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>

vendor/litellm-pgvector/models.py

@@ -1,86 +0,0 @@
-from typing import Optional, Dict, Any, List
-from pydantic import BaseModel
-from datetime import datetime
-
-
-class VectorStoreCreateRequest(BaseModel):
-    name: str
-    file_ids: Optional[List[str]] = None
-    expires_after: Optional[Dict[str, Any]] = None
-    chunking_strategy: Optional[Dict[str, Any]] = None
-    metadata: Optional[Dict[str, Any]] = None
-
-
-class VectorStoreResponse(BaseModel):
-    id: str
-    object: str = "vector_store"
-    created_at: int
-    name: str
-    usage_bytes: int
-    file_counts: Dict[str, int]
-    status: str
-    expires_after: Optional[Dict[str, Any]] = None
-    expires_at: Optional[int] = None
-    last_active_at: Optional[int] = None
-    metadata: Optional[Dict[str, Any]] = None
-
-
-class VectorStoreSearchRequest(BaseModel):
-    query: str
-    limit: Optional[int] = 20
-    filters: Optional[Dict[str, Any]] = None
-    return_metadata: Optional[bool] = True
-
-
-class ContentChunk(BaseModel):
-    type: str = "text"
-    text: str
-
-
-class SearchResult(BaseModel):
-    file_id: str
-    filename: str
-    score: float
-    attributes: Optional[Dict[str, Any]] = None
-    content: List[ContentChunk]
-
-
-class VectorStoreSearchResponse(BaseModel):
-    object: str = "vector_store.search_results.page"
-    search_query: str
-    data: List[SearchResult]
-    has_more: bool = False
-    next_page: Optional[str] = None
-
-
-class EmbeddingCreateRequest(BaseModel):
-    content: str
-    embedding: List[float]
-    metadata: Optional[Dict[str, Any]] = None
-
-
-class EmbeddingResponse(BaseModel):
-    id: str
-    object: str = "embedding"
-    vector_store_id: str
-    content: str
-    metadata: Optional[Dict[str, Any]] = None
-    created_at: int
-
-
-class EmbeddingBatchCreateRequest(BaseModel):
-    embeddings: List[EmbeddingCreateRequest]
-
-
-class EmbeddingBatchCreateResponse(BaseModel):
-    object: str = "embedding.batch"
-    data: List[EmbeddingResponse]
-    created: int
-
-
-class VectorStoreListResponse(BaseModel):
-    object: str = "list"
-    data: List[VectorStoreResponse]
-    first_id: Optional[str] = None
-    last_id: Optional[str] = None
-    has_more: bool = False