kartik-mem0
fbb8e71224
Each fix verified against mem0/vector_stores/ source and configs:
- baidu: table_name default mem0_table → mem0 (BaiduDBConfig)
- langchain: TS import mem0ai → mem0ai/oss; fix undefined LangchainVectorStore
variable to use MemoryVectorStore directly
- mongodb: collection_name default mem0_collection → mem0; mongo_uri default
corrected to mongodb://localhost:27017 (MongoDBConfig)
- neon: hnsw default False → True (PGVectorConfig.hnsw = True)
- neptune_analytics: extra name vector_stores → vector-stores (pyproject.toml)
- pgvector: diskann default True → False; hnsw default False → True
(PGVectorConfig)
- upstash-vector: move enable_embeddings inside config: {} block
(UpstashVectorConfig field, not top-level VectorStoreConfig)
- valkey: remove non-existent distance_metric row (not in ValkeyConfig);
fix extra name vector_stores → vector-stores
- vertex_ai: region is required (no default in GoogleMatchingEngineConfig)
- weaviate: install pip install weaviate weaviate-client → weaviate-client
(weaviate is not a separate package)
- overview: update TS supported vector DBs list to reflect actual
mem0-ts/src/oss/src/vector_stores/ files
114 lines
4.1 KiB
Plaintext
114 lines
4.1 KiB
Plaintext
---
|
|
title: LangChain
|
|
description: "Use LangChain as a unified vector store provider in Mem0 to access multiple vector databases through one interface."
|
|
---
|
|
|
|
Mem0 supports LangChain as a provider for vector store integration. LangChain provides a unified interface to various vector databases, making it easy to integrate different vector store providers through a consistent API.
|
|
|
|
<Note>
|
|
When using LangChain as your vector store provider, you must set the collection name to "mem0". This is a required configuration for proper integration with Mem0.
|
|
</Note>
|
|
|
|
## Usage
|
|
|
|
<CodeGroup>
|
|
```python Python
|
|
import os
|
|
from mem0 import Memory
|
|
from langchain_chroma import Chroma
|
|
from langchain_openai import OpenAIEmbeddings
|
|
|
|
# Initialize a LangChain vector store
|
|
embeddings = OpenAIEmbeddings()
|
|
vector_store = Chroma(
|
|
persist_directory="./chroma_db",
|
|
embedding_function=embeddings,
|
|
collection_name="mem0" # Required collection name
|
|
)
|
|
|
|
# Pass the initialized vector store to the config
|
|
config = {
|
|
"vector_store": {
|
|
"provider": "langchain",
|
|
"config": {
|
|
"client": vector_store
|
|
}
|
|
}
|
|
}
|
|
|
|
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";
|
|
import { OpenAIEmbeddings } from "@langchain/openai";
|
|
import { MemoryVectorStore } from "langchain/vectorstores/memory";
|
|
|
|
const embeddings = new OpenAIEmbeddings();
|
|
const vectorStore = new MemoryVectorStore(embeddings);
|
|
|
|
const config = {
|
|
"vector_store": {
|
|
"provider": "langchain",
|
|
"config": { "client": vectorStore }
|
|
}
|
|
}
|
|
|
|
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>
|
|
|
|
## Supported LangChain Vector Stores
|
|
|
|
LangChain supports a wide range of vector store providers, including:
|
|
|
|
- Chroma
|
|
- FAISS
|
|
- Pinecone
|
|
- Weaviate
|
|
- Milvus
|
|
- Qdrant
|
|
- And many more
|
|
|
|
You can use any of these vector store instances directly in your configuration. For a complete and up-to-date list of available providers, refer to the [LangChain Vector Stores documentation](https://python.langchain.com/docs/integrations/vectorstores).
|
|
|
|
## Limitations
|
|
|
|
When using LangChain as a vector store provider, there are some limitations to be aware of:
|
|
|
|
1. **Bulk Operations**: The `get_all` and `delete_all` operations are not supported when using LangChain as the vector store provider. This is because LangChain's vector store interface doesn't provide standardized methods for these bulk operations across all providers.
|
|
|
|
2. **Provider-Specific Features**: Some advanced features may not be available depending on the specific vector store implementation you're using through LangChain.
|
|
|
|
## Provider-Specific Configuration
|
|
|
|
When using LangChain as a vector store provider, you'll need to:
|
|
|
|
1. Set the appropriate environment variables for your chosen vector store provider
|
|
2. Import and initialize the specific vector store class you want to use
|
|
3. Pass the initialized vector store instance to the config
|
|
|
|
<Note>
|
|
Make sure to install the necessary LangChain packages and any provider-specific dependencies.
|
|
</Note>
|
|
|
|
## Config
|
|
|
|
All available parameters for the `langchain` vector store config are present in [Master List of All Params in Config](../config).
|