my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

my-project-public — gitlawb

#1	---
#2	title: Hugging Face
#3	---
#4
#5	You can use embedding models from Huggingface to run Mem0 locally.
#6
#7	### Usage
#8
#9	```python
#10	import os
#11	from mem0 import Memory
#12
#13	os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
#14
#15	config = {
#16	"embedder": {
#17	"provider": "huggingface",
#18	"config": {
#19	"model": "multi-qa-MiniLM-L6-cos-v1"
#20	}
#21	}
#22	}
#23
#24	m = Memory.from_config(config)
#25	messages = [
#26	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#27	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#28	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#29	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#30	]
#31	m.add(messages, user_id="john")
#32	```
#33
#34	### Using Text Embeddings Inference (TEI)
#35
#36	You can also use Hugging Face's Text Embeddings Inference service for faster and more efficient embeddings:
#37
#38	```python
#39	import os
#40	from mem0 import Memory
#41
#42	os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
#43
#44	# Using HuggingFace Text Embeddings Inference API
#45	config = {
#46	"embedder": {
#47	"provider": "huggingface",
#48	"config": {
#49	"huggingface_base_url": "http://localhost:3000/v1"
#50	}
#51	}
#52	}
#53
#54	m = Memory.from_config(config)
#55	m.add("This text will be embedded using the TEI service.", user_id="john")
#56	```
#57
#58	To run the TEI service, you can use Docker:
#59
#60	```bash
#61	docker run -d -p 3000:80 -v huggingfacetei:/data --platform linux/amd64 \
#62	ghcr.io/huggingface/text-embeddings-inference:cpu-1.6 \
#63	--model-id BAAI/bge-small-en-v1.5
#64	```
#65
#66	### Config
#67
#68	Here are the parameters available for configuring Huggingface embedder:
#69
#70	\| Parameter \| Description \| Default Value \|
#71	\| --- \| --- \| --- \|
#72	\| `model` \| The name of the model to use \| `multi-qa-MiniLM-L6-cos-v1` \|
#73	\| `embedding_dims` \| Dimensions of the embedding model \| `selected_model_dimensions` \|
#74	\| `model_kwargs` \| Additional arguments for the model \| `None` \|
#75	\| `huggingface_base_url` \| URL to connect to Text Embeddings Inference (TEI) API \| `None` \|

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public