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 to access a wide range of embedding models. LangChain is a framework for developing applications powered by language models, making it easy to integrate various embedding providers through a consistent interface.
#6
#7	For a complete list of available embedding models supported by LangChain, refer to the [LangChain Text Embedding documentation](https://python.langchain.com/docs/integrations/text_embedding/).
#8
#9	## Usage
#10
#11	<CodeGroup>
#12	```python Python
#13	import os
#14	from mem0 import Memory
#15	from langchain_openai import OpenAIEmbeddings
#16
#17	# Set necessary environment variables for your chosen LangChain provider
#18	os.environ["OPENAI_API_KEY"] = "your-api-key"
#19
#20	# Initialize a LangChain embeddings model directly
#21	openai_embeddings = OpenAIEmbeddings(
#22	model="text-embedding-3-small",
#23	dimensions=1536
#24	)
#25
#26	# Pass the initialized model to the config
#27	config = {
#28	"embedder": {
#29	"provider": "langchain",
#30	"config": {
#31	"model": openai_embeddings
#32	}
#33	}
#34	}
#35
#36	m = Memory.from_config(config)
#37	messages = [
#38	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#39	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#40	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#41	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#42	]
#43	m.add(messages, user_id="alice", metadata={"category": "movies"})
#44	```
#45
#46	```typescript TypeScript
#47	import { Memory } from 'mem0ai/oss';
#48	import { OpenAIEmbeddings } from "@langchain/openai";
#49
#50	// Initialize a LangChain embeddings model directly
#51	const openaiEmbeddings = new OpenAIEmbeddings({
#52	modelName: "text-embedding-3-small",
#53	dimensions: 1536,
#54	apiKey: process.env.OPENAI_API_KEY,
#55	});
#56
#57	const config = {
#58	embedder: {
#59	provider: 'langchain',
#60	config: {
#61	model: openaiEmbeddings,
#62	},
#63	},
#64	};
#65
#66	const memory = new Memory(config);
#67	const messages = [
#68	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#69	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#70	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#71	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#72	]
#73	await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
#74	```
#75	</CodeGroup>
#76
#77	## Supported LangChain Embedding Providers
#78
#79	LangChain supports a wide range of embedding providers, including:
#80
#81	- OpenAI (`OpenAIEmbeddings`)
#82	- Cohere (`CohereEmbeddings`)
#83	- Google (`VertexAIEmbeddings`)
#84	- Hugging Face (`HuggingFaceEmbeddings`)
#85	- Sentence Transformers (`HuggingFaceEmbeddings`)
#86	- Azure OpenAI (`AzureOpenAIEmbeddings`)
#87	- Ollama (`OllamaEmbeddings`)
#88	- Together (`TogetherEmbeddings`)
#89	- And many more
#90
#91	You can use any of these model instances directly in your configuration. For a complete and up-to-date list of available embedding providers, refer to the [LangChain Text Embedding documentation](https://python.langchain.com/docs/integrations/text_embedding/).
#92
#93	## Provider-Specific Configuration
#94
#95	When using LangChain as an embedder provider, you'll need to:
#96
#97	1. Set the appropriate environment variables for your chosen embedding provider
#98	2. Import and initialize the specific model class you want to use
#99	3. Pass the initialized model instance to the config
#100
#101	### Examples with Different Providers
#102
#103	<CodeGroup>
#104	#### HuggingFace Embeddings
#105
#106	```python Python
#107	from langchain_huggingface import HuggingFaceEmbeddings
#108
#109	# Initialize a HuggingFace embeddings model
#110	hf_embeddings = HuggingFaceEmbeddings(
#111	model_name="BAAI/bge-small-en-v1.5",
#112	encode_kwargs={"normalize_embeddings": True}
#113	)
#114
#115	config = {
#116	"embedder": {
#117	"provider": "langchain",
#118	"config": {
#119	"model": hf_embeddings
#120	}
#121	}
#122	}
#123	```
#124
#125	```typescript TypeScript
#126	import { Memory } from 'mem0ai/oss';
#127	import { HuggingFaceEmbeddings } from "@langchain/community/embeddings/hf";
#128
#129	// Initialize a HuggingFace embeddings model
#130	const hfEmbeddings = new HuggingFaceEmbeddings({
#131	modelName: "BAAI/bge-small-en-v1.5",
#132	encode: {
#133	normalize_embeddings: true,
#134	},
#135	});
#136
#137	const config = {
#138	embedder: {
#139	provider: 'langchain',
#140	config: {
#141	model: hfEmbeddings,
#142	},
#143	},
#144	};
#145	```
#146	</CodeGroup>
#147
#148	<CodeGroup>
#149	#### Ollama Embeddings
#150
#151	```python Python
#152	from langchain_ollama import OllamaEmbeddings
#153
#154	# Initialize an Ollama embeddings model
#155	ollama_embeddings = OllamaEmbeddings(
#156	model="nomic-embed-text"
#157	)
#158
#159	config = {
#160	"embedder": {
#161	"provider": "langchain",
#162	"config": {
#163	"model": ollama_embeddings
#164	}
#165	}
#166	}
#167	```
#168
#169	```typescript TypeScript
#170	import { Memory } from 'mem0ai/oss';
#171	import { OllamaEmbeddings } from "@langchain/community/embeddings/ollama";
#172
#173	// Initialize an Ollama embeddings model
#174	const ollamaEmbeddings = new OllamaEmbeddings({
#175	model: "nomic-embed-text",
#176	baseUrl: "http://localhost:11434", // Ollama server URL
#177	});
#178
#179	const config = {
#180	embedder: {
#181	provider: 'langchain',
#182	config: {
#183	model: ollamaEmbeddings,
#184	},
#185	},
#186	};
#187	```
#188	</CodeGroup>
#189
#190	<Note>
#191	Make sure to install the necessary LangChain packages and any provider-specific dependencies.
#192	</Note>
#193
#194	## Config
#195
#196	All available parameters for the `langchain` embedder config are present in [Master List of All Params in Config](../config).
#197

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public