haylan/LLM-Server
1
0
Fork 0
Code Issues 9 Pull Requests Actions Packages Projects Releases Wiki Activity

fix(litellm): prefix EMBEDDING__MODEL with openai/ for litellm-pgvector

Browse Source 
litellm.aembedding can't infer a provider from a bare model name plus a
custom api_base — litellm-pgvector's embedding_service.py was hitting
'litellm.BadRequestError: LLM Provider NOT provided' on every query-time
embedding (i.e. every search). Same openai/ prefix already used for
qwen3.8-27b-local and local-embedding in litellm-config.yaml.
This commit is contained in:
haylan
2026-09-02 21:32:23 +00:00
parent 3eda4e3ec0
commit 213550e44b
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker-compose.yml
+5 -1
View File
@@ -271,7 +271,11 @@ services:
- SERVER_API_KEY=${LITELLM_PGVECTOR_API_KEY} - SERVER_API_KEY=${LITELLM_PGVECTOR_API_KEY}
# Calls back into litellm for embeddings, same pattern as any other # Calls back into litellm for embeddings, same pattern as any other
# workload — see docs/proxy-key-onboarding.md for issuing this key. # workload — see docs/proxy-key-onboarding.md for issuing this key.
- EMBEDDING__MODEL=local-embedding # openai/ prefix required — litellm.aembedding can't infer a provider
# from a bare model name plus a custom api_base (raises "LLM Provider
# NOT provided"), same reasoning as the openai/ prefix on
# qwen3.8-27b-local and local-embedding in litellm-config.yaml.
- EMBEDDING__MODEL=openai/local-embedding
- EMBEDDING__BASE_URL=http://litellm:4000 - EMBEDDING__BASE_URL=http://litellm:4000
- EMBEDDING__API_KEY=${LITELLM_PGVECTOR_EMBEDDING_KEY} - EMBEDDING__API_KEY=${LITELLM_PGVECTOR_EMBEDDING_KEY}
- EMBEDDING__DIMENSIONS=768 - EMBEDDING__DIMENSIONS=768