LLM-Server/vendor/litellm-pgvector/requirements.txt at ec476c7950cffef955580b089481b4322291a600 - LLM-Server - Gitea, hosted by Arthur

haylan/LLM-Server

Files

T

haylanandClaude-Bot e7983f0710 Revert "feat(knowledgebase): replace litellm-pgvector connector with memory-retrieval"

This reverts commit abeadc49c8.

Restores vendor/litellm-pgvector/ and the vector_store_registry wiring
(in-band file_search tool-call support) at the user's request, after
re-confirming against docs.litellm.ai/docs/completion/knowledgebase and
litellm-pgvector's own README that pg_vector is still not an in-process
vector_store_registry backend -- it requires this same standalone
connector service either way, so there is no simpler 'native' path that
was missed. Trading back in: 793 lines of vendored code, the untested
Prisma migration, and the git-context build risk noted in VENDORED.md
(all flagged as unverified against real hardware in issue #24), in
exchange for the file_search in-band tool call memory-retrieval did not
support.

Conflicts resolved on top of later commits (Redis, update.sh key-minting
fold-in):
- .env.example / docs/memory-knowledgebase.md: kept the auto-mint-via-
  update.sh language, renamed MEMORY_RETRIEVAL_* back to
  LITELLM_PGVECTOR_*.
- scripts/generate-secrets.sh: left deleted -- its job was folded into
  update.sh in 24d749b, unrelated to this revert.
- scripts/update.sh: renamed the MEMORY_RETRIEVAL_* secret/mint calls to
  LITELLM_PGVECTOR_* to match.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018WHfjWrSEcGhCoeu6dQfDa

2026-09-02 22:45:08 +02:00

10 lines

199 B

Plaintext

Raw Blame History

 fastapi==0.104.1
 uvicorn[standard]==0.24.0
 prisma==0.11.0
 python-dotenv==1.0.0
 pydantic>=2.5.0
 psycopg2-binary==2.9.7
 pgvector==0.2.4
 python-multipart==0.0.6
 litellm==1.74.3
 pydantic-settings==2.1.0