LlamaIndex Tools Integration: Airweave

LlamaIndex Tools Integration: Airweave

This tool connects your LlamaIndex agent to Airweave, an open-source platform that makes any app searchable by syncing data from various sources with minimal configuration.

Installation

pip install llama-index-tools-airweave llama-index-llms-openai

Prerequisites

1. An Airweave account and API key
2. At least one collection set up with synced data

Get started at Airweave

Usage

Basic Usage

import os
import asyncio
from llama_index.tools.airweave import AirweaveToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

### Initialize the Airweave tool
airweave_tool = AirweaveToolSpec(
    api_key=os.environ["AIRWEAVE_API_KEY"],
)

### Create an agent with the Airweave tools
agent = FunctionAgent(
    tools=airweave_tool.to_tool_list(),
    llm=OpenAI(model="gpt-4o-mini"),
    system_prompt="""You are a helpful assistant that can search through
    Airweave collections to answer questions about your organization's data.""",
)


### Use the agent to search your data
async def main():
    response = await agent.run(
        "Search the finance-data collection for Q4 revenue reports"
    )
    print(response)


if __name__ == "__main__":
    asyncio.run(main())

Available Tools

search_collection

Simple search in a collection with default settings (most common use case).

Parameters:

• collection_id (str): The readable ID of the collection
• query (str): Your search query
• limit (int, optional): Max results to return (default: 10)
• offset (int, optional): Pagination offset (default: 0)

advanced_search_collection

Advanced search with full control over retrieval parameters.

Parameters:

• collection_id (str): The readable ID of the collection
• query (str): Your search query
• limit (int, optional): Max results to return (default: 10)
• offset (int, optional): Pagination offset (default: 0)
• retrieval_strategy (str, optional): "hybrid", "neural", or "keyword"
• temporal_relevance (float, optional): Weight recent content (0.0-1.0)
• expand_query (bool, optional): Generate query variations
• interpret_filters (bool, optional): Extract filters from natural language
• rerank (bool, optional): Use LLM-based reranking
• generate_answer (bool, optional): Generate natural language answer

Returns:
Dictionary with documents list and optional answer field.

search_and_generate_answer

Convenience method that searches and returns a direct natural language answer (RAG-style).

Parameters:

• collection_id (str): The readable ID of the collection
• query (str): Your question in natural language
• limit (int, optional): Max results to consider (default: 10)
• use_reranking (bool, optional): Use reranking (default: True)

Returns:
Natural language answer string.

list_collections

List all collections in your organization.

Parameters:

• skip (int, optional): Pagination skip (default: 0)
• limit (int, optional): Max collections to return (default: 100)

get_collection_info

Get detailed information about a specific collection.

Parameters:

• collection_id (str): The readable ID of the collection

Advanced Examples

Direct Tool Usage

You can use the tools directly without an agent:

from llama_index.tools.airweave import AirweaveToolSpec

airweave_tool = AirweaveToolSpec(api_key="your-key")

### List collections
collections = airweave_tool.list_collections()
print(f"Found {len(collections)} collections")

### Simple search
results = airweave_tool.search_collection(
    collection_id="finance-data", query="Q4 revenue reports", limit=5
)

for doc in results:
    print(f"Score: {doc.metadata.get('score', 'N/A')}")
    print(f"Text: {doc.text[:200]}...")

Advanced Search Options

### Advanced search with all options
result = airwea