Directory RAG Search

`DirectorySearchTool`

Description

The DirectorySearchTool enables semantic search within the content of specified directories, leveraging the Retrieval-Augmented Generation (RAG) methodology for efficient navigation through files. Designed for flexibility, it allows users to dynamically specify search directories at runtime or set a fixed directory during initial setup.

Installation

To use the DirectorySearchTool, begin by installing the crewai_tools package. Execute the following command in your terminal:

pip install 'crewai[tools]'

Initialization and Usage

Import the DirectorySearchTool from the crewai_tools package to start. You can initialize the tool without specifying a directory, enabling the setting of the search directory at runtime. Alternatively, the tool can be initialized with a predefined directory.

from crewai_tools import DirectorySearchTool

# For dynamic directory specification at runtime
tool = DirectorySearchTool()

# For fixed directory searches
tool = DirectorySearchTool(directory='/path/to/directory')

Arguments

directory: A string argument that specifies the search directory. This is optional during initialization but required for searches if not set initially.

Custom Model and Embeddings

The DirectorySearchTool uses OpenAI for embeddings and summarization by default. Customization options for these settings include changing the model provider and configuration, enhancing flexibility for advanced users.

from chromadb.config import Settings

tool = DirectorySearchTool(
    config={
        "embedding_model": {
            "provider": "openai",
            "config": {
                "model": "text-embedding-3-small",
                # "api_key": "sk-...",
            },
        },
        "vectordb": {
            "provider": "chromadb",  # or "qdrant"
            "config": {
                # "settings": Settings(persist_directory="/content/chroma", allow_reset=True, is_persistent=True),
                # from qdrant_client.models import VectorParams, Distance
                # "vectors_config": VectorParams(size=384, distance=Distance.COSINE),
            }
        },
    }
)

## Security

### Path Validation

Directory paths provided to this tool are validated against the current working directory. Paths that resolve outside the working directory are rejected with a `ValueError`.

To allow paths outside the working directory (for example, in tests or trusted pipelines), set the environment variable:

```shell
CREWAI_TOOLS_ALLOW_UNSAFE_PATHS=true