feat(knowledgebase): replace litellm-pgvector connector with memory-retrieval

Per docs/research/langchain-pgvector-vs-litellm-pgvector.md (issue #25):
the vendored litellm-pgvector connector (793 lines, Prisma migrations, a
fragile git-context build) is replaced by a ~90-line FastAPI service
(services/memory-retrieval/) wrapping langchain_postgres.PGVector directly
against pgvector-db. Same gateway boundary — it still calls litellm for
embeddings, nothing talks to Postgres or the model directly except this
service.

- New services/memory-retrieval/ (main.py, Dockerfile, requirements.txt):
  POST /ingest, POST /query, GET /health.
- docker-compose.yml: litellm-pgvector service replaced by memory-retrieval;
  pgvector-db and embedding-server untouched.
- litellm-config.yaml: vector_store_registry block removed (no
  langchain_postgres provider exists to register against; callers query
  memory-retrieval directly instead of an in-band file_search tool call —
  that mechanism was never confirmed working per issue #24 anyway).
- scripts/ingest-memory.sh rewritten for the new /ingest endpoint (same
  per-line chunking, no dedup).
- .env vars renamed: LITELLM_PGVECTOR_API_KEY/LITELLM_PGVECTOR_EMBEDDING_KEY
  -> MEMORY_RETRIEVAL_API_KEY/MEMORY_RETRIEVAL_EMBEDDING_KEY.
- vendor/litellm-pgvector/ removed entirely.
- docs/memory-knowledgebase.md updated for the new setup/query flow.

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

docker-compose.yml

@@ -214,38 +214,30 @@ services:
       retries: 10
 
   # LiteLLM's native knowledgebase/vector-store feature has no Qdrant backend
-  # (the qdrant service above only serves Open WebUI's own RAG/Memory) — this
-  # companion service (github.com/BerriAI/litellm-pgvector) is the only
-  # self-hosted path. No published image exists yet, so this builds from a
-  # vendored copy in vendor/litellm-pgvector/ (see that dir's README) rather
-  # than a remote git build context — the server's Docker/BuildKit couldn't
-  # do an authenticated-looking clone of a public github.com repo (fails
-  # with "could not read Username ... terminal prompts disabled"), and
-  # vendoring sidesteps needing that debugged. See
-  # docs/research/litellm-knowledgebase.md.
-  # ponytail: unverified against real hardware — Prisma migration behavior on
-  # first boot and the exact vector_store_registry field names for the
-  # pg_vector provider need a live smoke test. See issue #24.
-  litellm-pgvector:
+  # (the qdrant service above only serves Open WebUI's own RAG/Memory), so
+  # this small in-repo service wraps langchain_postgres.PGVector directly
+  # against pgvector-db instead — simpler than a vendored third-party
+  # connector (see docs/research/langchain-pgvector-vs-litellm-pgvector.md,
+  # which replaced the earlier litellm-pgvector approach). It still calls
+  # back into litellm for embeddings, same gateway boundary as everything
+  # else in this stack.
+  memory-retrieval:
     build:
-      context: ./vendor/litellm-pgvector
-    container_name: litellm-pgvector
+      context: ./services/memory-retrieval
+    container_name: memory-retrieval
     depends_on:
       pgvector-db:
         condition: service_healthy
       litellm:
         condition: service_healthy
     environment:
-      - DATABASE_URL=postgresql://litellm_pgvector:${PGVECTOR_DB_PASSWORD}@pgvector-db:5432/litellm_pgvector
-      - SERVER_API_KEY=${LITELLM_PGVECTOR_API_KEY}
-      # Calls back into litellm for embeddings, same pattern as any other
-      # workload — see docs/proxy-key-onboarding.md for issuing this key.
-      - EMBEDDING__MODEL=local-embedding
-      - EMBEDDING__BASE_URL=http://litellm:4000
-      - EMBEDDING__API_KEY=${LITELLM_PGVECTOR_EMBEDDING_KEY}
-      - EMBEDDING__DIMENSIONS=768
-    expose:
-      - "8000"
+      - DATABASE_URL=postgresql+psycopg://litellm_pgvector:${PGVECTOR_DB_PASSWORD}@pgvector-db:5432/litellm_pgvector
+      - LITELLM_BASE_URL=http://litellm:4000/v1
+      # A virtual key for this workload — see docs/proxy-key-onboarding.md.
+      - LITELLM_API_KEY=${MEMORY_RETRIEVAL_EMBEDDING_KEY}
+      - EMBEDDING_MODEL=local-embedding
+      - SERVER_API_KEY=${MEMORY_RETRIEVAL_API_KEY}
+      - COLLECTION_NAME=memory-and-notes
     restart: unless-stopped
     networks: [ai-stack]