-
Notifications
You must be signed in to change notification settings - Fork 1.1k
Open
Description
I am not sure if it is a good idea.. just AI amateur-enthusiast here. but i would like to try different embeddings. selecting ollama as embedding defaults to llama2.. but could we mb use env var for that
mb allow modifying dimension also?
option 1: separate variable for name
EMBEDDING_MODEL=ollama
EMBEDDING_MODEL_NAME=nomic-embed-text
option 2: spliting value (not ideal i guess)
EMBEDDING_MODEL=ollama/nomic-embed-text
Alt: mb allow fully custom HuggingFaceEmbeddings ?
in load_embedding_model (chains.py@L36-39):
if embedding_model_name == "ollama":
embeddings = OllamaEmbeddings(
base_url=config["ollama_base_url"], model="llama2"
)
Metadata
Metadata
Assignees
Labels
No labels