## Usage

Use [Neon](https://neon.com/) as a vector store in Mem0, powered by PostgreSQL and the [pgvector extension](https://neon.com/docs/extensions/pgvector). Neon is a serverless Postgres platform. Since Mem0 supports Postgres through the `pgvector` provider, Neon can be used with a standard Postgres connection string.

### Python

```python
import os

from dotenv import load_dotenv
from mem0 import Memory

load_dotenv()

config = {
    "vector_store": {
        "provider": "pgvector",
        "config": {
            "connection_string": os.environ["DATABASE_URL"],
            "collection_name": "memories",
            "embedding_model_dims": 1536,
            "hnsw": True,
        },
    },
}

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"})

results = m.search(
    "What movies should I recommend?",
    filters={"user_id": "alice"},
)

print(results)
```

### TypeScript

```typescript
import "dotenv/config";
import { Memory } from "mem0ai/oss";

const m = new Memory({
  vectorStore: {
    provider: "pgvector",
    config: {
      connectionString: process.env.DATABASE_URL!,
      ssl: {
        rejectUnauthorized: false,
      },
      collectionName: "memories",
      dimension: 1536,
      embeddingModelDims: 1536,
      hnsw: true,
    },
  },
});

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

await m.add(messages, {
  userId: "alice",
  metadata: { category: "movies" },
});

const results = await m.search("What movies should I recommend?", {
  filters: { user_id: "alice" },
});

console.log(results);
```

## SQL Migration  
You don’t need to run any SQL migrations. Mem0 creates the collection table when it initializes the `pgvector` store.

## Environment

```
OPENAI_API_KEY=sk-xx...
DATABASE_URL=postgresql://user:password@ep-example.us-east-2.aws.neon.tech/neondb?sslmode=require
```

## Config

- Python

- TypeScript

| Parameter | Description | Default Value |
| --- | --- | --- |
| `connection_string` | Neon Postgres connection string. | Required |
| `collection_name` | Name for the vector collection. | `mem0` |
| `embedding_model_dims` | Embedding model dimensions. | `1536` |
| `hnsw` | Enables HNSW indexing. | `False` |
| `sslmode` | PostgreSQL SSL mode. Use `require` for Neon. | Driver default |

### Best Practices

1. **Index Selection**:   - Use `hnsw` for faster search performance when memory usage is not a constraint  
   - Manage indexes manually if you need a different pgvector index strategy  
2. **Connection String**:   - Always use environment variables or even better, a secret manager for sensitive information in the connection string   
   - Format: `postgresql://user:password@host:port/database`

## Indexing

The `pgvector` provider can create an HNSW index for faster vector search.

- Set `hnsw` to `true` to enable a Hierarchical Navigable Small World index.
- Leave `hnsw` as `false` if you want to create or manage indexes yourself.

## Similarity Search

The `pgvector` provider uses cosine similarity for vector search. Make sure your embedding dimensions match the configured `embedding_model_dims` value.