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/embedding_service.py

@@ -1,90 +0,0 @@
-from typing import List, Optional
-from config import settings, EmbeddingConfig
-from litellm.types.utils import EmbeddingResponse
-import litellm
-import logging
-
-class EmbeddingService:
-    """Service for generating embeddings using OpenAI SDK pointed at LiteLLM proxy"""
-    
-    def __init__(self, config: Optional[EmbeddingConfig] = None):
-        self.config = config or settings.embedding
-
-
-    
-    async def generate_embedding(self, text: str) -> List[float]:
-        """
-        Generate embedding for a single text using LiteLLM proxy
-        
-        Args:
-            text: Text to embed
-            
-        Returns:
-            List of floats representing the embedding vector
-        """
-        try:
-            response: EmbeddingResponse = await litellm.aembedding(
-                model=self.config.model,
-                input=[text],
-                api_base=self.config.base_url,
-                api_key=self.config.api_key
-            )
-            logging.debug(f"Embedding response: {response}")
-            
-            # Extract embedding from response
-            embedding = response.data[0]["embedding"]
-            
-            # Validate embedding dimensions
-            if len(embedding) != self.config.dimensions:
-                raise ValueError(
-                    f"Expected embedding dimension {self.config.dimensions}, "
-                    f"got {len(embedding)}"
-                )
-            
-            return embedding
-            
-        except Exception as e:
-            raise RuntimeError(f"Failed to generate embedding: {str(e)}")
-    
-    async def generate_embeddings(self, texts: List[str]) -> List[List[float]]:
-        """
-        Generate embeddings for multiple texts
-        
-        Args:
-            texts: List of texts to embed
-            
-        Returns:
-            List of embedding vectors
-        """
-        try:
-            # Generate embeddings using LiteLLM
-            response = await litellm.aembedding(
-                model=self.config.model,
-                input=texts,
-                api_base=self.config.base_url,
-                api_key=self.config.api_key
-            )
-            
-            # Extract embeddings from response
-            embeddings = [item.embedding for item in response.data]
-            
-            # Validate embedding dimensions
-            for i, embedding in enumerate(embeddings):
-                if len(embedding) != self.config.dimensions:
-                    raise ValueError(
-                        f"Expected embedding dimension {self.config.dimensions} for text {i}, "
-                        f"got {len(embedding)}"
-                    )
-            
-            return embeddings
-            
-        except Exception as e:
-            raise RuntimeError(f"Failed to generate embeddings: {str(e)}")
-    
-    def update_config(self, new_config: EmbeddingConfig):
-        """Update the embedding configuration"""
-        self.config = new_config
-
-
-# Global embedding service instance
-embedding_service = EmbeddingService()