Notebooks
W
Weaviate Weaviate Query Agent Tool

Weaviate Query Agent Tool

vector-searchvector-databaseretrieval-augmented-generationllm-frameworksfunction-callingweaviate-recipesintegrationsPythongenerative-aillm-agent-frameworksanthropic
alph-notebooks/weaviate-recipes / weaviate-query-agent-tool.ipynb

Open In Colab

Weaviate Query Agent with Anthropic

This notebook will show you how to define the Weaviate Query Agent as a tool through Anthropic.

Requirements

  1. Weaviate Cloud instance (WCD): The Weaviate Query Agent is only accessible through WCD at the moment. You can create a serverless cluster or a free 14-day sandbox here.
  2. Install the Anthropic Python API with pip install anthropic. We're using version 0.49.0 at the time of creating this notebook.
  3. Install the Weaviate Agents package with pip install weaviate-agents
  4. You'll need a Weaviate cluster with data. If you don't have one, check out this notebook to import the Weaviate Blogs.

Import libraries and keys

[ ]
[1]

Define Query Agent function

[ ]

Connect to Anthropic client and define Query Agent function

[8]

Query time

[9]
Question:
How do I run Weaviate with Docker?
==================================================
Tool plan:
I'll help you find information about running Weaviate with Docker. Let me search for that information for you. 

Tool calls:
Tool name: send_query_agent_request | Parameters: {'query': 'How to run Weaviate with Docker'}
==================================================
Final response:
# Running Weaviate with Docker

Here's how to run Weaviate using Docker:

## Prerequisites
- Docker and Docker Compose installed on your system
- Basic familiarity with Docker commands

## Step-by-Step Instructions

1. **Install Docker and Docker Compose**
   - For Windows/Mac: Install [Docker Desktop](https://www.docker.com/products/docker-desktop)
   - For Linux: Install [Docker Engine](https://docs.docker.com/engine/install/) and [Docker Compose](https://docs.docker.com/compose/install/)

2. **Get the Docker Compose Configuration**
   - Option 1: Use the [Weaviate configuration tool](https://weaviate.io/developers/weaviate/installation/docker-compose) to generate a custom `docker-compose.yml`
   - Option 2: Download a sample configuration from Weaviate's documentation

3. **Start Weaviate**
   ```bash
   docker compose up -d
   ```
   The `-d` flag runs containers in detached mode (in the background)

4. **Verify Weaviate is Running**
   - Check if Weaviate is ready by accessing the readiness endpoint:
   ```bash
   curl http://localhost:8080/v1/.well-known/ready
   ```
   - You should receive a 2xx status code when Weaviate is operational

## Notes
- This Docker Compose setup is recommended for development and testing
- For production environments, a Kubernetes deployment is recommended

Would you like me to provide more specific information about configuring Weaviate modules or customizing your Docker setup?
==================================================