my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	---
#2	title: LangChain
#3	---
#4
#5	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.
#6
#7	<Note>
#8	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.
#9	</Note>
#10
#11	## Usage
#12
#13	<CodeGroup>
#14	```python Python
#15	import os
#16	from mem0 import Memory
#17	from langchain_community.vectorstores import Chroma
#18	from langchain_openai import OpenAIEmbeddings
#19
#20	# Initialize a LangChain vector store
#21	embeddings = OpenAIEmbeddings()
#22	vector_store = Chroma(
#23	persist_directory="./chroma_db",
#24	embedding_function=embeddings,
#25	collection_name="mem0" # Required collection name
#26	)
#27
#28	# Pass the initialized vector store to the config
#29	config = {
#30	"vector_store": {
#31	"provider": "langchain",
#32	"config": {
#33	"client": vector_store
#34	}
#35	}
#36	}
#37
#38	m = Memory.from_config(config)
#39	messages = [
#40	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#41	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#42	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#43	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#44	]
#45	m.add(messages, user_id="alice", metadata={"category": "movies"})
#46	```
#47
#48	```typescript TypeScript
#49	import { Memory } from "mem0ai";
#50	import { OpenAIEmbeddings } from "@langchain/openai";
#51	import { MemoryVectorStore as LangchainMemoryStore } from "langchain/vectorstores/memory";
#52
#53	const embeddings = new OpenAIEmbeddings();
#54	const vectorStore = new LangchainVectorStore(embeddings);
#55
#56	const config = {
#57	"vector_store": {
#58	"provider": "langchain",
#59	"config": { "client": vectorStore }
#60	}
#61	}
#62
#63	const memory = new Memory(config);
#64
#65	const messages = [
#66	{ role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
#67	{ role: "assistant", content: "How about thriller movies? They can be quite engaging." },
#68	{ role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
#69	{ role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." }
#70	]
#71
#72	await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
#73	```
#74	</CodeGroup>
#75
#76	## Supported LangChain Vector Stores
#77
#78	LangChain supports a wide range of vector store providers, including:
#79
#80	- Chroma
#81	- FAISS
#82	- Pinecone
#83	- Weaviate
#84	- Milvus
#85	- Qdrant
#86	- And many more
#87
#88	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).
#89
#90	## Limitations
#91
#92	When using LangChain as a vector store provider, there are some limitations to be aware of:
#93
#94	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.
#95
#96	2. Provider-Specific Features: Some advanced features may not be available depending on the specific vector store implementation you're using through LangChain.
#97
#98	## Provider-Specific Configuration
#99
#100	When using LangChain as a vector store provider, you'll need to:
#101
#102	1. Set the appropriate environment variables for your chosen vector store provider
#103	2. Import and initialize the specific vector store class you want to use
#104	3. Pass the initialized vector store instance to the config
#105
#106	<Note>
#107	Make sure to install the necessary LangChain packages and any provider-specific dependencies.
#108	</Note>
#109
#110	## Config
#111
#112	All available parameters for the `langchain` vector store config are present in [Master List of All Params in Config](../config).
#113

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public