Squashed 'packages/tools/' content from commit 78317b9c

git-subtree-dir: packages/tools
git-subtree-split: 78317b9c127f18bd040c1d77e3c0840cdc9a5b38

crewai_tools/tools/code_docs_search_tool/README.md

@@ -0,0 +1,56 @@
+# CodeDocsSearchTool
+
+## Description
+The CodeDocsSearchTool is a powerful RAG (Retrieval-Augmented Generation) tool designed for semantic searches within code documentation. It enables users to efficiently find specific information or topics within code documentation. By providing a `docs_url` during initialization, the tool narrows down the search to that particular documentation site. Alternatively, without a specific `docs_url`, it searches across a wide array of code documentation known or discovered throughout its execution, making it versatile for various documentation search needs.
+
+## Installation
+To start using the CodeDocsSearchTool, first, install the crewai_tools package via pip:
+```shell
+pip install 'crewai[tools]'
+```
+
+## Example
+Utilize the CodeDocsSearchTool as follows to conduct searches within code documentation:
+```python
+from crewai_tools import CodeDocsSearchTool
+
+# To search any code documentation content if the URL is known or discovered during its execution:
+tool = CodeDocsSearchTool()
+
+# OR
+
+# To specifically focus your search on a given documentation site by providing its URL:
+tool = CodeDocsSearchTool(docs_url='https://docs.example.com/reference')
+```
+Note: Substitute 'https://docs.example.com/reference' with your target documentation URL and 'How to use search tool' with the search query relevant to your needs.
+
+## Arguments
+- `docs_url`: Optional. Specifies the URL of the code documentation to be searched. Providing this during the tool's initialization focuses the search on the specified documentation content.
+
+## Custom model and embeddings
+
+By default, the tool uses OpenAI for both embeddings and summarization. To customize the model, you can use a config dictionary as follows:
+
+```python
+tool = CodeDocsSearchTool(
+    config=dict(
+        llm=dict(
+            provider="ollama", # or google, openai, anthropic, llama2, ...
+            config=dict(
+                model="llama2",
+                # temperature=0.5,
+                # top_p=1,
+                # stream=true,
+            ),
+        ),
+        embedder=dict(
+            provider="google",
+            config=dict(
+                model="models/embedding-001",
+                task_type="retrieval_document",
+                # title="Embeddings",
+            ),
+        ),
+    )
+)
+```

crewai_tools/tools/code_docs_search_tool/code_docs_search_tool.py

@@ -0,0 +1,56 @@
+from typing import Any, Optional, Type
+
+try:
+    from embedchain.models.data_type import DataType
+    EMBEDCHAIN_AVAILABLE = True
+except ImportError:
+    EMBEDCHAIN_AVAILABLE = False
+
+from pydantic import BaseModel, Field
+
+from ..rag.rag_tool import RagTool
+
+
+class FixedCodeDocsSearchToolSchema(BaseModel):
+    """Input for CodeDocsSearchTool."""
+
+    search_query: str = Field(
+        ...,
+        description="Mandatory search query you want to use to search the Code Docs content",
+    )
+
+
+class CodeDocsSearchToolSchema(FixedCodeDocsSearchToolSchema):
+    """Input for CodeDocsSearchTool."""
+
+    docs_url: str = Field(..., description="Mandatory docs_url path you want to search")
+
+
+class CodeDocsSearchTool(RagTool):
+    name: str = "Search a Code Docs content"
+    description: str = (
+        "A tool that can be used to semantic search a query from a Code Docs content."
+    )
+    args_schema: Type[BaseModel] = CodeDocsSearchToolSchema
+
+    def __init__(self, docs_url: Optional[str] = None, **kwargs):
+        super().__init__(**kwargs)
+        if docs_url is not None:
+            self.add(docs_url)
+            self.description = f"A tool that can be used to semantic search a query the {docs_url} Code Docs content."
+            self.args_schema = FixedCodeDocsSearchToolSchema
+            self._generate_description()
+
+    def add(self, docs_url: str) -> None:
+        if not EMBEDCHAIN_AVAILABLE:
+            raise ImportError("embedchain is not installed. Please install it with `pip install crewai-tools[embedchain]`")
+        super().add(docs_url, data_type=DataType.DOCS_SITE)
+
+    def _run(
+        self,
+        search_query: str,
+        docs_url: Optional[str] = None,
+    ) -> str:
+        if docs_url is not None:
+            self.add(docs_url)
+        return super()._run(query=search_query)