pgvector - Mem0

Documentation Index

Fetch the complete documentation index at: /llms.txt

Use this file to discover all available pages before exploring further.

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

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"})

import { Memory } from "mem0ai/oss";

const config = {
  vectorStore: {
    provider: "pgvector",
    config: {
      collectionName: "memories",
      embeddingModelDims: 1536,
      connectionString: "postgresql://test:123@localhost:5432/vector_store",
      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" } });

Config

Here are the parameters available for configuring pgvector:

Parameter	SDK	Description	Default Value
`connectionString`	TypeScript OSS	PostgreSQL connection string for direct connections. When set, Mem0 connects to the target database directly and skips the bootstrap `postgres` database flow.	`None`
`ssl`	TypeScript OSS	SSL option passed directly to `pg`, either `true` or an SSL config object, for both `connectionString` and split-field connections.	`None`
`dbname`	TypeScript OSS	Split-field database name. This is only used when `connectionString` is absent.	`vector_store`
`collectionName`	TypeScript OSS	Collection name.	`memories`
`embeddingModelDims`	TypeScript OSS	Dimensions of the embedding model.	Required
`user`	TypeScript OSS + Python	Database user for split-field connections.	`None`
`password`	TypeScript OSS + Python	Database password for split-field connections.	`None`
`host`	TypeScript OSS + Python	Database host for split-field connections.	`None`
`port`	TypeScript OSS + Python	Database port for split-field connections.	`None`
`diskann`	TypeScript OSS + Python	Whether to use DiskANN for vector similarity search, requires pgvectorscale.	`False`
`hnsw`	TypeScript OSS + Python	Whether to use HNSW for vector similarity search.	TypeScript OSS: `False`, Python: `True`
`connection_string`	Python only	PostgreSQL connection string, overrides individual connection parameters.	`None`
`sslmode`	Python only	SSL mode for PostgreSQL connections, such as `require`, `prefer`, or `disable`.	`None`
`connection_pool`	Python only	psycopg connection pool object, overrides connection string and individual connection parameters.	`None`

TypeScript OSS: Use connectionString plus optional ssl for managed Postgres setups. If you omit connectionString, Mem0 falls back to split fields and uses dbname, user, password, host, port, and optional ssl.Python: The Python SDK uses snake_case keys such as connection_string, sslmode, collection_name, and embedding_model_dims.Python connection priority:

connection_pool (highest priority)
connection_string
Individual connection parameters (user, password, host, port, sslmode)