector: str, thread_id: str = "default", **kwargs: Any
) -> str:
"""Use the async tool."""
try:
# Get the current page
@@ -246,7 +248,7 @@ class NavigateBackTool(BrowserBaseTool):
description: str = "Navigate back to the previous page"
args_schema: type[BaseModel] = NavigateBackToolInput
def _run(self, thread_id: str = "default", **kwargs) -> str:
def _run(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the sync tool."""
try:
# Get the current page
@@ -261,7 +263,7 @@ class NavigateBackTool(BrowserBaseTool):
except Exception as e:
return f"Error navigating back: {e!s}"
async def _arun(self, thread_id: str = "default", **kwargs) -> str:
async def _arun(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the async tool."""
try:
# Get the current page
@@ -284,7 +286,7 @@ class ExtractTextTool(BrowserBaseTool):
description: str = "Extract all the text on the current webpage"
args_schema: type[BaseModel] = ExtractTextToolInput
def _run(self, thread_id: str = "default", **kwargs) -> str:
def _run(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the sync tool."""
try:
# Import BeautifulSoup
@@ -306,7 +308,7 @@ class ExtractTextTool(BrowserBaseTool):
except Exception as e:
return f"Error extracting text: {e!s}"
async def _arun(self, thread_id: str = "default", **kwargs) -> str:
async def _arun(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the async tool."""
try:
# Import BeautifulSoup
@@ -336,12 +338,12 @@ class ExtractHyperlinksTool(BrowserBaseTool):
description: str = "Extract all hyperlinks on the current webpage"
args_schema: type[BaseModel] = ExtractHyperlinksToolInput
def _run(self, thread_id: str = "default", **kwargs) -> str:
def _run(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the sync tool."""
try:
# Import BeautifulSoup
try:
from bs4 import BeautifulSoup
from bs4 import BeautifulSoup, Tag
except ImportError:
return (
"The 'beautifulsoup4' package is required to use this tool."
@@ -356,9 +358,10 @@ class ExtractHyperlinksTool(BrowserBaseTool):
soup = BeautifulSoup(content, "html.parser")
links = []
for link in soup.find_all("a", href=True):
text = link.get_text().strip()
href = link["href"]
if href.startswith(("http", "https")): # type: ignore[union-attr]
tag = cast(Tag, link)
text = tag.get_text().strip()
href = str(tag.get("href", ""))
if href.startswith(("http", "https")):
links.append({"text": text, "url": href})
if not links:
@@ -368,12 +371,12 @@ class ExtractHyperlinksTool(BrowserBaseTool):
except Exception as e:
return f"Error extracting hyperlinks: {e!s}"
async def _arun(self, thread_id: str = "default", **kwargs) -> str:
async def _arun(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the async tool."""
try:
# Import BeautifulSoup
try:
from bs4 import BeautifulSoup
from bs4 import BeautifulSoup, Tag
except ImportError:
return (
"The 'beautifulsoup4' package is required to use this tool."
@@ -388,9 +391,10 @@ class ExtractHyperlinksTool(BrowserBaseTool):
soup = BeautifulSoup(content, "html.parser")
links = []
for link in soup.find_all("a", href=True):
text = link.get_text().strip()
href = link["href"]
if href.startswith(("http", "https")): # type: ignore[union-attr]
tag = cast(Tag, link)
text = tag.get_text().strip()
href = str(tag.get("href", ""))
if href.startswith(("http", "https")):
links.append({"text": text, "url": href})
if not links:
@@ -408,7 +412,7 @@ class GetElementsTool(BrowserBaseTool):
description: str = "Get elements from the webpage using a CSS selector"
args_schema: type[BaseModel] = GetElementsToolInput
def _run(self, selector: str, thread_id: str = "default", **kwargs) -> str:
def _run(self, selector: str, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the sync tool."""
try:
# Get the current page
@@ -428,7 +432,9 @@ class GetElementsTool(BrowserBaseTool):
except Exception as e:
return f"Error getting elements: {e!s}"
async def _arun(self, selector: str, thread_id: str = "default", **kwargs) -> str:
async def _arun(
self, selector: str, thread_id: str = "default", **kwargs: Any
) -> str:
"""Use the async tool."""
try:
# Get the current page
@@ -456,7 +462,7 @@ class CurrentWebPageTool(BrowserBaseTool):
description: str = "Get information about the current webpage"
args_schema: type[BaseModel] = CurrentWebPageToolInput
def _run(self, thread_id: str = "default", **kwargs) -> str:
def _run(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the sync tool."""
try:
# Get the current page
@@ -469,7 +475,7 @@ class CurrentWebPageTool(BrowserBaseTool):
except Exception as e:
return f"Error getting current webpage info: {e!s}"
async def _arun(self, thread_id: str = "default", **kwargs) -> str:
async def _arun(self, thread_id: str = "default", **kwargs: Any) -> str:
"""Use the async tool."""
try:
# Get the current page
@@ -535,7 +541,7 @@ class BrowserToolkit:
self._nest_current_loop()
self._setup_tools()
def _nest_current_loop(self):
def _nest_current_loop(self) -> None:
"""Apply nest_asyncio if we're in an asyncio loop."""
try:
loop = asyncio.get_event_loop()

38
lib/crewai-tools/src/crewai_tools/aws/bedrock/code_interpreter/code_interpreter_toolkit.py
View File

@@ -16,7 +16,7 @@ if TYPE_CHECKING:
logger = logging.getLogger(__name__)
def extract_output_from_stream(response):
def extract_output_from_stream(response: dict[str, Any]) -> str:
"""Extract output from code interpreter response stream.
Args:
@@ -143,8 +143,8 @@ class ExecuteCodeTool(BaseTool):
args_schema: type[BaseModel] = ExecuteCodeInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(
@@ -198,8 +198,8 @@ class ExecuteCommandTool(BaseTool):
args_schema: type[BaseModel] = ExecuteCommandInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, command: str, thread_id: str = "default") -> str:
@@ -231,8 +231,8 @@ class ReadFilesTool(BaseTool):
args_schema: type[BaseModel] = ReadFilesInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, paths: list[str], thread_id: str = "default") -> str:
@@ -264,8 +264,8 @@ class ListFilesTool(BaseTool):
args_schema: type[BaseModel] = ListFilesInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, directory_path: str = "", thread_id: str = "default") -> str:
@@ -297,8 +297,8 @@ class DeleteFilesTool(BaseTool):
args_schema: type[BaseModel] = DeleteFilesInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, paths: list[str], thread_id: str = "default") -> str:
@@ -330,8 +330,8 @@ class WriteFilesTool(BaseTool):
args_schema: type[BaseModel] = WriteFilesInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, files: list[dict[str, str]], thread_id: str = "default") -> str:
@@ -365,8 +365,8 @@ class StartCommandTool(BaseTool):
args_schema: type[BaseModel] = StartCommandInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, command: str, thread_id: str = "default") -> str:
@@ -398,8 +398,8 @@ class GetTaskTool(BaseTool):
args_schema: type[BaseModel] = GetTaskInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, task_id: str, thread_id: str = "default") -> str:
@@ -431,8 +431,8 @@ class StopTaskTool(BaseTool):
args_schema: type[BaseModel] = StopTaskInput
toolkit: Any = Field(default=None, exclude=True)
def __init__(self, toolkit):
super().__init__()
def __init__(self, toolkit: CodeInterpreterToolkit, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.toolkit = toolkit
def _run(self, task_id: str, thread_id: str = "default") -> str:

16
lib/crewai-tools/src/crewai_tools/aws/bedrock/knowledge_base/retriever_tool.py
View File

@@ -44,16 +44,16 @@ class BedrockKBRetrieverTool(BaseTool):
retrieval_configuration: dict[str, Any] | None = None,
guardrail_configuration: dict[str, Any] | None = None,
next_token: str | None = None,
**kwargs,
):
**kwargs: Any,
) -> None:
"""Initialize the BedrockKBRetrieverTool with knowledge base configuration.
Args:
knowledge_base_id (str): The unique identifier of the knowledge base to query
number_of_results (Optional[int], optional): The maximum number of results to return. Defaults to 5.
retrieval_configuration (Optional[Dict[str, Any]], optional): Configurations for the knowledge base query and retrieval process. Defaults to None.
guardrail_configuration (Optional[Dict[str, Any]], optional): Guardrail settings. Defaults to None.
next_token (Optional[str], optional): Token for retrieving the next batch of results. Defaults to None.
knowledge_base_id: The unique identifier of the knowledge base to query.
number_of_results: The maximum number of results to return.
retrieval_configuration: Configurations for the knowledge base query and retrieval process.
guardrail_configuration: Guardrail settings.
next_token: Token for retrieving the next batch of results.
"""
super().__init__(**kwargs)
@@ -89,7 +89,7 @@ class BedrockKBRetrieverTool(BaseTool):
return {"vectorSearchConfiguration": vector_search_config}
def _validate_parameters(self):
def _validate_parameters(self) -> None:
"""Validate the parameters according to AWS API requirements."""
try:
# Validate knowledge_base_id

5
lib/crewai-tools/src/crewai_tools/aws/s3/reader_tool.py
View File

@@ -39,11 +39,12 @@ class S3ReaderTool(BaseTool):
# Read file content from S3
response = s3.get_object(Bucket=bucket_name, Key=object_key)
return response["Body"].read().decode("utf-8")
result: str = response["Body"].read().decode("utf-8")
return result
except ClientError as e:
return f"Error reading file from S3: {e!s}"
def _parse_s3_path(self, file_path: str) -> tuple:
def _parse_s3_path(self, file_path: str) -> tuple[str, str]:
parts = file_path.replace("s3://", "").split("/", 1)
return parts[0], parts[1]

2
lib/crewai-tools/src/crewai_tools/aws/s3/writer_tool.py
View File

@@ -45,6 +45,6 @@ class S3WriterTool(BaseTool):
except ClientError as e:
return f"Error writing file to S3: {e!s}"
def _parse_s3_path(self, file_path: str) -> tuple:
def _parse_s3_path(self, file_path: str) -> tuple[str, str]:
parts = file_path.replace("s3://", "").split("/", 1)
return parts[0], parts[1]

39
lib/crewai-tools/src/crewai_tools/generate_tool_specs.py
View File

@@ -1,10 +1,10 @@
#!/usr/bin/env python3
from collections.abc import Mapping
from collections.abc import Callable, Mapping
import inspect
import json
from pathlib import Path
from typing import Any
from typing import Any, cast
from crewai.tools.base_tool import BaseTool, EnvVar
from pydantic import BaseModel
@@ -115,7 +115,8 @@ class ToolSpecExtractor:
default_value = field.default
if default_value is PydanticUndefined or default_value is None:
if field.default_factory:
return field.default_factory()
factory = cast(Callable[[], Any], field.default_factory)
return factory()
return None
return default_value
@@ -153,21 +154,19 @@ class ToolSpecExtractor:
return default_value
# Dynamically computed from BaseTool so that any future fields or
# computed_fields added to BaseTool are automatically excluded from
# the generated spec — no hardcoded denylist to maintain.
# ``package_dependencies`` is not a BaseTool field but is extracted
# into its own top-level key, so it's also excluded from init_params.
_BASE_TOOL_FIELDS: set[str] = (
set(BaseTool.model_fields)
| set(BaseTool.model_computed_fields)
| {"package_dependencies"}
)
@staticmethod
def _extract_init_params(tool_class: type[BaseTool]) -> dict[str, Any]:
ignored_init_params = [
"name",
"description",
"env_vars",
"args_schema",
"description_updated",
"cache_function",
"result_as_answer",
"max_usage_count",
"current_usage_count",
"package_dependencies",
]
json_schema = tool_class.model_json_schema(
schema_generator=SchemaGenerator, mode="serialization"
)
@@ -175,8 +174,14 @@ class ToolSpecExtractor:
json_schema["properties"] = {
key: value
for key, value in json_schema["properties"].items()
if key not in ignored_init_params
if key not in ToolSpecExtractor._BASE_TOOL_FIELDS
}
if "required" in json_schema:
json_schema["required"] = [
key
for key in json_schema["required"]
if key not in ToolSpecExtractor._BASE_TOOL_FIELDS
]
return json_schema
def save_to_json(self, output_path: str) -> None:

3
lib/crewai-tools/src/crewai_tools/rag/__init__.py
View File

@@ -1,5 +1,6 @@
from crewai_tools.rag.core import RAG, EmbeddingService
from crewai_tools.rag.core import RAG
from crewai_tools.rag.data_types import DataType
from crewai_tools.rag.embedding_service import EmbeddingService
__all__ = [

2
lib/crewai-tools/src/crewai_tools/rag/base_loader.py
View File

@@ -21,7 +21,7 @@ class BaseLoader(ABC):
self.config = config or {}
@abstractmethod
def load(self, content: SourceContent, **kwargs) -> LoaderResult: ...
def load(self, content: SourceContent, **kwargs: Any) -> LoaderResult: ...
@staticmethod
def generate_doc_id(

2
lib/crewai-tools/src/crewai_tools/rag/core.py
View File

@@ -77,7 +77,7 @@ class RAG(Adapter):
super().model_post_init(__context)
def add(
def add( # type: ignore[override]
self,
content: str | Path,
data_type: str | DataType | None = None,

2
lib/crewai-tools/src/crewai_tools/rag/data_types.py
View File

@@ -109,7 +109,7 @@ class DataTypes:
if isinstance(content, str):
try:
url = urlparse(content)
is_url = bool(url.scheme and url.netloc) or url.scheme == "file"
is_url = bool(url.scheme in ("http", "https") and url.netloc)
except Exception: # noqa: S110
pass

11
lib/crewai-tools/src/crewai_tools/rag/embedding_service.py
View File

@@ -9,6 +9,7 @@ import logging
import os
from typing import Any
from crewai.rag.core.base_embeddings_callable import EmbeddingFunction
from pydantic import BaseModel, Field
@@ -81,7 +82,7 @@ class EmbeddingService:
**kwargs,
)
self._embedding_function = None
self._embedding_function: EmbeddingFunction[Any] | None = None
self._initialize_embedding_function()
@staticmethod
@@ -107,7 +108,7 @@ class EmbeddingService:
return os.getenv(env_key)
return None
def _initialize_embedding_function(self):
def _initialize_embedding_function(self) -> None:
"""Initialize the embedding function using CrewAI's factory."""
try:
from crewai.rag.embeddings.factory import build_embedder
@@ -264,7 +265,7 @@ class EmbeddingService:
try:
# Use ChromaDB's embedding function interface
embeddings = self._embedding_function([text]) # type: ignore
return embeddings[0] if embeddings else []
return list(embeddings[0]) if embeddings else []
except Exception as e:
logger.error(f"Error generating embedding for text: {e}")
@@ -294,12 +295,12 @@ class EmbeddingService:
try:
# Process in batches to avoid API limits
all_embeddings = []
all_embeddings: list[list[float]] = []
for i in range(0, len(valid_texts), self.config.batch_size):
batch = valid_texts[i : i + self.config.batch_size]
batch_embeddings = self._embedding_function(batch) # type: ignore
all_embeddings.extend(batch_embeddings)
all_embeddings.extend(list(e) for e in batch_embeddings)
return all_embeddings

3
lib/crewai-tools/src/crewai_tools/rag/loaders/csv_loader.py
View File

@@ -1,5 +1,6 @@
import csv
from io import StringIO
from typing import Any
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
from crewai_tools.rag.loaders.utils import load_from_url
@@ -7,7 +8,7 @@ from crewai_tools.rag.source_content import SourceContent
class CSVLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
source_ref = source_content.source_ref
content_str = source_content.source

5
lib/crewai-tools/src/crewai_tools/rag/loaders/directory_loader.py
View File

@@ -1,12 +1,13 @@
import os
from pathlib import Path
from typing import Any
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
from crewai_tools.rag.source_content import SourceContent
class DirectoryLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
"""Load and process all files from a directory recursively.
Args:
@@ -32,7 +33,7 @@ class DirectoryLoader(BaseLoader):
return self._process_directory(source_ref, kwargs)
def _process_directory(self, dir_path: str, kwargs: dict) -> LoaderResult:
def _process_directory(self, dir_path: str, kwargs: dict[str, Any]) -> LoaderResult:
recursive: bool = kwargs.get("recursive", True)
include_extensions: list[str] | None = kwargs.get("include_extensions", None)
exclude_extensions: list[str] | None = kwargs.get("exclude_extensions", None)

13
lib/crewai-tools/src/crewai_tools/rag/loaders/docs_site_loader.py
View File

@@ -1,8 +1,9 @@
"""Documentation site loader."""
from typing import Any
from urllib.parse import urljoin, urlparse
from bs4 import BeautifulSoup
from bs4 import BeautifulSoup, Tag
import requests
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
@@ -12,7 +13,7 @@ from crewai_tools.rag.source_content import SourceContent
class DocsSiteLoader(BaseLoader):
"""Loader for documentation websites."""
def load(self, source: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
"""Load content from a documentation site.
Args:
@@ -53,7 +54,9 @@ class DocsSiteLoader(BaseLoader):
break
if not main_content:
main_content = soup.find("body")
body = soup.find("body")
if isinstance(body, Tag):
main_content = body
if not main_content:
raise ValueError(
@@ -66,6 +69,8 @@ class DocsSiteLoader(BaseLoader):
if headings:
text_parts.append("Table of Contents:")
for heading in headings[:15]:
if not isinstance(heading, Tag):
continue
level = int(heading.name[1])
indent = " " * (level - 1)
text_parts.append(f"{indent}- {heading.get_text(strip=True)}")
@@ -81,6 +86,8 @@ class DocsSiteLoader(BaseLoader):
if nav:
links = nav.find_all("a", href=True)
for link in links[:20]:
if not isinstance(link, Tag):
continue
href = link.get("href", "")
if isinstance(href, str) and not href.startswith(
("http://", "https://", "mailto:", "#")

4
lib/crewai-tools/src/crewai_tools/rag/loaders/docx_loader.py
View File

@@ -9,7 +9,7 @@ from crewai_tools.rag.source_content import SourceContent
class DOCXLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
try:
from docx import Document as DocxDocument
except ImportError as e:
@@ -33,7 +33,7 @@ class DOCXLoader(BaseLoader):
)
@staticmethod
def _download_from_url(url: str, kwargs: dict) -> str:
def _download_from_url(url: str, kwargs: dict[str, Any]) -> str:
headers = kwargs.get(
"headers",
{

4
lib/crewai-tools/src/crewai_tools/rag/loaders/github_loader.py
View File

@@ -1,5 +1,7 @@
"""GitHub repository content loader."""
from typing import Any
from github import Github, GithubException
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
@@ -9,7 +11,7 @@ from crewai_tools.rag.source_content import SourceContent
class GithubLoader(BaseLoader):
"""Loader for GitHub repository content."""
def load(self, source: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
"""Load content from a GitHub repository.
Args:

3
lib/crewai-tools/src/crewai_tools/rag/loaders/json_loader.py
View File

@@ -1,4 +1,5 @@
import json
from typing import Any
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
from crewai_tools.rag.loaders.utils import load_from_url
@@ -6,7 +7,7 @@ from crewai_tools.rag.source_content import SourceContent
class JSONLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
source_ref = source_content.source_ref
content = source_content.source

4
lib/crewai-tools/src/crewai_tools/rag/loaders/mdx_loader.py
View File

@@ -1,5 +1,5 @@
import re
from typing import Final
from typing import Any, Final
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
from crewai_tools.rag.loaders.utils import load_from_url
@@ -15,7 +15,7 @@ _EXTRA_NEWLINES_PATTERN: Final[re.Pattern[str]] = re.compile(r"\n\s*\n\s*\n")
class MDXLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
source_ref = source_content.source_ref
content = source_content.source

32
lib/crewai-tools/src/crewai_tools/rag/loaders/pdf_loader.py
View File

@@ -2,9 +2,11 @@
import os
from pathlib import Path
from typing import Any, cast
import tempfile
from typing import Any
from urllib.parse import urlparse
import urllib.request
import requests
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
from crewai_tools.rag.source_content import SourceContent
@@ -23,22 +25,34 @@ class PDFLoader(BaseLoader):
return False
@staticmethod
def _download_pdf(url: str) -> bytes:
"""Download PDF content from a URL.
def _download_from_url(url: str, kwargs: dict[str, Any]) -> str:
"""Download PDF from a URL to a temporary file and return its path.
Args:
url: The URL to download from.
kwargs: Optional dict that may contain custom headers.
Returns:
The PDF content as bytes.
Path to the temporary file containing the PDF.
Raises:
ValueError: If the download fails.
"""
headers = kwargs.get(
"headers",
{
"Accept": "application/pdf",
"User-Agent": "Mozilla/5.0 (compatible; crewai-tools PDFLoader)",
},
)
try:
with urllib.request.urlopen(url, timeout=30) as response: # noqa: S310
return cast(bytes, response.read())
response = requests.get(url, headers=headers, timeout=30)
response.raise_for_status()
with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as temp_file:
temp_file.write(response.content)
return temp_file.name
except Exception as e:
raise ValueError(f"Failed to download PDF from {url}: {e!s}") from e
@@ -80,8 +94,8 @@ class PDFLoader(BaseLoader):
try:
if is_url:
pdf_bytes = self._download_pdf(file_path)
doc = pymupdf.open(stream=pdf_bytes, filetype="pdf")
local_path = self._download_from_url(file_path, kwargs)
doc = pymupdf.open(local_path)
else:
if not os.path.isfile(file_path):
raise FileNotFoundError(f"PDF file not found: {file_path}")

3
lib/crewai-tools/src/crewai_tools/rag/loaders/postgres_loader.py
View File

@@ -1,5 +1,6 @@
"""PostgreSQL database loader."""
from typing import Any
from urllib.parse import urlparse
from psycopg2 import Error, connect
@@ -12,7 +13,7 @@ from crewai_tools.rag.source_content import SourceContent
class PostgresLoader(BaseLoader):
"""Loader for PostgreSQL database content."""
def load(self, source: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
"""Load content from a PostgreSQL database table.
Args:

6
lib/crewai-tools/src/crewai_tools/rag/loaders/text_loader.py
View File

@@ -1,9 +1,11 @@
from typing import Any
from crewai_tools.rag.base_loader import BaseLoader, LoaderResult
from crewai_tools.rag.source_content import SourceContent
class TextFileLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
source_ref = source_content.source_ref
if not source_content.path_exists():
raise FileNotFoundError(
@@ -21,7 +23,7 @@ class TextFileLoader(BaseLoader):
class TextLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
return LoaderResult(
content=source_content.source,
source=source_content.source_ref,

7
lib/crewai-tools/src/crewai_tools/rag/loaders/utils.py
View File

@@ -1,8 +1,13 @@
"""Utility functions for RAG loaders."""
from typing import Any
def load_from_url(
url: str, kwargs: dict, accept_header: str = "*/*", loader_name: str = "Loader"
url: str,
kwargs: dict[str, Any],
accept_header: str = "*/*",
loader_name: str = "Loader",
) -> str:
"""Load content from a URL.

4
lib/crewai-tools/src/crewai_tools/rag/loaders/webpage_loader.py
View File

@@ -1,5 +1,5 @@
import re
from typing import Final
from typing import Any, Final
from bs4 import BeautifulSoup
import requests
@@ -13,7 +13,7 @@ _NEWLINE_PATTERN: Final[re.Pattern[str]] = re.compile(r"\s+\n\s+")
class WebPageLoader(BaseLoader):
def load(self, source_content: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source_content: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
url = source_content.source
headers = kwargs.get(
"headers",

2
lib/crewai-tools/src/crewai_tools/rag/loaders/youtube_channel_loader.py
View File

@@ -10,7 +10,7 @@ from crewai_tools.rag.source_content import SourceContent
class YoutubeChannelLoader(BaseLoader):
"""Loader for YouTube channels."""
def load(self, source: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
"""Load and extract content from a YouTube channel.
Args:

2
lib/crewai-tools/src/crewai_tools/rag/loaders/youtube_video_loader.py
View File

@@ -11,7 +11,7 @@ from crewai_tools.rag.source_content import SourceContent
class YoutubeVideoLoader(BaseLoader):
"""Loader for YouTube videos."""
def load(self, source: SourceContent, **kwargs) -> LoaderResult: # type: ignore[override]
def load(self, source: SourceContent, **kwargs: Any) -> LoaderResult: # type: ignore[override]
"""Load and extract transcript from a YouTube video.
Args:

0
lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/__init__.py → lib/crewai-tools/src/crewai_tools/security/__init__.py
View File

205
lib/crewai-tools/src/crewai_tools/security/safe_path.py Normal file
View File

@@ -0,0 +1,205 @@
"""Path and URL validation utilities for crewai-tools.
Provides validation for file paths and URLs to prevent unauthorized
file access and server-side request forgery (SSRF) when tools accept
user-controlled or LLM-controlled inputs at runtime.
Set CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true to bypass validation (not
recommended for production).
"""
from __future__ import annotations
import ipaddress
import logging
import os
import socket
from urllib.parse import urlparse
logger = logging.getLogger(__name__)
_UNSAFE_PATHS_ENV = "CREWAI_TOOLS_ALLOW_UNSAFE_PATHS"
def _is_escape_hatch_enabled() -> bool:
"""Check if the unsafe paths escape hatch is enabled."""
return os.environ.get(_UNSAFE_PATHS_ENV, "").lower() in ("true", "1", "yes")
# ---------------------------------------------------------------------------
# File path validation
# ---------------------------------------------------------------------------
def validate_file_path(path: str, base_dir: str | None = None) -> str:
"""Validate that a file path is safe to read.
Resolves symlinks and ``..`` components, then checks that the resolved
path falls within *base_dir* (defaults to the current working directory).
Args:
path: The file path to validate.
base_dir: Allowed root directory. Defaults to ``os.getcwd()``.
Returns:
The resolved, validated absolute path.
Raises:
ValueError: If the path escapes the allowed directory.
"""
if _is_escape_hatch_enabled():
logger.warning(
"%s is enabled — skipping file path validation for: %s",
_UNSAFE_PATHS_ENV,
path,
)
return os.path.realpath(path)
if base_dir is None:
base_dir = os.getcwd()
resolved_base = os.path.realpath(base_dir)
resolved_path = os.path.realpath(
os.path.join(resolved_base, path) if not os.path.isabs(path) else path
)
# Ensure the resolved path is within the base directory.
# When resolved_base already ends with a separator (e.g. the filesystem
# root "/"), appending os.sep would double it ("//"), so use the base
# as-is in that case.
prefix = resolved_base if resolved_base.endswith(os.sep) else resolved_base + os.sep
if not resolved_path.startswith(prefix) and resolved_path != resolved_base:
raise ValueError(
f"Path '{path}' resolves to '{resolved_path}' which is outside "
f"the allowed directory '{resolved_base}'. "
f"Set {_UNSAFE_PATHS_ENV}=true to bypass this check."
)
return resolved_path
def validate_directory_path(path: str, base_dir: str | None = None) -> str:
"""Validate that a directory path is safe to read.
Same as :func:`validate_file_path` but also checks that the path
is an existing directory.
Args:
path: The directory path to validate.
base_dir: Allowed root directory. Defaults to ``os.getcwd()``.
Returns:
The resolved, validated absolute path.
Raises:
ValueError: If the path escapes the allowed directory or is not a directory.
"""
validated = validate_file_path(path, base_dir)
if not os.path.isdir(validated):
raise ValueError(f"Path '{validated}' is not a directory.")
return validated
# ---------------------------------------------------------------------------
# URL validation
# ---------------------------------------------------------------------------
# Private and reserved IP ranges that should not be accessed
_BLOCKED_IPV4_NETWORKS = [
ipaddress.ip_network("10.0.0.0/8"),
ipaddress.ip_network("172.16.0.0/12"),
ipaddress.ip_network("192.168.0.0/16"),
ipaddress.ip_network("127.0.0.0/8"),
ipaddress.ip_network("169.254.0.0/16"), # Link-local / cloud metadata
ipaddress.ip_network("0.0.0.0/32"),
]
_BLOCKED_IPV6_NETWORKS = [
ipaddress.ip_network("::1/128"),
ipaddress.ip_network("::/128"),
ipaddress.ip_network("fc00::/7"), # Unique local addresses
ipaddress.ip_network("fe80::/10"), # Link-local IPv6
]
def _is_private_or_reserved(ip_str: str) -> bool:
"""Check if an IP address is private, reserved, or otherwise unsafe."""
try:
addr = ipaddress.ip_address(ip_str)
# Unwrap IPv4-mapped IPv6 addresses (e.g., ::ffff:127.0.0.1) to IPv4
# so they are only checked against IPv4 networks (avoids TypeError when
# an IPv4Address is compared against an IPv6Network).
if isinstance(addr, ipaddress.IPv6Address) and addr.ipv4_mapped:
addr = addr.ipv4_mapped
networks = (
_BLOCKED_IPV4_NETWORKS
if isinstance(addr, ipaddress.IPv4Address)
else _BLOCKED_IPV6_NETWORKS
)
return any(addr in network for network in networks)
except ValueError:
return True # If we can't parse, block it
def validate_url(url: str) -> str:
"""Validate that a URL is safe to fetch.
Blocks ``file://`` scheme entirely. For ``http``/``https``, resolves
DNS and checks that the target IP is not private or reserved (prevents
SSRF to internal services and cloud metadata endpoints).
Args:
url: The URL to validate.
Returns:
The validated URL string.
Raises:
ValueError: If the URL uses a blocked scheme or resolves to a
private/reserved IP address.
"""
if _is_escape_hatch_enabled():
logger.warning(
"%s is enabled — skipping URL validation for: %s",
_UNSAFE_PATHS_ENV,
url,
)
return url
parsed = urlparse(url)
# Block file:// scheme
if parsed.scheme == "file":
raise ValueError(
f"file:// URLs are not allowed: '{url}'. "
f"Use a file path instead, or set {_UNSAFE_PATHS_ENV}=true to bypass."
)
# Only allow http and https
if parsed.scheme not in ("http", "https"):
raise ValueError(
f"URL scheme '{parsed.scheme}' is not allowed. Only http and https are supported."
)
if not parsed.hostname:
raise ValueError(f"URL has no hostname: '{url}'")
# Resolve DNS and check IPs
try:
addrinfos = socket.getaddrinfo(
parsed.hostname, parsed.port or (443 if parsed.scheme == "https" else 80)
)
except socket.gaierror as exc:
raise ValueError(f"Could not resolve hostname: '{parsed.hostname}'") from exc
for _family, _, _, _, sockaddr in addrinfos:
ip_str = str(sockaddr[0])
if _is_private_or_reserved(ip_str):
raise ValueError(
f"URL '{url}' resolves to private/reserved IP {ip_str}. "
f"Access to internal networks is not allowed. "
f"Set {_UNSAFE_PATHS_ENV}=true to bypass."
)
return url

4
lib/crewai-tools/src/crewai_tools/tools/__init__.py
View File

@@ -24,9 +24,6 @@ from crewai_tools.tools.browserbase_load_tool.browserbase_load_tool import (
from crewai_tools.tools.code_docs_search_tool.code_docs_search_tool import (
CodeDocsSearchTool,
)
from crewai_tools.tools.code_interpreter_tool.code_interpreter_tool import (
CodeInterpreterTool,
)
from crewai_tools.tools.composio_tool.composio_tool import ComposioTool
from crewai_tools.tools.contextualai_create_agent_tool.contextual_create_agent_tool import (
ContextualAICreateAgentTool,
@@ -210,7 +207,6 @@ __all__ = [
"BrowserbaseLoadTool",
"CSVSearchTool",
"CodeDocsSearchTool",
"CodeInterpreterTool",
"ComposioTool",
"ContextualAICreateAgentTool",
"ContextualAIParseTool",

10
lib/crewai-tools/src/crewai_tools/tools/ai_mind_tool/ai_mind_tool.py
View File

@@ -42,7 +42,7 @@ class AIMindTool(BaseTool):
]
)
def __init__(self, api_key: str | None = None, **kwargs):
def __init__(self, api_key: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.api_key = api_key or os.getenv("MINDS_API_KEY")
if not self.api_key:
@@ -51,8 +51,10 @@ class AIMindTool(BaseTool):
)
try:
from minds.client import Client # type: ignore
from minds.datasources import DatabaseConfig # type: ignore
from minds.client import Client # type: ignore[import-not-found]
from minds.datasources import ( # type: ignore[import-not-found]
DatabaseConfig,
)
except ImportError as e:
raise ImportError(
"`minds_sdk` package not found, please run `pip install minds-sdk`"
@@ -81,7 +83,7 @@ class AIMindTool(BaseTool):
self.mind_name = mind.name
def _run(self, query: str):
def _run(self, query: str) -> str | None:
# Run the query on the AI-Mind.
# The Minds API is OpenAI compatible and therefore, the OpenAI client can be used.
openai_client = OpenAI(

10
lib/crewai-tools/src/crewai_tools/tools/arxiv_paper_tool/arxiv_paper_tool.py
View File

@@ -2,7 +2,7 @@ import logging
from pathlib import Path
import re
import time
from typing import ClassVar
from typing import Any, ClassVar
import urllib.error
import urllib.parse
import urllib.request
@@ -75,7 +75,9 @@ class ArxivPaperTool(BaseTool):
logger.error(f"ArxivTool Error: {e!s}")
return f"Failed to fetch or download Arxiv papers: {e!s}"
def fetch_arxiv_data(self, search_query: str, max_results: int) -> list[dict]:
def fetch_arxiv_data(
self, search_query: str, max_results: int
) -> list[dict[str, Any]]:
api_url = f"{self.BASE_API_URL}?search_query={urllib.parse.quote(search_query)}&start=0&max_results={max_results}"
logger.info(f"Fetching data from Arxiv API: {api_url}")
@@ -135,7 +137,7 @@ class ArxivPaperTool(BaseTool):
return href
return None
def _format_paper_result(self, paper: dict) -> str:
def _format_paper_result(self, paper: dict[str, Any]) -> str:
summary = (
(paper["summary"][: self.SUMMARY_TRUNCATE_LENGTH] + "...")
if len(paper["summary"]) > self.SUMMARY_TRUNCATE_LENGTH
@@ -156,7 +158,7 @@ class ArxivPaperTool(BaseTool):
save_path.mkdir(parents=True, exist_ok=True)
return save_path
def download_pdf(self, pdf_url: str, save_path: str):
def download_pdf(self, pdf_url: str, save_path: str) -> None:
try:
logger.info(f"Downloading PDF from {pdf_url} to {save_path}")
urllib.request.urlretrieve(pdf_url, str(save_path)) # noqa: S310

11
lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/base.py
View File

@@ -138,7 +138,7 @@ class BraveSearchToolBase(BaseTool, ABC):
self._rate_limit_lock = threading.Lock()
@property
def api_key(self) -> str:
def api_key(self) -> str | None:
return self._api_key
@property
@@ -214,7 +214,8 @@ class BraveSearchToolBase(BaseTool, ABC):
# Response was OK, return the JSON body
if resp.ok:
try:
return resp.json()
result: dict[str, Any] = resp.json()
return result
except ValueError as exc:
raise RuntimeError(
f"Brave Search API returned invalid JSON (HTTP {resp.status_code}): {exc}"
@@ -239,9 +240,9 @@ class BraveSearchToolBase(BaseTool, ABC):
# (e.g., 422 Unprocessable Entity, 400 Bad Request (OPTION_NOT_IN_PLAN))
_raise_for_error(resp)
# All retries exhausted
_raise_for_error(last_resp or resp) # type: ignore[possibly-undefined]
return {} # unreachable (here to satisfy the type checker and linter)
# All retries exhausted — last_resp is always set when we reach here
_raise_for_error(last_resp or resp)
return {} # unreachable; satisfies return type
def _run(self, q: str | None = None, **params: Any) -> Any:
# Allow positional usage: tool.run("latest Brave browser features")

3
lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_llm_context_tool.py
View File

@@ -3,7 +3,6 @@ from typing import Any
from pydantic import BaseModel
from crewai_tools.tools.brave_search_tool.base import BraveSearchToolBase
from crewai_tools.tools.brave_search_tool.response_types import LLMContext
from crewai_tools.tools.brave_search_tool.schemas import (
LLMContextHeaders,
LLMContextParams,
@@ -27,6 +26,6 @@ class BraveLLMContextTool(BraveSearchToolBase):
def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
return params
def _refine_response(self, response: LLMContext.Response) -> LLMContext.Response:
def _refine_response(self, response: dict[str, Any]) -> Any:
"""The LLM Context response schema is fairly simple. Return as is."""
return response

13
lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_local_pois_tool.py
View File

@@ -1,4 +1,4 @@
from typing import Any
from typing import Any, cast
from pydantic import BaseModel
@@ -65,8 +65,8 @@ class BraveLocalPOIsTool(BraveSearchToolBase):
def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
return params
def _refine_response(self, response: LocalPOIsResponse) -> list[dict[str, Any]]:
results = response.get("results", [])
def _refine_response(self, response: dict[str, Any]) -> list[dict[str, Any]]:
results: list[dict[str, Any]] = response.get("results", [])
return [
{
"title": result.get("title"),
@@ -76,7 +76,7 @@ class BraveLocalPOIsTool(BraveSearchToolBase):
"contact": result.get("contact", {}).get("telephone")
or result.get("contact", {}).get("email")
or None,
"opening_hours": _simplify_opening_hours(result),
"opening_hours": _simplify_opening_hours(cast(LocationResult, result)),
}
for result in results
]
@@ -97,9 +97,8 @@ class BraveLocalPOIsDescriptionTool(BraveSearchToolBase):
def _refine_request_payload(self, params: dict[str, Any]) -> dict[str, Any]:
return params
def _refine_response(self, response: LocalPOIsResponse) -> list[dict[str, Any]]:
# Make the response more concise, and easier to consume
results = response.get("results", [])
def _refine_response(self, response: dict[str, Any]) -> list[dict[str, Any]]:
results: list[dict[str, Any]] = response.get("results", [])
return [
{
"id": result.get("id"),

2
lib/crewai-tools/src/crewai_tools/tools/brave_search_tool/brave_search_tool.py
View File

@@ -50,7 +50,7 @@ class BraveSearchTool(BaseTool):
_last_request_time: ClassVar[float] = 0
_min_request_interval: ClassVar[float] = 1.0 # seconds
def __init__(self, *args, **kwargs):
def __init__(self, *args: Any, **kwargs: Any) -> None:
super().__init__(*args, **kwargs)
if "BRAVE_API_KEY" not in os.environ:
raise ValueError(

12
lib/crewai-tools/src/crewai_tools/tools/brightdata_tool/brightdata_dataset.py
View File

@@ -1,3 +1,5 @@
from __future__ import annotations
import asyncio
import os
from typing import Any
@@ -13,7 +15,7 @@ class BrightDataConfig(BaseModel):
DEFAULT_POLLING_INTERVAL: int = 1
@classmethod
def from_env(cls):
def from_env(cls) -> BrightDataConfig:
return cls(
API_URL=os.environ.get("BRIGHTDATA_API_URL", "https://api.brightdata.com"),
DEFAULT_TIMEOUT=int(os.environ.get("BRIGHTDATA_DEFAULT_TIMEOUT", "600")),
@@ -26,12 +28,12 @@ class BrightDataConfig(BaseModel):
class BrightDataDatasetToolException(Exception): # noqa: N818
"""Exception raised for custom error in the application."""
def __init__(self, message, error_code):
def __init__(self, message: str, error_code: int) -> None:
self.message = message
super().__init__(message)
self.error_code = error_code
def __str__(self):
def __str__(self) -> str:
return f"{self.message} (Error Code: {self.error_code})"
@@ -62,7 +64,7 @@ config = BrightDataConfig.from_env()
BRIGHTDATA_API_URL = config.API_URL
timeout = config.DEFAULT_TIMEOUT
datasets = [
datasets: list[dict[str, Any]] = [
{
"id": "amazon_product",
"dataset_id": "gd_l7q7dkf244hwjntr0",
@@ -440,7 +442,7 @@ class BrightDataDatasetTool(BaseTool):
self.zipcode = zipcode
self.additional_params = additional_params
def filter_dataset_by_id(self, target_id):
def filter_dataset_by_id(self, target_id: str) -> list[dict[str, Any]]:
return [dataset for dataset in datasets if dataset["id"] == target_id]
async def get_dataset_data_async(

8
lib/crewai-tools/src/crewai_tools/tools/brightdata_tool/brightdata_serp.py
View File

@@ -1,3 +1,5 @@
from __future__ import annotations
import os
from typing import Any
import urllib.parse
@@ -11,7 +13,7 @@ class BrightDataConfig(BaseModel):
API_URL: str = "https://api.brightdata.com/request"
@classmethod
def from_env(cls):
def from_env(cls) -> BrightDataConfig:
return cls(
API_URL=os.environ.get(
"BRIGHTDATA_API_URL", "https://api.brightdata.com/request"
@@ -127,7 +129,7 @@ class BrightDataSearchTool(BaseTool):
if not self.zone:
raise ValueError("BRIGHT_DATA_ZONE environment variable is required.")
def get_search_url(self, engine: str, query: str):
def get_search_url(self, engine: str, query: str) -> str:
if engine == "yandex":
return f"https://yandex.com/search/?text=${query}"
if engine == "bing":
@@ -143,7 +145,7 @@ class BrightDataSearchTool(BaseTool):
search_type: str | None = None,
device_type: str | None = None,
parse_results: bool | None = None,
**kwargs,
**kwargs: Any,
) -> Any:
"""Executes a search query using Bright Data SERP API and returns results.

7
lib/crewai-tools/src/crewai_tools/tools/brightdata_tool/brightdata_unlocker.py
View File

@@ -1,3 +1,5 @@
from __future__ import annotations
import os
from typing import Any
@@ -5,12 +7,14 @@ from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, Field
import requests
from crewai_tools.security.safe_path import validate_url
class BrightDataConfig(BaseModel):
API_URL: str = "https://api.brightdata.com/request"
@classmethod
def from_env(cls):
def from_env(cls) -> BrightDataConfig:
return cls(
API_URL=os.environ.get(
"BRIGHTDATA_API_URL", "https://api.brightdata.com/request"
@@ -132,6 +136,7 @@ class BrightDataWebUnlockerTool(BaseTool):
"Content-Type": "application/json",
}
validate_url(url)
try:
response = requests.post(
self.base_url, json=payload, headers=headers, timeout=30

10
lib/crewai-tools/src/crewai_tools/tools/browserbase_load_tool/browserbase_load_tool.py
View File

@@ -42,15 +42,15 @@ class BrowserbaseLoadTool(BaseTool):
text_content: bool | None = False,
session_id: str | None = None,
proxy: bool | None = None,
**kwargs,
):
**kwargs: Any,
) -> None:
super().__init__(**kwargs)
if not self.api_key:
raise EnvironmentError(
"BROWSERBASE_API_KEY environment variable is required for initialization"
)
try:
from browserbase import Browserbase # type: ignore
from browserbase import Browserbase
except ImportError:
import click
@@ -60,7 +60,7 @@ class BrowserbaseLoadTool(BaseTool):
import subprocess
subprocess.run(["uv", "add", "browserbase"], check=True) # noqa: S607
from browserbase import Browserbase # type: ignore
from browserbase import Browserbase
else:
raise ImportError(
"`browserbase` package not found, please run `uv add browserbase`"
@@ -71,7 +71,7 @@ class BrowserbaseLoadTool(BaseTool):
self.session_id = session_id
self.proxy = proxy
def _run(self, url: str):
def _run(self, url: str) -> Any:
return self.browserbase.load_url( # type: ignore[union-attr]
url, self.text_content, self.session_id, self.proxy
)

6
lib/crewai-tools/src/crewai_tools/tools/code_docs_search_tool/code_docs_search_tool.py
View File

@@ -1,3 +1,5 @@
from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.rag.data_types import DataType
@@ -26,7 +28,7 @@ class CodeDocsSearchTool(RagTool):
)
args_schema: type[BaseModel] = CodeDocsSearchToolSchema
def __init__(self, docs_url: str | None = None, **kwargs):
def __init__(self, docs_url: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
if docs_url is not None:
self.add(docs_url)
@@ -34,7 +36,7 @@ class CodeDocsSearchTool(RagTool):
self.args_schema = FixedCodeDocsSearchToolSchema
self._generate_description()
def add(self, docs_url: str) -> None:
def add(self, docs_url: str) -> None: # type: ignore[override]
super().add(docs_url, data_type=DataType.DOCS_SITE)
def _run( # type: ignore[override]

6
lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/Dockerfile
View File

@@ -1,6 +0,0 @@
FROM python:3.12-alpine
RUN pip install requests beautifulsoup4
# Set the working directory
WORKDIR /workspace

95
lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/README.md
View File

@@ -1,95 +0,0 @@
# CodeInterpreterTool
## Description
This tool is used to give the Agent the ability to run code (Python3) from the code generated by the Agent itself. The code is executed in a Docker container for secure isolation.
It is incredibly useful since it allows the Agent to generate code, run it in an isolated environment, get the result and use it to make decisions.
## ⚠️ Security Requirements
**Docker is REQUIRED** for safe code execution. The tool will refuse to execute code without Docker to prevent security vulnerabilities.
### Why Docker is Required
Previous versions included a "restricted sandbox" fallback when Docker was unavailable. This has been **removed** due to critical security vulnerabilities:
- The Python-based sandbox could be escaped via object introspection
- Attackers could recover the original `__import__` function and access any module
- This allowed arbitrary command execution on the host system
**Docker provides real process isolation** and is the only secure way to execute untrusted code.
## Requirements
- **Docker (REQUIRED)** - Install from [docker.com](https://docs.docker.com/get-docker/)
## Installation
Install the crewai_tools package
```shell
pip install 'crewai[tools]'
```
## Example
Remember that when using this tool, the code must be generated by the Agent itself. The code must be Python3 code. It will take some time the first time to run because it needs to build the Docker image.
### Basic Usage (Docker Container - Recommended)
```python
from crewai_tools import CodeInterpreterTool
Agent(
...
tools=[CodeInterpreterTool()],
)
```
### Custom Dockerfile
If you need to pass your own Dockerfile:
```python
from crewai_tools import CodeInterpreterTool
Agent(
...
tools=[CodeInterpreterTool(user_dockerfile_path="<Dockerfile_path>")],
)
```
### Manual Docker Host Configuration
If it is difficult to connect to the Docker daemon automatically (especially for macOS users), you can set up the Docker host manually:
```python
from crewai_tools import CodeInterpreterTool
Agent(
...
tools=[CodeInterpreterTool(
user_docker_base_url="<Docker Host Base Url>",
user_dockerfile_path="<Dockerfile_path>"
)],
)
```
### Unsafe Mode (NOT RECOMMENDED)
If you absolutely cannot use Docker and **fully trust the code source**, you can use unsafe mode:
```python
from crewai_tools import CodeInterpreterTool
# WARNING: Only use with fully trusted code!
Agent(
...
tools=[CodeInterpreterTool(unsafe_mode=True)],
)
```
**⚠️ SECURITY WARNING:** `unsafe_mode=True` executes code directly on the host without any isolation. Only use this if:
- You completely trust the code being executed
- You understand the security risks
- You cannot install Docker in your environment
For production use, **always use Docker** (the default mode).

423
lib/crewai-tools/src/crewai_tools/tools/code_interpreter_tool/code_interpreter_tool.py
View File

@@ -1,423 +0,0 @@
"""Code Interpreter Tool for executing Python code in isolated environments.
This module provides a tool for executing Python code either in a Docker container for
safe isolation or directly in a restricted sandbox. It includes mechanisms for blocking
potentially unsafe operations and importing restricted modules.
"""
import importlib.util
import os
import subprocess
import sys
from types import ModuleType
from typing import Any, ClassVar, TypedDict
from crewai.tools import BaseTool
from docker import ( # type: ignore[import-untyped]
DockerClient,
from_env as docker_from_env,
)
from docker.errors import ImageNotFound, NotFound # type: ignore[import-untyped]
from docker.models.containers import Container # type: ignore[import-untyped]
from pydantic import BaseModel, Field
from typing_extensions import Unpack
from crewai_tools.printer import Printer
class RunKwargs(TypedDict, total=False):
"""Keyword arguments for the _run method."""
code: str
libraries_used: list[str]
class CodeInterpreterSchema(BaseModel):
"""Schema for defining inputs to the CodeInterpreterTool.
This schema defines the required parameters for code execution,
including the code to run and any libraries that need to be installed.
"""
code: str = Field(
...,
description="Python3 code used to be interpreted in the Docker container. ALWAYS PRINT the final result and the output of the code",
)
libraries_used: list[str] = Field(
...,
description="List of libraries used in the code with proper installing names separated by commas. Example: numpy,pandas,beautifulsoup4",
)
class SandboxPython:
"""INSECURE: A restricted Python execution environment with known vulnerabilities.
WARNING: This class does NOT provide real security isolation and is vulnerable to
sandbox escape attacks via Python object introspection. Attackers can recover the
original __import__ function and bypass all restrictions.
DO NOT USE for untrusted code execution. Use Docker containers instead.
This class attempts to restrict access to dangerous modules and built-in functions
but provides no real security boundary against a motivated attacker.
"""
BLOCKED_MODULES: ClassVar[set[str]] = {
"os",
"sys",
"subprocess",
"shutil",
"importlib",
"inspect",
"tempfile",
"sysconfig",
"builtins",
}
UNSAFE_BUILTINS: ClassVar[set[str]] = {
"exec",
"eval",
"open",
"compile",
"input",
"globals",
"locals",
"vars",
"help",
"dir",
}
@staticmethod
def restricted_import(
name: str,
custom_globals: dict[str, Any] | None = None,
custom_locals: dict[str, Any] | None = None,
fromlist: list[str] | None = None,
level: int = 0,
) -> ModuleType:
"""A restricted import function that blocks importing of unsafe modules.
Args:
name: The name of the module to import.
custom_globals: Global namespace to use.
custom_locals: Local namespace to use.
fromlist: List of items to import from the module.
level: The level value passed to __import__.
Returns:
The imported module if allowed.
Raises:
ImportError: If the module is in the blocked modules list.
"""
if name in SandboxPython.BLOCKED_MODULES:
raise ImportError(f"Importing '{name}' is not allowed.")
return __import__(name, custom_globals, custom_locals, fromlist or (), level)
@staticmethod
def safe_builtins() -> dict[str, Any]:
"""Creates a dictionary of built-in functions with unsafe ones removed.
Returns:
A dictionary of safe built-in functions and objects.
"""
import builtins
safe_builtins = {
k: v
for k, v in builtins.__dict__.items()
if k not in SandboxPython.UNSAFE_BUILTINS
}
safe_builtins["__import__"] = SandboxPython.restricted_import
return safe_builtins
@staticmethod
def exec(code: str, locals_: dict[str, Any]) -> None:
"""Executes Python code in a restricted environment.
Args:
code: The Python code to execute as a string.
locals_: A dictionary that will be used for local variable storage.
"""
exec(code, {"__builtins__": SandboxPython.safe_builtins()}, locals_) # noqa: S102
class CodeInterpreterTool(BaseTool):
"""A tool for executing Python code in isolated environments.
This tool provides functionality to run Python code either in a Docker container
for safe isolation or directly in a restricted sandbox. It can handle installing
Python packages and executing arbitrary Python code.
"""
name: str = "Code Interpreter"
description: str = "Interprets Python3 code strings with a final print statement."
args_schema: type[BaseModel] = CodeInterpreterSchema
default_image_tag: str = "code-interpreter:latest"
code: str | None = None
user_dockerfile_path: str | None = None
user_docker_base_url: str | None = None
unsafe_mode: bool = False
@staticmethod
def _get_installed_package_path() -> str:
"""Gets the installation path of the crewai_tools package.
Returns:
The directory path where the package is installed.
Raises:
RuntimeError: If the package cannot be found.
"""
spec = importlib.util.find_spec("crewai_tools")
if spec is None or spec.origin is None:
raise RuntimeError("Cannot find crewai_tools package installation path")
return os.path.dirname(spec.origin)
def _verify_docker_image(self) -> None:
"""Verifies if the Docker image is available or builds it if necessary.
Checks if the required Docker image exists. If not, builds it using either a
user-provided Dockerfile or the default one included with the package.
Raises:
FileNotFoundError: If the Dockerfile cannot be found.
"""
client = (
docker_from_env()
if self.user_docker_base_url is None
else DockerClient(base_url=self.user_docker_base_url)
)
try:
client.images.get(self.default_image_tag)
except ImageNotFound:
if self.user_dockerfile_path and os.path.exists(self.user_dockerfile_path):
dockerfile_path = self.user_dockerfile_path
else:
package_path = self._get_installed_package_path()
dockerfile_path = os.path.join(
package_path, "tools/code_interpreter_tool"
)
if not os.path.exists(dockerfile_path):
raise FileNotFoundError(
f"Dockerfile not found in {dockerfile_path}"
) from None
client.images.build(
path=dockerfile_path,
tag=self.default_image_tag,
rm=True,
)
def _run(self, **kwargs: Unpack[RunKwargs]) -> str:
"""Runs the code interpreter tool with the provided arguments.
Args:
**kwargs: Keyword arguments that should include 'code' and 'libraries_used'.
Returns:
The output of the executed code as a string.
"""
code: str | None = kwargs.get("code", self.code)
libraries_used: list[str] = kwargs.get("libraries_used", [])
if not code:
return "No code provided to execute."
if self.unsafe_mode:
return self.run_code_unsafe(code, libraries_used)
return self.run_code_safety(code, libraries_used)
@staticmethod
def _install_libraries(container: Container, libraries: list[str]) -> None:
"""Installs required Python libraries in the Docker container.
Args:
container: The Docker container where libraries will be installed.
libraries: A list of library names to install using pip.
"""
for library in libraries:
container.exec_run(["pip", "install", library])
def _init_docker_container(self) -> Container:
"""Initializes and returns a Docker container for code execution.
Stops and removes any existing container with the same name before creating
a new one. Maps the current working directory to /workspace in the container.
Returns:
A Docker container object ready for code execution.
"""
container_name = "code-interpreter"
client = docker_from_env()
current_path = os.getcwd()
# Check if the container is already running
try:
existing_container = client.containers.get(container_name)
existing_container.stop()
existing_container.remove()
except NotFound:
pass # Container does not exist, no need to remove
return client.containers.run(
self.default_image_tag,
detach=True,
tty=True,
working_dir="/workspace",
name=container_name,
volumes={current_path: {"bind": "/workspace", "mode": "rw"}}, # type: ignore
)
@staticmethod
def _check_docker_available() -> bool:
"""Checks if Docker is available and running on the system.
Attempts to run the 'docker info' command to verify Docker availability.
Prints appropriate messages if Docker is not installed or not running.
Returns:
True if Docker is available and running, False otherwise.
"""
try:
subprocess.run(
["docker", "info"], # noqa: S607
check=True,
stdout=subprocess.DEVNULL,
stderr=subprocess.DEVNULL,
timeout=1,
)
return True
except (subprocess.CalledProcessError, subprocess.TimeoutExpired):
Printer.print(
"Docker is installed but not running or inaccessible.",
color="bold_purple",
)
return False
except FileNotFoundError:
Printer.print("Docker is not installed", color="bold_purple")
return False
def run_code_safety(self, code: str, libraries_used: list[str]) -> str:
"""Runs code in the safest available environment.
Requires Docker to be available for secure code execution. Fails closed
if Docker is not available to prevent sandbox escape vulnerabilities.
Args:
code: The Python code to execute as a string.
libraries_used: A list of Python library names to install before execution.
Returns:
The output of the executed code as a string.
Raises:
RuntimeError: If Docker is not available, as the restricted sandbox
is vulnerable to escape attacks and should not be used
for untrusted code execution.
"""
if self._check_docker_available():
return self.run_code_in_docker(code, libraries_used)
error_msg = (
"Docker is required for safe code execution but is not available. "
"The restricted sandbox fallback has been removed due to security vulnerabilities "
"that allow sandbox escape via Python object introspection. "
"Please install Docker (https://docs.docker.com/get-docker/) or use unsafe_mode=True "
"if you trust the code source and understand the security risks."
)
Printer.print(error_msg, color="bold_red")
raise RuntimeError(error_msg)
def run_code_in_docker(self, code: str, libraries_used: list[str]) -> str:
"""Runs Python code in a Docker container for safe isolation.
Creates a Docker container, installs the required libraries, executes the code,
and then cleans up by stopping and removing the container.
Args:
code: The Python code to execute as a string.
libraries_used: A list of Python library names to install before execution.
Returns:
The output of the executed code as a string, or an error message if execution failed.
"""
Printer.print("Running code in Docker environment", color="bold_blue")
self._verify_docker_image()
container = self._init_docker_container()
self._install_libraries(container, libraries_used)
exec_result = container.exec_run(["python3", "-c", code])
container.stop()
container.remove()
if exec_result.exit_code != 0:
return f"Something went wrong while running the code: \n{exec_result.output.decode('utf-8')}"
return exec_result.output.decode("utf-8")
@staticmethod
def run_code_in_restricted_sandbox(code: str) -> str:
"""DEPRECATED AND INSECURE: Runs Python code in a restricted sandbox environment.
WARNING: This method is vulnerable to sandbox escape attacks via Python object
introspection and should NOT be used for untrusted code execution. It has been
deprecated and is only kept for backward compatibility with trusted code.
The "restricted" environment can be bypassed by attackers who can:
- Use object graph introspection to recover the original __import__ function
- Access any Python module including os, subprocess, sys, etc.
- Execute arbitrary commands on the host system
Use run_code_in_docker() for secure code execution, or run_code_unsafe()
if you explicitly acknowledge the security risks.
Args:
code: The Python code to execute as a string.
Returns:
The value of the 'result' variable from the executed code,
or an error message if execution failed.
"""
Printer.print(
"WARNING: Running code in INSECURE restricted sandbox (vulnerable to escape attacks)",
color="bold_red"
)
exec_locals: dict[str, Any] = {}
try:
SandboxPython.exec(code=code, locals_=exec_locals)
return exec_locals.get("result", "No result variable found.")
except Exception as e:
return f"An error occurred: {e!s}"
@staticmethod
def run_code_unsafe(code: str, libraries_used: list[str]) -> str:
"""Runs code directly on the host machine without any safety restrictions.
WARNING: This mode is unsafe and should only be used in trusted environments
with code from trusted sources.
Args:
code: The Python code to execute as a string.
libraries_used: A list of Python library names to install before execution.
Returns:
The value of the 'result' variable from the executed code,
or an error message if execution failed.
"""
Printer.print("WARNING: Running code in unsafe mode", color="bold_magenta")
# Install libraries on the host machine
for library in libraries_used:
subprocess.run([sys.executable, "-m", "pip", "install", library], check=False) # noqa: S603
# Execute the code
try:
exec_locals: dict[str, Any] = {}
exec(code, {}, exec_locals) # noqa: S102
return exec_locals.get("result", "No result variable found.")
except Exception as e:
return f"An error occurred: {e!s}"

4
lib/crewai-tools/src/crewai_tools/tools/composio_tool/composio_tool.py
View File

@@ -10,7 +10,7 @@ import typing_extensions as te
class ComposioTool(BaseTool):
"""Wrapper for composio tools."""
composio_action: t.Callable
composio_action: t.Callable[..., t.Any]
env_vars: list[EnvVar] = Field(
default_factory=lambda: [
EnvVar(
@@ -70,7 +70,7 @@ class ComposioTool(BaseTool):
schema = action_schema.model_dump(exclude_none=True)
entity_id = kwargs.pop("entity_id", DEFAULT_ENTITY_ID)
def function(**kwargs: t.Any) -> dict:
def function(**kwargs: t.Any) -> dict[str, t.Any]:
"""Wrapper function for composio action."""
return toolset.execute_action(
action=Action(schema["name"]),

7
lib/crewai-tools/src/crewai_tools/tools/contextualai_create_agent_tool/contextual_create_agent_tool.py
View File

@@ -3,6 +3,8 @@ from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class ContextualAICreateAgentSchema(BaseModel):
"""Schema for contextual create agent tool."""
@@ -28,7 +30,7 @@ class ContextualAICreateAgentTool(BaseTool):
default_factory=lambda: ["contextual-client"]
)
def __init__(self, **kwargs):
def __init__(self, **kwargs: Any) -> None:
super().__init__(**kwargs)
try:
from contextual import ContextualAI
@@ -47,6 +49,7 @@ class ContextualAICreateAgentTool(BaseTool):
document_paths: list[str],
) -> str:
"""Create a complete RAG pipeline with documents."""
resolved_paths = [validate_file_path(doc_path) for doc_path in document_paths]
try:
import os
@@ -56,7 +59,7 @@ class ContextualAICreateAgentTool(BaseTool):
# Upload documents
document_ids = []
for doc_path in document_paths:
for doc_path in resolved_paths:
if not os.path.exists(doc_path):
raise FileNotFoundError(f"Document not found: {doc_path}")

3
lib/crewai-tools/src/crewai_tools/tools/contextualai_parse_tool/contextual_parse_tool.py
View File

@@ -1,6 +1,8 @@
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class ContextualAIParseSchema(BaseModel):
"""Schema for contextual parse tool."""
@@ -45,6 +47,7 @@ class ContextualAIParseTool(BaseTool):
"""Parse a document using Contextual AI's parser."""
if output_types is None:
output_types = ["markdown-per-page"]
file_path = validate_file_path(file_path)
try:
import json
import os

27
lib/crewai-tools/src/crewai_tools/tools/contextualai_query_tool/contextual_query_tool.py
View File

@@ -31,7 +31,7 @@ class ContextualAIQueryTool(BaseTool):
default_factory=lambda: ["contextual-client"]
)
def __init__(self, **kwargs):
def __init__(self, **kwargs: Any) -> None:
super().__init__(**kwargs)
try:
from contextual import ContextualAI
@@ -99,20 +99,19 @@ class ContextualAIQueryTool(BaseTool):
response = self.contextual_client.agents.query.create(
agent_id=agent_id, messages=[{"role": "user", "content": query}]
)
if hasattr(response, "content"):
return response.content
if hasattr(response, "message"):
content = getattr(response, "content", None)
if content is not None:
return str(content)
message = getattr(response, "message", None)
if message is not None:
msg_content = getattr(message, "content", None)
return str(msg_content) if msg_content is not None else str(message)
messages = getattr(response, "messages", None)
if messages and len(messages) > 0:
last_message = messages[-1]
last_content = getattr(last_message, "content", None)
return (
response.message.content
if hasattr(response.message, "content")
else str(response.message)
)
if hasattr(response, "messages") and len(response.messages) > 0:
last_message = response.messages[-1]
return (
last_message.content
if hasattr(last_message, "content")
else str(last_message)
str(last_content) if last_content is not None else str(last_message)
)
return str(response)
except Exception as e:

14
lib/crewai-tools/src/crewai_tools/tools/couchbase_tool/couchbase_tool.py
View File

@@ -15,11 +15,11 @@ try:
COUCHBASE_AVAILABLE = True
except ImportError:
COUCHBASE_AVAILABLE = False
search = Any
Cluster = Any
SearchOptions = Any
VectorQuery = Any
VectorSearch = Any
search = Any # type: ignore[assignment,unused-ignore]
Cluster = Any # type: ignore[assignment,unused-ignore]
SearchOptions = Any # type: ignore[assignment,unused-ignore]
VectorQuery = Any # type: ignore[assignment,unused-ignore]
VectorSearch = Any # type: ignore[assignment,unused-ignore]
from crewai.tools import BaseTool
from pydantic import BaseModel, ConfigDict, Field, SkipValidation
@@ -41,7 +41,7 @@ class CouchbaseFTSVectorSearchTool(BaseTool):
name: str = "CouchbaseFTSVectorSearchTool"
description: str = "A tool to search the Couchbase database for relevant information on internal documents."
args_schema: type[BaseModel] = CouchbaseToolSchema
cluster: SkipValidation[Cluster] = Field(
cluster: SkipValidation[Any] = Field(
description="An instance of the Couchbase Cluster connected to the desired Couchbase server.",
)
collection_name: str = Field(
@@ -136,7 +136,7 @@ class CouchbaseFTSVectorSearchTool(BaseTool):
return True
def __init__(self, **kwargs):
def __init__(self, **kwargs: Any) -> None:
"""Initialize the CouchbaseFTSVectorSearchTool.
Args:

6
lib/crewai-tools/src/crewai_tools/tools/csv_search_tool/csv_search_tool.py
View File

@@ -1,3 +1,5 @@
from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.rag.data_types import DataType
@@ -26,7 +28,7 @@ class CSVSearchTool(RagTool):
)
args_schema: type[BaseModel] = CSVSearchToolSchema
def __init__(self, csv: str | None = None, **kwargs):
def __init__(self, csv: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
if csv is not None:
self.add(csv)
@@ -34,7 +36,7 @@ class CSVSearchTool(RagTool):
self.args_schema = FixedCSVSearchToolSchema
self._generate_description()
def add(self, csv: str) -> None:
def add(self, csv: str) -> None: # type: ignore[override]
super().add(csv, data_type=DataType.CSV)
def _run( # type: ignore[override]

12
lib/crewai-tools/src/crewai_tools/tools/dalle_tool/dalle_tool.py
View File

@@ -1,8 +1,8 @@
import json
from typing import Literal
from typing import Any, Literal
from crewai.tools import BaseTool, EnvVar
from openai import Omit, OpenAI
from openai import OpenAI
from pydantic import BaseModel, Field
@@ -33,9 +33,9 @@ class DallETool(BaseTool):
]
| None
) = "1024x1024"
quality: (
Literal["standard", "hd", "low", "medium", "high", "auto"] | None | Omit
) = "standard"
quality: Literal["standard", "hd", "low", "medium", "high", "auto"] | None = (
"standard"
)
n: int = 1
env_vars: list[EnvVar] = Field(
@@ -48,7 +48,7 @@ class DallETool(BaseTool):
]
)
def _run(self, **kwargs) -> str:
def _run(self, **kwargs: Any) -> str:
client = OpenAI()
image_description = kwargs.get("image_description")

5
lib/crewai-tools/src/crewai_tools/tools/directory_read_tool/directory_read_tool.py
View File

@@ -4,6 +4,8 @@ from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_directory_path
class FixedDirectoryReadToolSchema(BaseModel):
"""Input for DirectoryReadTool."""
@@ -23,7 +25,7 @@ class DirectoryReadTool(BaseTool):
args_schema: type[BaseModel] = DirectoryReadToolSchema
directory: str | None = None
def __init__(self, directory: str | None = None, **kwargs):
def __init__(self, directory: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
if directory is not None:
self.directory = directory
@@ -39,6 +41,7 @@ class DirectoryReadTool(BaseTool):
if directory is None:
raise ValueError("Directory must be provided.")
directory = validate_directory_path(directory)
if directory[-1] == "/":
directory = directory[:-1]
files_list = [

8
lib/crewai-tools/src/crewai_tools/tools/directory_search_tool/directory_search_tool.py
View File

@@ -1,6 +1,9 @@
from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.rag.data_types import DataType
from crewai_tools.security.safe_path import validate_directory_path
from crewai_tools.tools.rag.rag_tool import RagTool
@@ -26,7 +29,7 @@ class DirectorySearchTool(RagTool):
)
args_schema: type[BaseModel] = DirectorySearchToolSchema
def __init__(self, directory: str | None = None, **kwargs):
def __init__(self, directory: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
if directory is not None:
self.add(directory)
@@ -34,7 +37,8 @@ class DirectorySearchTool(RagTool):
self.args_schema = FixedDirectorySearchToolSchema
self._generate_description()
def add(self, directory: str) -> None:
def add(self, directory: str) -> None: # type: ignore[override]
directory = validate_directory_path(directory)
super().add(directory, data_type=DataType.DIRECTORY)
def _run( # type: ignore[override]

4
lib/crewai-tools/src/crewai_tools/tools/docx_search_tool/docx_search_tool.py
View File

@@ -34,7 +34,7 @@ class DOCXSearchTool(RagTool):
)
args_schema: type[BaseModel] = DOCXSearchToolSchema
def __init__(self, docx: str | None = None, **kwargs):
def __init__(self, docx: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
if docx is not None:
self.add(docx)
@@ -42,7 +42,7 @@ class DOCXSearchTool(RagTool):
self.args_schema = FixedDOCXSearchToolSchema
self._generate_description()
def add(self, docx: str) -> None:
def add(self, docx: str) -> None: # type: ignore[override]
super().add(docx, data_type=DataType.DOCX)
def _run( # type: ignore[override]

4
lib/crewai-tools/src/crewai_tools/tools/exa_tools/exa_search_tool.py
View File

@@ -71,8 +71,8 @@ class EXASearchTool(BaseTool):
content: bool | None = False,
summary: bool | None = False,
type: str | None = "auto",
**kwargs,
):
**kwargs: Any,
) -> None:
super().__init__(
**kwargs,
)

3
lib/crewai-tools/src/crewai_tools/tools/file_read_tool/file_read_tool.py
View File

@@ -3,6 +3,8 @@ from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class FileReadToolSchema(BaseModel):
"""Input for FileReadTool."""
@@ -76,6 +78,7 @@ class FileReadTool(BaseTool):
if file_path is None:
return "Error: No file path provided. Please provide a file path either in the constructor or as an argument."
file_path = validate_file_path(file_path)
try:
with open(file_path, "r") as file:
if start_line == 1 and line_count is None:

44
lib/crewai-tools/src/crewai_tools/tools/file_writer_tool/file_writer_tool.py
View File

@@ -1,11 +1,12 @@
import os
from pathlib import Path
from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel
def strtobool(val) -> bool:
def strtobool(val: str | bool) -> bool:
if isinstance(val, bool):
return val
val = val.lower()
@@ -30,28 +31,41 @@ class FileWriterTool(BaseTool):
def _run(self, **kwargs: Any) -> str:
try:
directory = kwargs.get("directory") or "./"
filename = kwargs["filename"]
filepath = os.path.join(directory, filename)
# Prevent path traversal: the resolved path must be strictly inside
# the resolved directory. This blocks ../sequences, absolute paths in
# filename, and symlink escapes regardless of how directory is set.
# is_relative_to() does a proper path-component comparison that is
# safe on case-insensitive filesystems and avoids the "// " edge case
# that plagues startswith(real_directory + os.sep).
# We also reject the case where filepath resolves to the directory
# itself, since that is not a valid file target.
real_directory = Path(directory).resolve()
real_filepath = Path(filepath).resolve()
if (
not real_filepath.is_relative_to(real_directory)
or real_filepath == real_directory
):
return "Error: Invalid file path — the filename must not escape the target directory."
if kwargs.get("directory"):
os.makedirs(kwargs["directory"], exist_ok=True)
os.makedirs(real_directory, exist_ok=True)
# Construct the full path
filepath = os.path.join(kwargs.get("directory") or "", kwargs["filename"])
# Convert overwrite to boolean
kwargs["overwrite"] = strtobool(kwargs["overwrite"])
# Check if file exists and overwrite is not allowed
if os.path.exists(filepath) and not kwargs["overwrite"]:
return f"File {filepath} already exists and overwrite option was not passed."
if os.path.exists(real_filepath) and not kwargs["overwrite"]:
return f"File {real_filepath} already exists and overwrite option was not passed."
# Write content to the file
mode = "w" if kwargs["overwrite"] else "x"
with open(filepath, mode) as file:
with open(real_filepath, mode) as file:
file.write(kwargs["content"])
return f"Content successfully written to {filepath}"
return f"Content successfully written to {real_filepath}"
except FileExistsError:
return (
f"File {filepath} already exists and overwrite option was not passed."
)
return f"File {real_filepath} already exists and overwrite option was not passed."
except KeyError as e:
return f"An error occurred while accessing key: {e!s}"
except Exception as e:

9
lib/crewai-tools/src/crewai_tools/tools/files_compressor_tool/files_compressor_tool.py
View File

@@ -5,6 +5,8 @@ import zipfile
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class FileCompressorToolInput(BaseModel):
"""Input schema for FileCompressorTool."""
@@ -40,12 +42,15 @@ class FileCompressorTool(BaseTool):
overwrite: bool = False,
format: str = "zip",
) -> str:
input_path = validate_file_path(input_path)
if not os.path.exists(input_path):
return f"Input path '{input_path}' does not exist."
if not output_path:
output_path = self._generate_output_path(input_path, format)
output_path = validate_file_path(output_path)
format_extension = {
"zip": ".zip",
"tar": ".tar",
@@ -106,7 +111,7 @@ class FileCompressorTool(BaseTool):
return True
@staticmethod
def _compress_zip(input_path: str, output_path: str):
def _compress_zip(input_path: str, output_path: str) -> None:
"""Compresses input into a zip archive."""
with zipfile.ZipFile(output_path, "w", zipfile.ZIP_DEFLATED) as zipf:
if os.path.isfile(input_path):
@@ -119,7 +124,7 @@ class FileCompressorTool(BaseTool):
zipf.write(full_path, arcname)
@staticmethod
def _compress_tar(input_path: str, output_path: str, format: str):
def _compress_tar(input_path: str, output_path: str, format: str) -> None:
"""Compresses input into a tar archive with the given format."""
format_mode = {
"tar": "w",

23
lib/crewai-tools/src/crewai_tools/tools/firecrawl_crawl_website_tool/firecrawl_crawl_website_tool.py
View File

@@ -1,13 +1,12 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from typing import Any
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, ConfigDict, Field, PrivateAttr
from crewai_tools.security.safe_path import validate_url
if TYPE_CHECKING:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
try:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
@@ -63,7 +62,7 @@ class FirecrawlCrawlWebsiteTool(BaseTool):
},
}
)
_firecrawl: FirecrawlApp | None = PrivateAttr(None)
_firecrawl: Any = PrivateAttr(None)
package_dependencies: list[str] = Field(default_factory=lambda: ["firecrawl-py"])
env_vars: list[EnvVar] = Field(
default_factory=lambda: [
@@ -75,14 +74,14 @@ class FirecrawlCrawlWebsiteTool(BaseTool):
]
)
def __init__(self, api_key: str | None = None, **kwargs):
def __init__(self, api_key: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.api_key = api_key
self._initialize_firecrawl()
def _initialize_firecrawl(self) -> None:
try:
from firecrawl import FirecrawlApp # type: ignore
from firecrawl import FirecrawlApp
self._firecrawl = FirecrawlApp(api_key=self.api_key)
except ImportError:
@@ -105,21 +104,19 @@ class FirecrawlCrawlWebsiteTool(BaseTool):
"`firecrawl-py` package not found, please run `uv add firecrawl-py`"
) from None
def _run(self, url: str):
def _run(self, url: str) -> Any:
if not self._firecrawl:
raise RuntimeError("FirecrawlApp not properly initialized")
url = validate_url(url)
return self._firecrawl.crawl(url=url, poll_interval=2, **self.config)
try:
from firecrawl import FirecrawlApp
from firecrawl import FirecrawlApp # noqa: F401
# Only rebuild if the class hasn't been initialized yet
if not hasattr(FirecrawlCrawlWebsiteTool, "_model_rebuilt"):
if not getattr(FirecrawlCrawlWebsiteTool, "_model_rebuilt", False):
FirecrawlCrawlWebsiteTool.model_rebuild()
FirecrawlCrawlWebsiteTool._model_rebuilt = True # type: ignore[attr-defined]
except ImportError:
"""
When this tool is not used, then exception can be ignored.
"""
pass

23
lib/crewai-tools/src/crewai_tools/tools/firecrawl_scrape_website_tool/firecrawl_scrape_website_tool.py
View File

@@ -1,13 +1,12 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from typing import Any
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, ConfigDict, Field, PrivateAttr
from crewai_tools.security.safe_path import validate_url
if TYPE_CHECKING:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
try:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
@@ -70,7 +69,7 @@ class FirecrawlScrapeWebsiteTool(BaseTool):
}
)
_firecrawl: FirecrawlApp | None = PrivateAttr(None)
_firecrawl: Any = PrivateAttr(None)
package_dependencies: list[str] = Field(default_factory=lambda: ["firecrawl-py"])
env_vars: list[EnvVar] = Field(
default_factory=lambda: [
@@ -82,10 +81,10 @@ class FirecrawlScrapeWebsiteTool(BaseTool):
]
)
def __init__(self, api_key: str | None = None, **kwargs):
def __init__(self, api_key: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
try:
from firecrawl import FirecrawlApp # type: ignore
from firecrawl import FirecrawlApp
except ImportError:
import click
@@ -105,21 +104,19 @@ class FirecrawlScrapeWebsiteTool(BaseTool):
self._firecrawl = FirecrawlApp(api_key=api_key)
def _run(self, url: str):
def _run(self, url: str) -> Any:
if not self._firecrawl:
raise RuntimeError("FirecrawlApp not properly initialized")
url = validate_url(url)
return self._firecrawl.scrape(url=url, **self.config)
try:
from firecrawl import FirecrawlApp
from firecrawl import FirecrawlApp # noqa: F401
# Must rebuild model after class is defined
if not hasattr(FirecrawlScrapeWebsiteTool, "_model_rebuilt"):
if not getattr(FirecrawlScrapeWebsiteTool, "_model_rebuilt", False):
FirecrawlScrapeWebsiteTool.model_rebuild()
FirecrawlScrapeWebsiteTool._model_rebuilt = True # type: ignore[attr-defined]
except ImportError:
"""
When this tool is not used, then exception can be ignored.
"""
pass

21
lib/crewai-tools/src/crewai_tools/tools/firecrawl_search_tool/firecrawl_search_tool.py
View File

@@ -1,15 +1,11 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from typing import Any
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, ConfigDict, Field, PrivateAttr
if TYPE_CHECKING:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
try:
from firecrawl import FirecrawlApp # type: ignore[import-untyped]
@@ -65,7 +61,7 @@ class FirecrawlSearchTool(BaseTool):
},
}
)
_firecrawl: FirecrawlApp | None = PrivateAttr(None)
_firecrawl: Any = PrivateAttr(None)
package_dependencies: list[str] = Field(default_factory=lambda: ["firecrawl-py"])
env_vars: list[EnvVar] = Field(
default_factory=lambda: [
@@ -77,14 +73,14 @@ class FirecrawlSearchTool(BaseTool):
]
)
def __init__(self, api_key: str | None = None, **kwargs):
def __init__(self, api_key: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.api_key = api_key
self._initialize_firecrawl()
def _initialize_firecrawl(self) -> None:
try:
from firecrawl import FirecrawlApp # type: ignore
from firecrawl import FirecrawlApp
self._firecrawl = FirecrawlApp(api_key=self.api_key)
except ImportError:
@@ -121,13 +117,10 @@ class FirecrawlSearchTool(BaseTool):
try:
from firecrawl import FirecrawlApp # type: ignore
from firecrawl import FirecrawlApp # noqa: F401
# Only rebuild if the class hasn't been initialized yet
if not hasattr(FirecrawlSearchTool, "_model_rebuilt"):
if not getattr(FirecrawlSearchTool, "_model_rebuilt", False):
FirecrawlSearchTool.model_rebuild()
FirecrawlSearchTool._model_rebuilt = True # type: ignore[attr-defined]
except ImportError:
"""
When this tool is not used, then exception can be ignored.
"""
pass

5
lib/crewai-tools/src/crewai_tools/tools/generate_crewai_automation_tool/generate_crewai_automation_tool.py
View File

@@ -1,4 +1,5 @@
import os
from typing import Any
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, Field
@@ -46,7 +47,7 @@ class GenerateCrewaiAutomationTool(BaseTool):
]
)
def _run(self, **kwargs) -> str:
def _run(self, **kwargs: Any) -> str:
input_data = GenerateCrewaiAutomationToolSchema(**kwargs)
response = requests.post( # noqa: S113
f"{self.crewai_enterprise_url}/crewai_plus/api/v1/studio",
@@ -58,7 +59,7 @@ class GenerateCrewaiAutomationTool(BaseTool):
studio_project_url = response.json().get("url")
return f"Generated CrewAI Studio project URL: {studio_project_url}"
def _get_headers(self, organization_id: str | None = None) -> dict:
def _get_headers(self, organization_id: str | None = None) -> dict[str, str]:
headers = {
"Authorization": f"Bearer {self.personal_access_token}",
"Content-Type": "application/json",

8
lib/crewai-tools/src/crewai_tools/tools/github_search_tool/github_search_tool.py
View File

@@ -1,3 +1,5 @@
from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.rag.data_types import DataType
@@ -38,8 +40,8 @@ class GithubSearchTool(RagTool):
self,
github_repo: str | None = None,
content_types: list[str] | None = None,
**kwargs,
):
**kwargs: Any,
) -> None:
super().__init__(**kwargs)
if github_repo and content_types:
@@ -48,7 +50,7 @@ class GithubSearchTool(RagTool):
self.args_schema = FixedGithubSearchToolSchema
self._generate_description()
def add(
def add( # type: ignore[override]
self,
repo: str,
content_types: list[str] | None = None,

17
lib/crewai-tools/src/crewai_tools/tools/hyperbrowser_load_tool/hyperbrowser_load_tool.py
View File

@@ -4,13 +4,15 @@ from typing import Any, Literal
from crewai.tools import BaseTool, EnvVar
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_url
class HyperbrowserLoadToolSchema(BaseModel):
url: str = Field(description="Website URL")
operation: Literal["scrape", "crawl"] = Field(
description="Operation to perform on the website. Either 'scrape' or 'crawl'"
)
params: dict | None = Field(
params: dict[str, Any] | None = Field(
description="Optional params for scrape or crawl. For more information on the supported params, visit https://docs.hyperbrowser.ai/reference/sdks/python/scrape#start-scrape-job-and-wait or https://docs.hyperbrowser.ai/reference/sdks/python/crawl#start-crawl-job-and-wait"
)
@@ -42,7 +44,7 @@ class HyperbrowserLoadTool(BaseTool):
]
)
def __init__(self, api_key: str | None = None, **kwargs):
def __init__(self, api_key: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.api_key = api_key or os.getenv("HYPERBROWSER_API_KEY")
if not api_key:
@@ -65,7 +67,7 @@ class HyperbrowserLoadTool(BaseTool):
self.hyperbrowser = Hyperbrowser(api_key=self.api_key)
@staticmethod
def _prepare_params(params: dict) -> dict:
def _prepare_params(params: dict[str, Any]) -> dict[str, Any]:
"""Prepare session and scrape options parameters."""
try:
from hyperbrowser.models.scrape import ( # type: ignore[import-untyped]
@@ -91,7 +93,7 @@ class HyperbrowserLoadTool(BaseTool):
params["scrape_options"] = ScrapeOptions(**params["scrape_options"])
return params
def _extract_content(self, data: Any | None):
def _extract_content(self, data: Any | None) -> str:
"""Extract content from response data."""
content = ""
if data:
@@ -102,15 +104,15 @@ class HyperbrowserLoadTool(BaseTool):
self,
url: str,
operation: Literal["scrape", "crawl"] = "scrape",
params: dict | None = None,
):
params: dict[str, Any] | None = None,
) -> str:
if params is None:
params = {}
try:
from hyperbrowser.models.crawl import ( # type: ignore[import-untyped]
StartCrawlJobParams,
)
from hyperbrowser.models.scrape import ( # type: ignore[import-untyped]
from hyperbrowser.models.scrape import (
StartScrapeJobParams,
)
except ImportError as e:
@@ -119,6 +121,7 @@ class HyperbrowserLoadTool(BaseTool):
) from e
params = self._prepare_params(params)
url = validate_url(url)
if operation == "scrape":
scrape_params = StartScrapeJobParams(url=url, **params)

10
lib/crewai-tools/src/crewai_tools/tools/invoke_crewai_automation_tool/invoke_crewai_automation_tool.py
View File

@@ -134,7 +134,8 @@ class InvokeCrewAIAutomationTool(BaseTool):
json={"inputs": inputs},
timeout=30,
)
return response.json()
result: dict[str, Any] = response.json()
return result
def _get_crew_status(self, crew_id: str) -> dict[str, Any]:
"""Get the status of a crew task.
@@ -153,9 +154,10 @@ class InvokeCrewAIAutomationTool(BaseTool):
},
timeout=30,
)
return response.json()
result: dict[str, Any] = response.json()
return result
def _run(self, **kwargs) -> str:
def _run(self, **kwargs: Any) -> str:
"""Execute the crew invocation tool."""
if kwargs is None:
kwargs = {}
@@ -172,7 +174,7 @@ class InvokeCrewAIAutomationTool(BaseTool):
try:
status_response = self._get_crew_status(crew_id=kickoff_id)
if status_response.get("state", "").lower() == "success":
return status_response.get("result", "No result returned")
return str(status_response.get("result", "No result returned"))
if status_response.get("state", "").lower() == "failed":
return f"Error: Crew task failed. Response: {status_response}"
except Exception as e:

11
lib/crewai-tools/src/crewai_tools/tools/jina_scrape_website_tool/jina_scrape_website_tool.py
View File

@@ -1,7 +1,11 @@
from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
import requests
from crewai_tools.security.safe_path import validate_url
class JinaScrapeWebsiteToolInput(BaseModel):
"""Input schema for JinaScrapeWebsiteTool."""
@@ -15,14 +19,14 @@ class JinaScrapeWebsiteTool(BaseTool):
args_schema: type[BaseModel] = JinaScrapeWebsiteToolInput
website_url: str | None = None
api_key: str | None = None
headers: dict = Field(default_factory=dict)
headers: dict[str, str] = Field(default_factory=dict)
def __init__(
self,
website_url: str | None = None,
api_key: str | None = None,
custom_headers: dict | None = None,
**kwargs,
custom_headers: dict[str, str] | None = None,
**kwargs: Any,
):
super().__init__(**kwargs)
if website_url is not None:
@@ -43,6 +47,7 @@ class JinaScrapeWebsiteTool(BaseTool):
"Website URL must be provided either during initialization or execution"
)
url = validate_url(url)
response = requests.get(
f"https://r.jina.ai/{url}", headers=self.headers, timeout=15
)

4
lib/crewai-tools/src/crewai_tools/tools/json_search_tool/json_search_tool.py
View File

@@ -1,3 +1,5 @@
from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.tools.rag.rag_tool import RagTool
@@ -27,7 +29,7 @@ class JSONSearchTool(RagTool):
)
args_schema: type[BaseModel] = JSONSearchToolSchema
def __init__(self, json_path: str | None = None, **kwargs):
def __init__(self, json_path: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
if json_path is not None:
self.add(json_path)

4
lib/crewai-tools/src/crewai_tools/tools/linkup/linkup_search_tool.py
View File

@@ -20,7 +20,7 @@ class LinkupSearchTool(BaseTool):
description: str = (
"Performs an API call to Linkup to retrieve contextual information."
)
_client: LinkupClient = PrivateAttr() # type: ignore
_client: Any = PrivateAttr()
package_dependencies: list[str] = Field(default_factory=lambda: ["linkup-sdk"])
env_vars: list[EnvVar] = Field(
default_factory=lambda: [
@@ -60,7 +60,7 @@ class LinkupSearchTool(BaseTool):
output_type: Literal[
"searchResults", "sourcedAnswer", "structured"
] = "searchResults",
) -> dict:
) -> dict[str, Any]:
"""Executes a search using the Linkup API.
:param query: The query to search for.

11
lib/crewai-tools/src/crewai_tools/tools/llamaindex_tool/llamaindex_tool.py
View File

@@ -17,11 +17,7 @@ class LlamaIndexTool(BaseTool):
**kwargs: Any,
) -> Any:
"""Run tool."""
from llama_index.core.tools import ( # type: ignore[import-not-found]
BaseTool as LlamaBaseTool,
)
tool = cast(LlamaBaseTool, self.llama_index_tool)
tool = self.llama_index_tool
if self.result_as_answer:
return tool(*args, **kwargs).content
@@ -36,7 +32,6 @@ class LlamaIndexTool(BaseTool):
if not isinstance(tool, LlamaBaseTool):
raise ValueError(f"Expected a LlamaBaseTool, got {type(tool)}")
tool = cast(LlamaBaseTool, tool)
if tool.metadata.fn_schema is None:
raise ValueError(
@@ -64,9 +59,7 @@ class LlamaIndexTool(BaseTool):
from llama_index.core.query_engine import ( # type: ignore[import-not-found]
BaseQueryEngine,
)
from llama_index.core.tools import ( # type: ignore[import-not-found]
QueryEngineTool,
)
from llama_index.core.tools import QueryEngineTool
if not isinstance(query_engine, BaseQueryEngine):
raise ValueError(f"Expected a BaseQueryEngine, got {type(query_engine)}")

6
lib/crewai-tools/src/crewai_tools/tools/mdx_search_tool/mdx_search_tool.py
View File

@@ -1,3 +1,5 @@
from typing import Any
from pydantic import BaseModel, Field
from crewai_tools.rag.data_types import DataType
@@ -26,7 +28,7 @@ class MDXSearchTool(RagTool):
)
args_schema: type[BaseModel] = MDXSearchToolSchema
def __init__(self, mdx: str | None = None, **kwargs):
def __init__(self, mdx: str | None = None, **kwargs: Any) -> None:
super().__init__(**kwargs)
if mdx is not None:
self.add(mdx)
@@ -34,7 +36,7 @@ class MDXSearchTool(RagTool):
self.args_schema = FixedMDXSearchToolSchema
self._generate_description()
def add(self, mdx: str) -> None:
def add(self, mdx: str) -> None: # type: ignore[override]
super().add(mdx, data_type=DataType.MDX)
def _run( # type: ignore[override]

10
lib/crewai-tools/src/crewai_tools/tools/merge_agent_handler_tool/merge_agent_handler_tool.py
View File

@@ -2,7 +2,7 @@
import json
import logging
from typing import Any
from typing import Any, cast
from uuid import uuid4
from crewai.tools import BaseTool, EnvVar
@@ -108,7 +108,7 @@ class MergeAgentHandlerTool(BaseTool):
)
raise MergeAgentHandlerToolError(f"API Error: {error_msg}")
return result
return cast(dict[str, Any], result)
except requests.exceptions.RequestException as e:
logger.error(f"Failed to call Agent Handler API: {e!s}")
@@ -219,8 +219,8 @@ class MergeAgentHandlerTool(BaseTool):
required = params.get("required", [])
for field_name, field_schema in properties.items():
field_type = Any # Default type
field_default = ... # Required by default
field_type: Any = Any
field_default: Any = ...
# Map JSON schema types to Python types
json_type = field_schema.get("type", "string")
@@ -256,7 +256,7 @@ class MergeAgentHandlerTool(BaseTool):
# Create the Pydantic model
if fields:
args_schema = create_model(
args_schema = create_model( # type: ignore[call-overload]
f"{tool_name.replace('__', '_').title()}Args",
**fields,
)

8
lib/crewai-tools/src/crewai_tools/tools/mongodb_vector_search_tool/utils.py
View File

@@ -6,7 +6,7 @@ from typing import TYPE_CHECKING, Any
if TYPE_CHECKING:
from pymongo.collection import Collection
from pymongo.collection import Collection as MongoCollection
def _vector_search_index_definition(
@@ -34,7 +34,7 @@ def _vector_search_index_definition(
def create_vector_search_index(
collection: Collection,
collection: MongoCollection[Any],
index_name: str,
dimensions: int,
path: str,
@@ -84,7 +84,7 @@ def create_vector_search_index(
)
def _is_index_ready(collection: Collection, index_name: str) -> bool:
def _is_index_ready(collection: MongoCollection[Any], index_name: str) -> bool:
"""Check for the index name in the list of available search indexes to see if the
specified index is of status READY.
@@ -102,7 +102,7 @@ def _is_index_ready(collection: Collection, index_name: str) -> bool:
def _wait_for_predicate(
predicate: Callable, err: str, timeout: float = 120, interval: float = 0.5
predicate: Callable[[], bool], err: str, timeout: float = 120, interval: float = 0.5
) -> None:
"""Generic to block until the predicate returns true.

21
lib/crewai-tools/src/crewai_tools/tools/mongodb_vector_search_tool/vector_search.py
View File

@@ -31,7 +31,7 @@ class MongoDBVectorSearchConfig(BaseModel):
default=None,
description="List of MQL match expressions comparing an indexed field",
)
post_filter_pipeline: list[dict] | None = Field(
post_filter_pipeline: list[dict[str, Any]] | None = Field(
default=None,
description="Pipeline of MongoDB aggregation stages to filter/process results after $vectorSearch.",
)
@@ -105,7 +105,7 @@ class MongoDBVectorSearchTool(BaseTool):
)
package_dependencies: list[str] = Field(default_factory=lambda: ["mongdb"])
def __init__(self, **kwargs):
def __init__(self, **kwargs: Any) -> None:
super().__init__(**kwargs)
if not MONGODB_AVAILABLE:
import click
@@ -120,6 +120,7 @@ class MongoDBVectorSearchTool(BaseTool):
else:
raise ImportError("You are missing the 'mongodb' crewai tool.")
self._openai_client: AzureOpenAI | Client
if "AZURE_OPENAI_ENDPOINT" in os.environ:
self._openai_client = AzureOpenAI()
elif "OPENAI_API_KEY" in os.environ:
@@ -132,7 +133,7 @@ class MongoDBVectorSearchTool(BaseTool):
from pymongo import MongoClient
from pymongo.driver_info import DriverInfo
self._client = MongoClient(
self._client: MongoClient[dict[str, Any]] = MongoClient(
self.connection_string,
driver=DriverInfo(name="CrewAI", version=version("crewai-tools")),
)
@@ -236,7 +237,7 @@ class MongoDBVectorSearchTool(BaseTool):
def _bulk_embed_and_insert_texts(
self,
texts: list[str],
metadatas: list[dict],
metadatas: list[dict[str, Any]],
ids: list[str],
) -> list[str]:
"""Bulk insert single batch of texts, embeddings, and ids."""
@@ -315,16 +316,18 @@ class MongoDBVectorSearchTool(BaseTool):
logger.error(f"Error: {e}")
return ""
def __del__(self):
def __del__(self) -> None:
"""Cleanup clients on deletion."""
try:
if hasattr(self, "_client") and self._client:
self._client.close()
client: Any = getattr(self, "_client", None)
if client is not None:
client.close()
except Exception as e:
logger.error(f"Error: {e}")
try:
if hasattr(self, "_openai_client") and self._openai_client:
self._openai_client.close()
openai_client: Any = getattr(self, "_openai_client", None)
if openai_client is not None:
openai_client.close()
except Exception as e:
logger.error(f"Error: {e}")

6
lib/crewai-tools/src/crewai_tools/tools/multion_tool/multion_tool.py
View File

@@ -31,11 +31,11 @@ class MultiOnTool(BaseTool):
def __init__(
self,
api_key: str | None = None,
**kwargs,
**kwargs: Any,
):
super().__init__(**kwargs)
try:
from multion.client import MultiOn # type: ignore
from multion.client import MultiOn
except ImportError:
import click
@@ -78,4 +78,4 @@ class MultiOnTool(BaseTool):
)
self.session_id = browse.session_id
return browse.message + "\n\n STATUS: " + browse.status
return str(browse.message) + "\n\n STATUS: " + str(browse.status)

4
lib/crewai-tools/src/crewai_tools/tools/mysql_search_tool/mysql_search_tool.py
View File

@@ -21,13 +21,13 @@ class MySQLSearchTool(RagTool):
args_schema: type[BaseModel] = MySQLSearchToolSchema
db_uri: str = Field(..., description="Mandatory database URI")
def __init__(self, table_name: str, **kwargs):
def __init__(self, table_name: str, **kwargs: Any) -> None:
super().__init__(**kwargs)
self.add(table_name, data_type=DataType.MYSQL, metadata={"db_uri": self.db_uri})
self.description = f"A tool that can be used to semantic search a query the {table_name} database table's content."
self._generate_description()
def add(
def add( # type: ignore[override]
self,
table_name: str,
**kwargs: Any,

455
lib/crewai-tools/src/crewai_tools/tools/nl2sql/nl2sql_tool.py
View File

@@ -1,7 +1,17 @@
from collections.abc import Iterator
import logging
import os
import re
from typing import Any
try:
from typing import Self
except ImportError:
from typing_extensions import Self
from crewai.tools import BaseTool
from pydantic import BaseModel, Field
from pydantic import BaseModel, Field, model_validator
try:
@@ -12,6 +22,186 @@ try:
except ImportError:
SQLALCHEMY_AVAILABLE = False
logger = logging.getLogger(__name__)
# Commands allowed in read-only mode
# NOTE: WITH is intentionally excluded — writable CTEs start with WITH, so the
# CTE body must be inspected separately (see _validate_statement).
_READ_ONLY_COMMANDS = {"SELECT", "SHOW", "DESCRIBE", "DESC", "EXPLAIN"}
# Commands that mutate state and are blocked by default
_WRITE_COMMANDS = {
"INSERT",
"UPDATE",
"DELETE",
"DROP",
"ALTER",
"CREATE",
"TRUNCATE",
"GRANT",
"REVOKE",
"EXEC",
"EXECUTE",
"CALL",
"MERGE",
"REPLACE",
"UPSERT",
"LOAD",
"COPY",
"VACUUM",
"ANALYZE",
"ANALYSE",
"REINDEX",
"CLUSTER",
"REFRESH",
"COMMENT",
"SET",
"RESET",
}
# Subset of write commands that can realistically appear *inside* a CTE body.
# Narrower than _WRITE_COMMANDS to avoid false positives on identifiers like
# ``comment``, ``set``, or ``reset`` which are common column/table names.
_CTE_WRITE_INDICATORS = {
"INSERT",
"UPDATE",
"DELETE",
"DROP",
"ALTER",
"CREATE",
"TRUNCATE",
"MERGE",
}
_AS_PAREN_RE = re.compile(r"\bAS\s*\(", re.IGNORECASE)
def _iter_as_paren_matches(stmt: str) -> Iterator[re.Match[str]]:
"""Yield regex matches for ``AS\\s*(`` outside of string literals."""
# Build a set of character positions that are inside string literals.
in_string: set[int] = set()
i = 0
while i < len(stmt):
if stmt[i] == "'":
start = i
end = _skip_string_literal(stmt, i)
in_string.update(range(start, end))
i = end
else:
i += 1
for m in _AS_PAREN_RE.finditer(stmt):
if m.start() not in in_string:
yield m
def _detect_writable_cte(stmt: str) -> str | None:
"""Return the first write command inside a CTE body, or None.
Instead of tokenizing the whole statement (which falsely matches column
names like ``comment``), this walks through parenthesized CTE bodies and
checks only the *first keyword after* an opening ``AS (`` for a write
command. Uses a regex to handle any whitespace (spaces, tabs, newlines)
between ``AS`` and ``(``. Skips matches inside string literals.
"""
for m in _iter_as_paren_matches(stmt):
body = stmt[m.end() :].lstrip()
first_word = body.split()[0].upper().strip("()") if body.split() else ""
if first_word in _CTE_WRITE_INDICATORS:
return first_word
return None
def _skip_string_literal(stmt: str, pos: int) -> int:
"""Skip past a string literal starting at pos (single-quoted).
Handles escaped quotes ('') inside the literal.
Returns the index after the closing quote.
"""
quote_char = stmt[pos]
i = pos + 1
while i < len(stmt):
if stmt[i] == quote_char:
# Check for escaped quote ('')
if i + 1 < len(stmt) and stmt[i + 1] == quote_char:
i += 2
continue
return i + 1
i += 1
return i # Unterminated literal — return end
def _find_matching_close_paren(stmt: str, start: int) -> int:
"""Find the matching close paren, skipping string literals."""
depth = 1
i = start
while i < len(stmt) and depth > 0:
ch = stmt[i]
if ch == "'":
i = _skip_string_literal(stmt, i)
continue
if ch == "(":
depth += 1
elif ch == ")":
depth -= 1
i += 1
return i
def _extract_main_query_after_cte(stmt: str) -> str | None:
"""Extract the main (outer) query that follows all CTE definitions.
For ``WITH cte AS (SELECT 1) DELETE FROM users``, returns ``DELETE FROM users``.
Returns None if no main query is found after the last CTE body.
Handles parentheses inside string literals (e.g., ``SELECT '(' FROM t``).
"""
last_cte_end = 0
for m in _iter_as_paren_matches(stmt):
last_cte_end = _find_matching_close_paren(stmt, m.end())
if last_cte_end > 0:
remainder = stmt[last_cte_end:].strip().lstrip(",").strip()
if remainder:
return remainder
return None
def _resolve_explain_command(stmt: str) -> str | None:
"""Resolve the underlying command from an EXPLAIN [ANALYZE] [VERBOSE] statement.
Returns the real command (e.g., 'DELETE') if ANALYZE is present, else None.
Handles both space-separated and parenthesized syntax.
"""
rest = stmt.strip()[len("EXPLAIN") :].strip()
if not rest:
return None
analyze_found = False
explain_opts = {"ANALYZE", "ANALYSE", "VERBOSE"}
if rest.startswith("("):
close = rest.find(")")
if close != -1:
options_str = rest[1:close].upper()
analyze_found = any(
opt.strip() in ("ANALYZE", "ANALYSE") for opt in options_str.split(",")
)
rest = rest[close + 1 :].strip()
else:
while rest:
first_opt = rest.split()[0].upper().rstrip(";") if rest.split() else ""
if first_opt in ("ANALYZE", "ANALYSE"):
analyze_found = True
if first_opt not in explain_opts:
break
rest = rest[len(first_opt) :].strip()
if analyze_found and rest:
return rest.split()[0].upper().rstrip(";")
return None
class NL2SQLToolInput(BaseModel):
sql_query: str = Field(
@@ -21,24 +211,77 @@ class NL2SQLToolInput(BaseModel):
class NL2SQLTool(BaseTool):
"""Tool that converts natural language to SQL and executes it against a database.
By default the tool operates in **read-only mode**: only SELECT, SHOW,
DESCRIBE, EXPLAIN, and read-only CTEs (WITH … SELECT) are permitted. Write
operations (INSERT, UPDATE, DELETE, DROP, ALTER, CREATE, TRUNCATE, …) are
blocked unless ``allow_dml=True`` is set explicitly or the environment
variable ``CREWAI_NL2SQL_ALLOW_DML=true`` is present.
Writable CTEs (``WITH d AS (DELETE …) SELECT …``) and
``EXPLAIN ANALYZE <write-stmt>`` are treated as write operations and are
blocked in read-only mode.
The ``_fetch_all_available_columns`` helper uses parameterised queries so
that table names coming from the database catalogue cannot be used as an
injection vector.
"""
name: str = "NL2SQLTool"
description: str = "Converts natural language to SQL queries and executes them."
description: str = (
"Converts natural language to SQL queries and executes them against a "
"database. Read-only by default — only SELECT/SHOW/DESCRIBE/EXPLAIN "
"queries (and read-only CTEs) are allowed unless configured with "
"allow_dml=True."
)
db_uri: str = Field(
title="Database URI",
description="The URI of the database to connect to.",
)
tables: list = Field(default_factory=list)
columns: dict = Field(default_factory=dict)
allow_dml: bool = Field(
default=False,
title="Allow DML",
description=(
"When False (default) only read statements are permitted. "
"Set to True to allow INSERT/UPDATE/DELETE/DROP and other "
"write operations."
),
)
tables: list[dict[str, Any]] = Field(default_factory=list)
columns: dict[str, list[dict[str, Any]] | str] = Field(default_factory=dict)
args_schema: type[BaseModel] = NL2SQLToolInput
@model_validator(mode="after")
def _apply_env_override(self) -> Self:
"""Allow CREWAI_NL2SQL_ALLOW_DML=true to override allow_dml at runtime."""
if os.environ.get("CREWAI_NL2SQL_ALLOW_DML", "").strip().lower() == "true":
if not self.allow_dml:
logger.warning(
"NL2SQLTool: CREWAI_NL2SQL_ALLOW_DML env var is set — "
"DML/DDL operations are enabled. Ensure this is intentional."
)
self.allow_dml = True
return self
def model_post_init(self, __context: Any) -> None:
if not SQLALCHEMY_AVAILABLE:
raise ImportError(
"sqlalchemy is not installed. Please install it with `pip install crewai-tools[sqlalchemy]`"
"sqlalchemy is not installed. Please install it with "
"`pip install crewai-tools[sqlalchemy]`"
)
data = {}
tables = self._fetch_available_tables()
if self.allow_dml:
logger.warning(
"NL2SQLTool: allow_dml=True — write operations (INSERT/UPDATE/"
"DELETE/DROP/…) are permitted. Use with caution."
)
data: dict[str, list[dict[str, Any]] | str] = {}
result = self._fetch_available_tables()
if isinstance(result, str):
raise RuntimeError(f"Failed to fetch tables: {result}")
tables: list[dict[str, Any]] = result
for table in tables:
table_columns = self._fetch_all_available_columns(table["table_name"])
@@ -47,40 +290,216 @@ class NL2SQLTool(BaseTool):
self.tables = tables
self.columns = data
def _fetch_available_tables(self):
# ------------------------------------------------------------------
# Query validation
# ------------------------------------------------------------------
def _validate_query(self, sql_query: str) -> None:
"""Raise ValueError if *sql_query* is not permitted under the current config.
Splits the query on semicolons and validates each statement
independently. When ``allow_dml=False`` (the default), multi-statement
queries are rejected outright to prevent ``SELECT 1; DROP TABLE users``
style bypasses. When ``allow_dml=True`` every statement is checked and
a warning is emitted for write operations.
"""
statements = [s.strip() for s in sql_query.split(";") if s.strip()]
if not statements:
raise ValueError("NL2SQLTool received an empty SQL query.")
if not self.allow_dml and len(statements) > 1:
raise ValueError(
"NL2SQLTool blocked a multi-statement query in read-only mode. "
"Semicolons are not permitted when allow_dml=False."
)
for stmt in statements:
self._validate_statement(stmt)
def _validate_statement(self, stmt: str) -> None:
"""Validate a single SQL statement (no semicolons)."""
command = self._extract_command(stmt)
# EXPLAIN ANALYZE / EXPLAIN ANALYSE actually *executes* the underlying
# query. Resolve the real command so write operations are caught.
# Handles both space-separated ("EXPLAIN ANALYZE DELETE …") and
# parenthesized ("EXPLAIN (ANALYZE) DELETE …", "EXPLAIN (ANALYZE, VERBOSE) DELETE …").
# EXPLAIN ANALYZE actually executes the underlying query — resolve the
# real command so write operations are caught.
if command == "EXPLAIN":
resolved = _resolve_explain_command(stmt)
if resolved:
command = resolved
# WITH starts a CTE. Read-only CTEs are fine; writable CTEs
# (e.g. WITH d AS (DELETE …) SELECT …) must be blocked in read-only mode.
if command == "WITH":
# Check for write commands inside CTE bodies.
write_found = _detect_writable_cte(stmt)
if write_found:
found = write_found
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool is configured in read-only mode and blocked a "
f"writable CTE containing a '{found}' statement. To allow "
f"write operations set allow_dml=True or "
f"CREWAI_NL2SQL_ALLOW_DML=true."
)
logger.warning(
"NL2SQLTool: executing writable CTE with '%s' because allow_dml=True.",
found,
)
return
# Check the main query after the CTE definitions.
main_query = _extract_main_query_after_cte(stmt)
if main_query:
main_cmd = main_query.split()[0].upper().rstrip(";")
if main_cmd in _WRITE_COMMANDS:
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool is configured in read-only mode and blocked a "
f"'{main_cmd}' statement after a CTE. To allow write "
f"operations set allow_dml=True or "
f"CREWAI_NL2SQL_ALLOW_DML=true."
)
logger.warning(
"NL2SQLTool: executing '%s' after CTE because allow_dml=True.",
main_cmd,
)
elif main_cmd not in _READ_ONLY_COMMANDS:
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool blocked an unrecognised SQL command '{main_cmd}' "
f"after a CTE. Only {sorted(_READ_ONLY_COMMANDS)} are allowed "
f"in read-only mode."
)
return
if command in _WRITE_COMMANDS:
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool is configured in read-only mode and blocked a "
f"'{command}' statement. To allow write operations set "
f"allow_dml=True or CREWAI_NL2SQL_ALLOW_DML=true."
)
logger.warning(
"NL2SQLTool: executing write statement '%s' because allow_dml=True.",
command,
)
elif command not in _READ_ONLY_COMMANDS:
# Unknown command — block by default unless DML is explicitly enabled
if not self.allow_dml:
raise ValueError(
f"NL2SQLTool blocked an unrecognised SQL command '{command}'. "
f"Only {sorted(_READ_ONLY_COMMANDS)} are allowed in read-only "
f"mode."
)
@staticmethod
def _extract_command(sql_query: str) -> str:
"""Return the uppercased first keyword of *sql_query*."""
stripped = sql_query.strip().lstrip("(")
first_token = stripped.split()[0] if stripped.split() else ""
return first_token.upper().rstrip(";")
# ------------------------------------------------------------------
# Schema introspection helpers
# ------------------------------------------------------------------
def _fetch_available_tables(self) -> list[dict[str, Any]] | str:
return self.execute_sql(
"SELECT table_name FROM information_schema.tables WHERE table_schema = 'public';"
"SELECT table_name FROM information_schema.tables "
"WHERE table_schema = 'public';"
)
def _fetch_all_available_columns(self, table_name: str):
def _fetch_all_available_columns(
self, table_name: str
) -> list[dict[str, Any]] | str:
"""Fetch columns for *table_name* using a parameterised query.
The table name is bound via SQLAlchemy's ``:param`` syntax to prevent
SQL injection from catalogue values.
"""
return self.execute_sql(
f"SELECT column_name, data_type FROM information_schema.columns WHERE table_name = '{table_name}';" # noqa: S608
"SELECT column_name, data_type FROM information_schema.columns "
"WHERE table_name = :table_name",
params={"table_name": table_name},
)
def _run(self, sql_query: str):
# ------------------------------------------------------------------
# Core execution
# ------------------------------------------------------------------
def _run(self, sql_query: str) -> list[dict[str, Any]] | str:
try:
self._validate_query(sql_query)
data = self.execute_sql(sql_query)
except ValueError:
raise
except Exception as exc:
data = (
f"Based on these tables {self.tables} and columns {self.columns}, "
"you can create SQL queries to retrieve data from the database."
f"Get the original request {sql_query} and the error {exc} and create the correct SQL query."
"you can create SQL queries to retrieve data from the database. "
f"Get the original request {sql_query} and the error {exc} and "
"create the correct SQL query."
)
return data
def execute_sql(self, sql_query: str) -> list | str:
def execute_sql(
self,
sql_query: str,
params: dict[str, Any] | None = None,
) -> list[dict[str, Any]] | str:
"""Execute *sql_query* and return the results as a list of dicts.
Parameters
----------
sql_query:
The SQL statement to run.
params:
Optional mapping of bind parameters (e.g. ``{"table_name": "users"}``).
"""
if not SQLALCHEMY_AVAILABLE:
raise ImportError(
"sqlalchemy is not installed. Please install it with `pip install crewai-tools[sqlalchemy]`"
"sqlalchemy is not installed. Please install it with "
"`pip install crewai-tools[sqlalchemy]`"
)
# Check ALL statements so that e.g. "SELECT 1; DROP TABLE t" triggers a
# commit when allow_dml=True, regardless of statement order.
_stmts = [s.strip() for s in sql_query.split(";") if s.strip()]
def _is_write_stmt(s: str) -> bool:
cmd = self._extract_command(s)
if cmd in _WRITE_COMMANDS:
return True
if cmd == "EXPLAIN":
# Resolve the underlying command for EXPLAIN ANALYZE
resolved = _resolve_explain_command(s)
if resolved and resolved in _WRITE_COMMANDS:
return True
if cmd == "WITH":
if _detect_writable_cte(s):
return True
main_q = _extract_main_query_after_cte(s)
if main_q:
return main_q.split()[0].upper().rstrip(";") in _WRITE_COMMANDS
return False
is_write = any(_is_write_stmt(s) for s in _stmts)
engine = create_engine(self.db_uri)
Session = sessionmaker(bind=engine) # noqa: N806
session = Session()
try:
result = session.execute(text(sql_query))
session.commit()
result = session.execute(text(sql_query), params or {})
# Only commit when the operation actually mutates state
if self.allow_dml and is_write:
session.commit()
if result.returns_rows: # type: ignore[attr-defined]
columns = result.keys()

8
lib/crewai-tools/src/crewai_tools/tools/ocr_tool/ocr_tool.py
View File

@@ -4,12 +4,15 @@ This tool provides functionality for extracting text from images using supported
"""
import base64
from typing import Any
from crewai.llm import LLM
from crewai.tools.base_tool import BaseTool
from crewai.utilities.types import LLMMessage
from pydantic import BaseModel, Field
from crewai_tools.security.safe_path import validate_file_path
class OCRToolSchema(BaseModel):
"""Input schema for Optical Character Recognition Tool.
@@ -43,7 +46,7 @@ class OCRTool(BaseTool):
llm: LLM = Field(default_factory=lambda: LLM(model="gpt-4o", temperature=0.7))
args_schema: type[BaseModel] = OCRToolSchema
def _run(self, **kwargs) -> str:
def _run(self, **kwargs: Any) -> str:
"""Execute the OCR operation on the provided image.
Args:
@@ -88,7 +91,7 @@ class OCRTool(BaseTool):
return self.llm.call(messages=messages)
@staticmethod
def _encode_image(image_path: str):
def _encode_image(image_path: str) -> str:
"""Encode an image file to base64 format.
Args:
@@ -97,5 +100,6 @@ class OCRTool(BaseTool):
Returns:
str: Base64-encoded image data as a UTF-8 string.
"""
image_path = validate_file_path(image_path)
with open(image_path, "rb") as image_file:
return base64.b64encode(image_file.read()).decode()

12
lib/crewai-tools/src/crewai_tools/tools/oxylabs_amazon_product_scraper_tool/oxylabs_amazon_product_scraper_tool.py
View File

@@ -41,12 +41,12 @@ class OxylabsAmazonProductScraperConfig(BaseModel):
user_agent_type: str | None = Field(None, description="Device type and browser.")
render: str | None = Field(None, description="Enables JavaScript rendering.")
callback_url: str | None = Field(None, description="URL to your callback endpoint.")
context: list | None = Field(
context: list[Any] | None = Field(
None,
description="Additional advanced settings and controls for specialized requirements.",
)
parse: bool | None = Field(None, description="True will return structured data.")
parsing_instructions: dict | None = Field(
parsing_instructions: dict[str, Any] | None = Field(
None, description="Instructions for parsing the results."
)
@@ -71,7 +71,7 @@ class OxylabsAmazonProductScraperTool(BaseTool):
description: str = "Scrape Amazon product pages with Oxylabs Amazon Product Scraper"
args_schema: type[BaseModel] = OxylabsAmazonProductScraperArgs
oxylabs_api: RealtimeClient
oxylabs_api: Any
config: OxylabsAmazonProductScraperConfig
package_dependencies: list[str] = Field(default_factory=lambda: ["oxylabs"])
env_vars: list[EnvVar] = Field(
@@ -93,8 +93,8 @@ class OxylabsAmazonProductScraperTool(BaseTool):
self,
username: str | None = None,
password: str | None = None,
config: OxylabsAmazonProductScraperConfig | dict | None = None,
**kwargs,
config: OxylabsAmazonProductScraperConfig | dict[str, Any] | None = None,
**kwargs: Any,
) -> None:
bits, _ = architecture()
sdk_type = (
@@ -164,4 +164,4 @@ class OxylabsAmazonProductScraperTool(BaseTool):
if isinstance(content, dict):
return json.dumps(content)
return content
return str(content)

14
lib/crewai-tools/src/crewai_tools/tools/oxylabs_amazon_search_scraper_tool/oxylabs_amazon_search_scraper_tool.py
View File

@@ -43,12 +43,12 @@ class OxylabsAmazonSearchScraperConfig(BaseModel):
user_agent_type: str | None = Field(None, description="Device type and browser.")
render: str | None = Field(None, description="Enables JavaScript rendering.")
callback_url: str | None = Field(None, description="URL to your callback endpoint.")
context: list | None = Field(
context: list[Any] | None = Field(
None,
description="Additional advanced settings and controls for specialized requirements.",
)
parse: bool | None = Field(None, description="True will return structured data.")
parsing_instructions: dict | None = Field(
parsing_instructions: dict[str, Any] | None = Field(
None, description="Instructions for parsing the results."
)
@@ -73,7 +73,7 @@ class OxylabsAmazonSearchScraperTool(BaseTool):
description: str = "Scrape Amazon search results with Oxylabs Amazon Search Scraper"
args_schema: type[BaseModel] = OxylabsAmazonSearchScraperArgs
oxylabs_api: RealtimeClient
oxylabs_api: Any
config: OxylabsAmazonSearchScraperConfig
package_dependencies: list[str] = Field(default_factory=lambda: ["oxylabs"])
env_vars: list[EnvVar] = Field(
@@ -95,9 +95,9 @@ class OxylabsAmazonSearchScraperTool(BaseTool):
self,
username: str | None = None,
password: str | None = None,
config: OxylabsAmazonSearchScraperConfig | dict | None = None,
**kwargs,
):
config: OxylabsAmazonSearchScraperConfig | dict[str, Any] | None = None,
**kwargs: Any,
) -> None:
bits, _ = architecture()
sdk_type = (
f"oxylabs-crewai-sdk-python/"
@@ -166,4 +166,4 @@ class OxylabsAmazonSearchScraperTool(BaseTool):
if isinstance(content, dict):
return json.dumps(content)
return content
return str(content)

16
lib/crewai-tools/src/crewai_tools/tools/oxylabs_google_search_scraper_tool/oxylabs_google_search_scraper_tool.py
View File

@@ -46,12 +46,12 @@ class OxylabsGoogleSearchScraperConfig(BaseModel):
user_agent_type: str | None = Field(None, description="Device type and browser.")
render: str | None = Field(None, description="Enables JavaScript rendering.")
callback_url: str | None = Field(None, description="URL to your callback endpoint.")
context: list | None = Field(
context: list[Any] | None = Field(
None,
description="Additional advanced settings and controls for specialized requirements.",
)
parse: bool | None = Field(None, description="True will return structured data.")
parsing_instructions: dict | None = Field(
parsing_instructions: dict[str, Any] | None = Field(
None, description="Instructions for parsing the results."
)
@@ -76,7 +76,7 @@ class OxylabsGoogleSearchScraperTool(BaseTool):
description: str = "Scrape Google Search results with Oxylabs Google Search Scraper"
args_schema: type[BaseModel] = OxylabsGoogleSearchScraperArgs
oxylabs_api: RealtimeClient
oxylabs_api: Any
config: OxylabsGoogleSearchScraperConfig
package_dependencies: list[str] = Field(default_factory=lambda: ["oxylabs"])
env_vars: list[EnvVar] = Field(
@@ -98,9 +98,9 @@ class OxylabsGoogleSearchScraperTool(BaseTool):
self,
username: str | None = None,
password: str | None = None,
config: OxylabsGoogleSearchScraperConfig | dict | None = None,
**kwargs,
):
config: OxylabsGoogleSearchScraperConfig | dict[str, Any] | None = None,
**kwargs: Any,
) -> None:
bits, _ = architecture()
sdk_type = (
f"oxylabs-crewai-sdk-python/"
@@ -158,7 +158,7 @@ class OxylabsGoogleSearchScraperTool(BaseTool):
)
return username, password
def _run(self, query: str, **kwargs) -> str:
def _run(self, query: str, **kwargs: Any) -> str:
response = self.oxylabs_api.google.scrape_search(
query,
**self.config.model_dump(exclude_none=True),
@@ -169,4 +169,4 @@ class OxylabsGoogleSearchScraperTool(BaseTool):
if isinstance(content, dict):
return json.dumps(content)
return content
return str(content)

14
lib/crewai-tools/src/crewai_tools/tools/oxylabs_universal_scraper_tool/oxylabs_universal_scraper_tool.py
View File

@@ -37,12 +37,12 @@ class OxylabsUniversalScraperConfig(BaseModel):
user_agent_type: str | None = Field(None, description="Device type and browser.")
render: str | None = Field(None, description="Enables JavaScript rendering.")
callback_url: str | None = Field(None, description="URL to your callback endpoint.")
context: list | None = Field(
context: list[Any] | None = Field(
None,
description="Additional advanced settings and controls for specialized requirements.",
)
parse: bool | None = Field(None, description="True will return structured data.")
parsing_instructions: dict | None = Field(
parsing_instructions: dict[str, Any] | None = Field(
None, description="Instructions for parsing the results."
)
@@ -67,7 +67,7 @@ class OxylabsUniversalScraperTool(BaseTool):
description: str = "Scrape any url with Oxylabs Universal Scraper"
args_schema: type[BaseModel] = OxylabsUniversalScraperArgs
oxylabs_api: RealtimeClient
oxylabs_api: Any
config: OxylabsUniversalScraperConfig
package_dependencies: list[str] = Field(default_factory=lambda: ["oxylabs"])
env_vars: list[EnvVar] = Field(
@@ -89,9 +89,9 @@ class OxylabsUniversalScraperTool(BaseTool):
self,
username: str | None = None,
password: str | None = None,
config: OxylabsUniversalScraperConfig | dict | None = None,
**kwargs,
):
config: OxylabsUniversalScraperConfig | dict[str, Any] | None = None,
**kwargs: Any,
) -> None:
bits, _ = architecture()
sdk_type = (
f"oxylabs-crewai-sdk-python/"
@@ -160,4 +160,4 @@ class OxylabsUniversalScraperTool(BaseTool):
if isinstance(content, dict):
return json.dumps(content)
return content
return str(content)

9
lib/crewai-tools/src/crewai_tools/tools/patronus_eval_tool/example.py
View File

@@ -1,11 +1,12 @@
import random
from typing import Any
from crewai import Agent, Crew, Task
from patronus import ( # type: ignore[import-not-found,import-untyped]
from patronus import ( # type: ignore[import-untyped]
Client,
EvaluationResult,
)
from patronus_local_evaluator_tool import ( # type: ignore[import-not-found,import-untyped]
from patronus_local_evaluator_tool import ( # type: ignore[import-not-found]
PatronusLocalEvaluatorTool,
)
@@ -15,8 +16,8 @@ client = Client()
# Example of an evaluator that returns a random pass/fail result
@client.register_local_evaluator("random_evaluator")
def random_evaluator(**kwargs):
@client.register_local_evaluator("random_evaluator") # type: ignore[untyped-decorator]
def random_evaluator(**kwargs: Any) -> Any:
score = random.random() # noqa: S311
return EvaluationResult(
score_raw=score,

5
lib/crewai-tools/src/crewai_tools/tools/patronus_eval_tool/patronus_eval_tool.py
View File

@@ -34,7 +34,7 @@ class PatronusEvalTool(BaseTool):
stacklevel=2,
)
def _init_run(self):
def _init_run(self) -> tuple[list[dict[str, str]], list[dict[str, str]]]:
evaluators_set = json.loads(
requests.get(
"https://api.patronus.ai/v1/evaluators",
@@ -136,8 +136,9 @@ class PatronusEvalTool(BaseTool):
"evaluators": evals,
}
api_key = os.getenv("PATRONUS_API_KEY", "")
headers = {
"X-API-KEY": os.getenv("PATRONUS_API_KEY"),
"X-API-KEY": api_key,
"accept": "application/json",
"content-type": "application/json",
}

15
lib/crewai-tools/src/crewai_tools/tools/patronus_eval_tool/patronus_local_evaluator_tool.py
View File

@@ -1,16 +1,13 @@
from __future__ import annotations
from typing import TYPE_CHECKING, Any
from typing import Any
from crewai.tools import BaseTool
from pydantic import BaseModel, ConfigDict, Field
if TYPE_CHECKING:
from patronus import Client, EvaluationResult # type: ignore[import-untyped]
try:
import patronus # noqa: F401
import patronus # type: ignore[import-untyped] # noqa: F401
PYPATRONUS_AVAILABLE = True
except ImportError:
@@ -37,7 +34,7 @@ class PatronusLocalEvaluatorTool(BaseTool):
name: str = "Patronus Local Evaluator Tool"
description: str = "This tool is used to evaluate the model input and output using custom function evaluators."
args_schema: type[BaseModel] = FixedLocalEvaluatorToolSchema
client: Client = None
client: Any = None
evaluator: str
evaluated_model_gold_answer: str
@@ -46,7 +43,7 @@ class PatronusLocalEvaluatorTool(BaseTool):
def __init__(
self,
patronus_client: Client = None,
patronus_client: Any = None,
evaluator: str = "",
evaluated_model_gold_answer: str = "",
**kwargs: Any,
@@ -56,7 +53,7 @@ class PatronusLocalEvaluatorTool(BaseTool):
self.evaluated_model_gold_answer = evaluated_model_gold_answer
self._initialize_patronus(patronus_client)
def _initialize_patronus(self, patronus_client: Client) -> None:
def _initialize_patronus(self, patronus_client: Any) -> None:
try:
if PYPATRONUS_AVAILABLE:
self.client = patronus_client
@@ -94,7 +91,7 @@ class PatronusLocalEvaluatorTool(BaseTool):
evaluated_model_gold_answer = self.evaluated_model_gold_answer
evaluator = self.evaluator
result: EvaluationResult = self.client.evaluate(
result: Any = self.client.evaluate(
evaluator=evaluator,
evaluated_model_input=evaluated_model_input,
evaluated_model_output=evaluated_model_output,

11
lib/crewai-tools/src/crewai_tools/tools/patronus_eval_tool/patronus_predefined_criteria_eval_tool.py
View File

@@ -8,16 +8,16 @@ import requests
class FixedBaseToolSchema(BaseModel):
evaluated_model_input: dict = Field(
evaluated_model_input: dict[str, Any] = Field(
..., description="The agent's task description in simple text"
)
evaluated_model_output: dict = Field(
evaluated_model_output: dict[str, Any] = Field(
..., description="The agent's output of the task"
)
evaluated_model_retrieved_context: dict = Field(
evaluated_model_retrieved_context: dict[str, Any] = Field(
..., description="The agent's context"
)
evaluated_model_gold_answer: dict = Field(
evaluated_model_gold_answer: dict[str, Any] = Field(
..., description="The agent's gold answer only if available"
)
evaluators: list[dict[str, str]] = Field(
@@ -57,8 +57,9 @@ class PatronusPredefinedCriteriaEvalTool(BaseTool):
evaluated_model_gold_answer = kwargs.get("evaluated_model_gold_answer")
evaluators = self.evaluators
api_key = os.getenv("PATRONUS_API_KEY", "")
headers = {
"X-API-KEY": os.getenv("PATRONUS_API_KEY"),
"X-API-KEY": api_key,
"accept": "application/json",
"content-type": "application/json",
}

2
lib/crewai-tools/src/crewai_tools/tools/pdf_search_tool/pdf_search_tool.py
View File

@@ -37,7 +37,7 @@ class PDFSearchTool(RagTool):
self._generate_description()
return self
def add(self, pdf: str) -> None:
def add(self, pdf: str) -> None: # type: ignore[override]
super().add(pdf, data_type=DataType.PDF_FILE)
def _run( # type: ignore[override]

2
lib/crewai-tools/src/crewai_tools/tools/qdrant_vector_search_tool/qdrant_search_tool.py
View File

@@ -119,7 +119,7 @@ class QdrantVectorSearchTool(BaseTool):
)
)()
)
results = self.client.query_points(
results = self.client.query_points( # type: ignore[union-attr]
collection_name=self.qdrant_config.collection_name,
query=query_vector,
query_filter=search_filter,

Some files were not shown because too many files have changed in this diff Show More