To use Together embedding models, set the TOGETHER_API_KEY environment variable. You can obtain the Together API key from the Together Platform.
The embedding_model_dims parameter for vector_store should be set to 768 for Together embedder.
import os
from mem0 import Memory
os.environ["TOGETHER_API_KEY"] = "your_api_key"
os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
config = {
"embedder": {
"provider": "together",
"config": {
"model": "togethercomputer/m2-bert-80M-8k-retrieval"
}
}
}
m = Memory.from_config(config)
messages = [
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
{"role": "user", "content": "Iām not a big fan of thriller movies but I love sci-fi movies."},
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
]
m.add(messages, user_id="john")
| Parameter | Description | Default Value |
|---|
model | The name of the embedding model to use | togethercomputer/m2-bert-80M-8k-retrieval |
embedding_dims | Dimensions of the embedding model | 768 |
api_key | The Together API key | None |
