my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: LangChain
#3	---
#4
#5
#6	Mem0 supports LangChain as a provider to access a wide range of LLM models. LangChain is a framework for developing applications powered by language models, making it easy to integrate various LLM providers through a consistent interface.
#7
#8	For a complete list of available chat models supported by LangChain, refer to the [LangChain Chat Models documentation](https://python.langchain.com/docs/integrations/chat).
#9
#10	## Usage
#11
#12	<CodeGroup>
#13	```python Python
#14	import os
#15	from mem0 import Memory
#16	from langchain_openai import ChatOpenAI
#17
#18	# Set necessary environment variables for your chosen LangChain provider
#19	os.environ["OPENAI_API_KEY"] = "your-api-key"
#20
#21	# Initialize a LangChain model directly
#22	openai_model = ChatOpenAI(
#23	model="gpt-4.1-nano-2025-04-14",
#24	temperature=0.2,
#25	max_tokens=2000
#26	)
#27
#28	# Pass the initialized model to the config
#29	config = {
#30	"llm": {
#31	"provider": "langchain",
#32	"config": {
#33	"model": openai_model
#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/oss';
#50	import { ChatOpenAI } from "@langchain/openai";
#51
#52	// Initialize a LangChain model directly
#53	const openaiModel = new ChatOpenAI({
#54	modelName: "gpt-4",
#55	temperature: 0.2,
#56	maxTokens: 2000,
#57	apiKey: process.env.OPENAI_API_KEY,
#58	});
#59
#60	const config = {
#61	llm: {
#62	provider: 'langchain',
#63	config: {
#64	model: openaiModel,
#65	},
#66	},
#67	};
#68
#69	const memory = new Memory(config);
#70	const messages = [
#71	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#72	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#73	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#74	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#75	]
#76	await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
#77	```
#78	</CodeGroup>
#79
#80	## Supported LangChain Providers
#81
#82	LangChain supports a wide range of LLM providers, including:
#83
#84	- OpenAI (`ChatOpenAI`)
#85	- Anthropic (`ChatAnthropic`)
#86	- Google (`ChatGoogleGenerativeAI`, `ChatGooglePalm`)
#87	- Mistral (`ChatMistralAI`)
#88	- Ollama (`ChatOllama`)
#89	- Azure OpenAI (`AzureChatOpenAI`)
#90	- HuggingFace (`HuggingFaceChatEndpoint`)
#91	- And many more
#92
#93	You can use any of these model instances directly in your configuration. For a complete and up-to-date list of available providers, refer to the [LangChain Chat Models documentation](https://python.langchain.com/docs/integrations/chat).
#94
#95	## Provider-Specific Configuration
#96
#97	When using LangChain as a provider, you'll need to:
#98
#99	1. Set the appropriate environment variables for your chosen LLM provider
#100	2. Import and initialize the specific model class you want to use
#101	3. Pass the initialized model instance to the config
#102
#103	<Note>
#104	Make sure to install the necessary LangChain packages and any provider-specific dependencies.
#105	</Note>
#106
#107	## Config
#108
#109	All available parameters for the `langchain` config are present in [Master List of All Params in Config](../config).
#110

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public