pratik/knowledge-base
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

deploy: route embedder through OpenAI-compat proxy instead of Ollama

Browse source 
The custom OpenAI-compatible endpoint (LiteLLM) serves the same
qwen3-embedding model and is reachable from the container in all
deployments; direct Ollama may not be. Vectors stay compatible because
the underlying model is the same.

Captured from a beast production hotfix.
This commit is contained in:
Pratik Narola 2026-05-23 15:03:02 +05:30
parent 0f0addb36b
commit 7cc8fc5112
1 changed files with 8 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
backend/mem0_manager.py
View file

@ -102,10 +102,16 @@ class Mem0Manager:
}, },
}, },
"embedder": { "embedder": {
"provider": "ollama", # Route embeddings through the OpenAI-compatible LiteLLM proxy
# rather than Ollama directly — the proxy is reachable from the
# container in all deployments, Ollama may not be. The model
# name is the same (qwen3-embedding:4b-q8_0); existing vectors
# generated via this path stay compatible.
"provider": "openai",
"config": { "config": {
"model": settings.embedding_model, "model": settings.embedding_model,
"ollama_base_url": settings.ollama_base_url, "api_key": settings.openai_api_key,
"openai_base_url": settings.openai_base_url,
"embedding_dims": settings.embedding_dims, "embedding_dims": settings.embedding_dims,
}, },
}, },