Weaviate Vector Search

Overview

The WeaviateVectorSearchTool is specifically crafted for conducting semantic searches within documents stored in a Weaviate vector database. This tool allows you to find semantically similar documents to a given query, leveraging the power of vector and keyword search for more accurate and contextually relevant search results.

Weaviate is a vector database that stores and queries vector embeddings, enabling semantic search capabilities.

Installation

To incorporate this tool into your project, you need to install the Weaviate client:

uv add weaviate-client

Steps to Get Started

To effectively use the WeaviateVectorSearchTool, follow these steps:

1. Package Installation: Confirm that the crewai[tools] and weaviate-client packages are installed in your Python environment.
2. Weaviate Setup: Set up a Weaviate cluster. You can follow the Weaviate documentation for instructions.
3. API Keys: Obtain your Weaviate cluster URL and API key.
4. OpenAI API Key: Ensure you have an OpenAI API key set in your environment variables as OPENAI_API_KEY.

Example

The following example demonstrates how to initialize the tool and execute a search:

from crewai_tools import WeaviateVectorSearchTool

# Initialize the tool
tool = WeaviateVectorSearchTool(
    collection_name='example_collections',
    limit=3,
    alpha=0.75,
    weaviate_cluster_url="https://your-weaviate-cluster-url.com",
    weaviate_api_key="your-weaviate-api-key",
)

@agent
def search_agent(self) -> Agent:
    '''
    This agent uses the WeaviateVectorSearchTool to search for
    semantically similar documents in a Weaviate vector database.
    '''
    return Agent(
        config=self.agents_config["search_agent"],
        tools=[tool]
    )

Parameters

The WeaviateVectorSearchTool accepts the following parameters:

• collection_name: Required. The name of the collection to search within.
• weaviate_cluster_url: Required. The URL of the Weaviate cluster.
• weaviate_api_key: Required. The API key for the Weaviate cluster.
• limit: Optional. The number of results to return. Default is 3.
• alpha: Optional. Controls the weighting between vector and keyword (BM25) search. alpha = 0 -> BM25 only, alpha = 1 -> vector search only. Default is 0.75.
• vectorizer: Optional. The vectorizer to use. If not provided, it will use text2vec_openai with the nomic-embed-text model.
• generative_model: Optional. The generative model to use. If not provided, it will use OpenAI’s gpt-4o.

Advanced Configuration

You can customize the vectorizer and generative model used by the tool:

from crewai_tools import WeaviateVectorSearchTool
from weaviate.classes.config import Configure

# Setup custom model for vectorizer and generative model
tool = WeaviateVectorSearchTool(
    collection_name='example_collections',
    limit=3,
    alpha=0.75,
    vectorizer=Configure.Vectorizer.text2vec_openai(model="nomic-embed-text"),
    generative_model=Configure.Generative.openai(model="gpt-4o-mini"),
    weaviate_cluster_url="https://your-weaviate-cluster-url.com",
    weaviate_api_key="your-weaviate-api-key",
)

Preloading Documents

You can preload your Weaviate database with documents before using the tool:

import os
from crewai_tools import WeaviateVectorSearchTool
import weaviate
from weaviate.classes.init import Auth

# Connect to Weaviate
client = weaviate.connect_to_weaviate_cloud(
    cluster_url="https://your-weaviate-cluster-url.com",
    auth_credentials=Auth.api_key("your-weaviate-api-key"),
    headers={"X-OpenAI-Api-Key": "your-openai-api-key"}
)

# Get or create collection
test_docs = client.collections.get("example_collections")
if not test_docs:
    test_docs = client.collections.create(
        name="example_collections",
        vectorizer_config=Configure.Vectorizer.text2vec_openai(model="nomic-embed-text"),
        generative_config=Configure.Generative.openai(model="gpt-4o"),
    )

# Load documents
docs_to_load = os.listdir("knowledge")
with test_docs.batch.dynamic() as batch:
    for d in docs_to_load:
        with open(os.path.join("knowledge", d), "r") as f:
            content = f.read()
        batch.add_object(
            {
                "content": content,
                "year": d.split("_")[0],
            }
        )

# Initialize the tool
tool = WeaviateVectorSearchTool(
    collection_name='example_collections',
    limit=3,
    alpha=0.75,
    weaviate_cluster_url="https://your-weaviate-cluster-url.com",
    weaviate_api_key="your-weaviate-api-key",
)

Agent Integration Example

Here’s how to integrate the WeaviateVectorSearchTool with a CrewAI agent:

from crewai import Agent
from crewai_tools import WeaviateVectorSearchTool

# Initialize the tool
weaviate_tool = WeaviateVectorSearchTool(
    collection_name='example_collections',
    limit=3,
    alpha=0.75,
    weaviate_cluster_url="https://your-weaviate-cluster-url.com",
    weaviate_api_key="your-weaviate-api-key",
)

# Create an agent with the tool
rag_agent = Agent(
    name="rag_agent",
    role="You are a helpful assistant that can answer questions with the help of the WeaviateVectorSearchTool.",
    llm="gpt-4o-mini",
    tools=[weaviate_tool],
)

Conclusion

The WeaviateVectorSearchTool provides a powerful way to search for semantically similar documents in a Weaviate vector database. By leveraging vector embeddings, it enables more accurate and contextually relevant search results compared to traditional keyword-based searches. This tool is particularly useful for applications that require finding information based on meaning rather than exact matches.