mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-01-11 17:18:29 +00:00
c960f26601
0b3f00e6 chore: update project version to 0.73.0 and revise uv.lock dependencies (#455) ad19b074 feat: replace embedchain with native crewai adapter (#451) git-subtree-dir: packages/tools git-subtree-split: 0b3f00e67c0dae24d188c292dc99759fd1c841f7
81 lines
2.8 KiB
Python
81 lines
2.8 KiB
Python
from typing import List, Optional, Type
|
|
|
|
from pydantic import BaseModel, Field
|
|
|
|
from ..rag.rag_tool import RagTool
|
|
from crewai_tools.rag.data_types import DataType
|
|
|
|
|
|
class FixedGithubSearchToolSchema(BaseModel):
|
|
"""Input for GithubSearchTool."""
|
|
|
|
search_query: str = Field(
|
|
...,
|
|
description="Mandatory search query you want to use to search the github repo's content",
|
|
)
|
|
|
|
|
|
class GithubSearchToolSchema(FixedGithubSearchToolSchema):
|
|
"""Input for GithubSearchTool."""
|
|
|
|
github_repo: str = Field(..., description="Mandatory github you want to search")
|
|
content_types: List[str] = Field(
|
|
...,
|
|
description="Mandatory content types you want to be included search, options: [code, repo, pr, issue]",
|
|
)
|
|
|
|
|
|
class GithubSearchTool(RagTool):
|
|
name: str = "Search a github repo's content"
|
|
description: str = (
|
|
"A tool that can be used to semantic search a query from a github repo's content. This is not the GitHub API, but instead a tool that can provide semantic search capabilities."
|
|
)
|
|
summarize: bool = False
|
|
gh_token: str
|
|
args_schema: Type[BaseModel] = GithubSearchToolSchema
|
|
content_types: List[str] = Field(
|
|
default_factory=lambda: ["code", "repo", "pr", "issue"],
|
|
description="Content types you want to be included search, options: [code, repo, pr, issue]",
|
|
)
|
|
|
|
def __init__(
|
|
self,
|
|
github_repo: Optional[str] = None,
|
|
content_types: Optional[List[str]] = None,
|
|
**kwargs,
|
|
):
|
|
super().__init__(**kwargs)
|
|
|
|
if github_repo and content_types:
|
|
self.add(repo=github_repo, content_types=content_types)
|
|
self.description = f"A tool that can be used to semantic search a query the {github_repo} github repo's content. This is not the GitHub API, but instead a tool that can provide semantic search capabilities."
|
|
self.args_schema = FixedGithubSearchToolSchema
|
|
self._generate_description()
|
|
|
|
def add(
|
|
self,
|
|
repo: str,
|
|
content_types: Optional[List[str]] = None,
|
|
) -> None:
|
|
content_types = content_types or self.content_types
|
|
super().add(
|
|
f"https://github.com/{repo}",
|
|
data_type=DataType.GITHUB,
|
|
metadata={"content_types": content_types, "gh_token": self.gh_token}
|
|
)
|
|
|
|
def _run(
|
|
self,
|
|
search_query: str,
|
|
github_repo: Optional[str] = None,
|
|
content_types: Optional[List[str]] = None,
|
|
similarity_threshold: float | None = None,
|
|
limit: int | None = None,
|
|
) -> str:
|
|
if github_repo:
|
|
self.add(
|
|
repo=github_repo,
|
|
content_types=content_types,
|
|
)
|
|
return super()._run(query=search_query, similarity_threshold=similarity_threshold, limit=limit)
|