Pinecone - Mem0

Documentation Index

Fetch the complete documentation index at: /llms.txt

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

Pinecone is a fully managed vector database designed for machine learning applications, offering high performance vector search with low latency at scale. It’s particularly well-suited for semantic search, recommendation systems, and other AI-powered applications.

New: Pinecone integration now supports custom namespaces! Use the namespace parameter to logically separate data within the same index. This is especially useful for multi-tenant or multi-user applications.

Note: Before configuring Pinecone, you need to select an embedding model (e.g., OpenAI, Cohere, or custom models) and ensure the embedding_model_dims in your config matches your chosen model’s dimensions. For example, OpenAI’s text-embedding-3-small uses 1536 dimensions.

Usage

Python

TypeScript

import os
from mem0 import Memory

os.environ["OPENAI_API_KEY"] = "sk-xx"
os.environ["PINECONE_API_KEY"] = "your-api-key"

# Example using serverless configuration
config = {
    "vector_store": {
        "provider": "pinecone",
        "config": {
            "collection_name": "testing",
            "embedding_model_dims": 1536,  # Matches OpenAI's text-embedding-3-small
            "namespace": "my-namespace", # Optional: specify a namespace for multi-tenancy
            "serverless_config": {
                "cloud": "aws",  # Choose between 'aws' or 'gcp' or 'azure'
                "region": "us-east-1"
            },
            "metric": "cosine"
        }
    }
}

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';

// Set OPENAI_API_KEY and PINECONE_API_KEY in your environment
const config = {
  vectorStore: {
    provider: 'pinecone',
    config: {
      collectionName: 'testing',
      embeddingModelDims: 1536, // Matches OpenAI's text-embedding-3-small
      namespace: 'my-namespace', // Optional: specify a namespace for multi-tenancy
      serverlessConfig: {
        cloud: 'aws', // 'aws' | 'gcp' | 'azure'
        region: 'us-east-1',
      },
      metric: 'cosine',
    },
  },
};

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 Pinecone:

Important: You must choose either serverless_config or pod_config for your deployment, but not both.

Serverless Config Example

Python

TypeScript

config = {
    "vector_store": {
        "provider": "pinecone",
        "config": {
            "collection_name": "memory_index",
            "embedding_model_dims": 1536,  # For OpenAI's text-embedding-3-small
            "namespace": "my-namespace",  # Optional: custom namespace
            "serverless_config": {
                "cloud": "aws",  # or "gcp" or "azure"
                "region": "us-east-1"  # Choose appropriate region
            }
        }
    }
}

const config = {
  vectorStore: {
    provider: 'pinecone',
    config: {
      collectionName: 'memory_index',
      embeddingModelDims: 1536, // For OpenAI's text-embedding-3-small
      namespace: 'my-namespace', // Optional: custom namespace
      serverlessConfig: {
        cloud: 'aws', // 'gcp' | 'azure'
        region: 'us-east-1', // Choose appropriate region
      },
    },
  },
};

Pod Config Example

Python

TypeScript

config = {
    "vector_store": {
        "provider": "pinecone",
        "config": {
            "collection_name": "memory_index",
            "embedding_model_dims": 1536,  # For OpenAI's text-embedding-ada-002
            "namespace": "my-namespace",  # Optional: custom namespace
            "pod_config": {
                "environment": "gcp-starter",
                "replicas": 1,
                "pod_type": "starter"
            }
        }
    }
}

const config = {
  vectorStore: {
    provider: 'pinecone',
    config: {
      collectionName: 'memory_index',
      embeddingModelDims: 1536, // For OpenAI's text-embedding-ada-002
      namespace: 'my-namespace', // Optional: custom namespace
      podConfig: {
        environment: 'gcp-starter',
        replicas: 1,
        podType: 'starter',
      },
    },
  },
};