> ## Documentation Index
> Fetch the complete documentation index at: https://docs.mem0.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Weaviate

> Use Weaviate as an open-source vector search engine in Mem0 for storing and retrieving vector embeddings.

[Weaviate](https://weaviate.io/) is an open-source vector search engine. It allows efficient storage and retrieval of high-dimensional vector embeddings, enabling powerful search and retrieval capabilities.

### Installation

<CodeGroup>
  ```bash Python theme={null}
  pip install weaviate-client
  ```

  ```bash TypeScript theme={null}
  npm install weaviate-client
  ```
</CodeGroup>

### Usage

<CodeGroup>
  ```python Python theme={null}
  import os
  from mem0 import Memory

  os.environ["OPENAI_API_KEY"] = "sk-xx"

  config = {
      "vector_store": {
          "provider": "weaviate",
          "config": {
              "collection_name": "test",
              "cluster_url": "http://localhost:8080",
              "auth_client_secret": None,
          }
      }
  }

  m = Memory.from_config(config)
  messages = [
      {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
      {"role": "assistant", "content": "How about a thriller movie? They can be quite engaging."},
      {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
      {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
  ]
  m.add(messages, user_id="alice", metadata={"category": "movies"})
  ```

  ```typescript TypeScript theme={null}
  import { Memory } from "mem0ai/oss";

  const config = {
    vectorStore: {
      provider: "weaviate",
      config: {
        collectionName: "test",
        embeddingModelDims: 1536,
        clusterUrl: "http://localhost:8080",
      },
    },
  };

  const memory = new Memory(config);

  const messages = [
    {
      role: "user",
      content: "I'm planning to watch a movie tonight. Any recommendations?",
    },
    {
      role: "assistant",
      content: "How about a thriller movie? They can be quite engaging.",
    },
    {
      role: "user",
      content: "I'm not a big fan of thriller movies but I love sci-fi movies.",
    },
    {
      role: "assistant",
      content:
        "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future.",
    },
  ];

  await memory.add(messages, {
    userId: "alice",
    metadata: {
      category: "movies",
    },
  });
  ```
</CodeGroup>

The TypeScript SDK picks the connection mode from the config you pass:

* `clusterUrl` pointing at `localhost` connects to a local instance.
* `clusterUrl` plus `apiKey` connects to a Weaviate Cloud cluster (for example `https://my-cluster.weaviate.cloud`).
* Any other `clusterUrl` without an `apiKey` connects to a custom deployment, using the host and port from the URL.

You can also pass a pre-configured `client` (a `WeaviateClient` instance) to reuse an existing connection.

### Config

Here are the parameters available for configuring Weaviate:

| Python                 | TypeScript           | Description                                     | Default Value |
| ---------------------- | -------------------- | ----------------------------------------------- | ------------- |
| `collection_name`      | `collectionName`     | The name of the collection to store the vectors | `mem0`        |
| `embedding_model_dims` | `embeddingModelDims` | Dimensions of the embedding model               | `1536`        |
| `cluster_url`          | `clusterUrl`         | URL for the Weaviate server                     | `None`        |
| `auth_client_secret`   | `apiKey`             | API key for Weaviate authentication             | `None`        |
| `additional_headers`   | `additionalHeaders`  | Additional headers to include in requests       | `None`        |