---
title: "pgvector"
description: "Use pgvector as a vector store in Mem0 for PostgreSQL-based vector similarity search with open-source simplicity."
---
[pgvector](https://github.com/pgvector/pgvector) is an open-source vector similarity search extension for Postgres. After connecting to Postgres, run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.

### Usage

<CodeGroup>
```python Python
import os
from mem0 import Memory

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

config = {
    "vector_store": {
        "provider": "pgvector",
        "config": {
            "user": "test",
            "password": "123",
            "host": "127.0.0.1",
            "port": "5432",
        }
    }
}

m = Memory.from_config(config)
messages = [
    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
    {"role": "assistant", "content": "How about thriller movies? 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
import { Memory } from 'mem0ai/oss';

const config = {
  vectorStore: {
    provider: 'pgvector',
    config: {
      collectionName: 'memories',
      embeddingModelDims: 1536,
      user: 'test',
      password: '123',
      host: '127.0.0.1',
      port: 5432,
      dbname: 'vector_store', // Optional; TypeScript OSS defaults to `vector_store` when omitted
      diskann: false, // Optional, requires pgvectorscale extension
      hnsw: false, // Optional, for HNSW indexing
    },
  },
};

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 thriller movies? 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>

### Config

Here are the parameters available for configuring pgvector:

| Parameter | Description | Default Value |
| --- | --- | --- |
| `dbname` | The name of the database | `postgres` |
| `collection_name` | The name of the collection | `mem0` |
| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
| `user` | User name to connect to the database | `None` |
| `password` | Password to connect to the database | `None` |
| `host` | The host where the Postgres server is running | `None` |
| `port` | The port where the Postgres server is running | `None` |
| `diskann` | Whether to use diskann for vector similarity search (requires pgvectorscale) | `True` |
| `hnsw` | Whether to use hnsw for vector similarity search | `False` |
| `sslmode` | SSL mode for PostgreSQL connection (e.g., 'require', 'prefer', 'disable') | `None` |
| `connection_string` | PostgreSQL connection string (overrides individual connection parameters) | `None` |
| `connection_pool` | psycopg2 connection pool object (overrides connection string and individual parameters) | `None` |

**Note (TypeScript OSS):** If you omit `dbname`, the TypeScript client uses the database name `vector_store`. Python defaults to `postgres` for `dbname`, as in the table above.

**Note**: The connection parameters have the following priority:
1. `connection_pool` (highest priority)
2. `connection_string`
3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)