my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	You can use embedding models from Ollama to run Mem0 locally.
#2
#3	### Usage
#4
#5	<CodeGroup>
#6	```python Python
#7	import os
#8	from mem0 import Memory
#9
#10	os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
#11
#12	config = {
#13	"embedder": {
#14	"provider": "ollama",
#15	"config": {
#16	"model": "mxbai-embed-large"
#17	}
#18	}
#19	}
#20
#21	m = Memory.from_config(config)
#22	messages = [
#23	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#24	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#25	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#26	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#27	]
#28	m.add(messages, user_id="john")
#29	```
#30
#31	```typescript TypeScript
#32	import { Memory } from 'mem0ai/oss';
#33
#34	const config = {
#35	embedder: {
#36	provider: 'ollama',
#37	config: {
#38	model: 'nomic-embed-text:latest', // or any other Ollama embedding model
#39	url: 'http://localhost:11434', // Ollama server URL
#40	},
#41	},
#42	};
#43
#44	const memory = new Memory(config);
#45	const messages = [
#46	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#47	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#48	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#49	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#50	]
#51	await memory.add(messages, { userId: "john" });
#52	```
#53	</CodeGroup>
#54
#55	### Config
#56
#57	Here are the parameters available for configuring Ollama embedder:
#58
#59	<Tabs>
#60	<Tab title="Python">
#61	\| Parameter \| Description \| Default Value \|
#62	\| --- \| --- \| --- \|
#63	\| `model` \| The name of the Ollama model to use \| `nomic-embed-text` \|
#64	\| `embedding_dims` \| Dimensions of the embedding model \| `512` \|
#65	\| `ollama_base_url` \| Base URL for ollama connection \| `None` \|
#66	</Tab>
#67	<Tab title="TypeScript">
#68	\| Parameter \| Description \| Default Value \|
#69	\| --- \| --- \| --- \|
#70	\| `model` \| The name of the Ollama model to use \| `nomic-embed-text:latest` \|
#71	\| `url` \| Base URL for Ollama server \| `http://localhost:11434` \|
#72	\| `embeddingDims` \| Dimensions of the embedding model \| 768
#73	</Tab>
#74	</Tabs>

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public