feat(benchmarking): add query pipeline with logging and tracing

Why:
- Need query pipeline to ask questions against chunked documents
- Need comprehensive logging for debugging

Changes:
- Query service: embed question → vector search → LLM answer
- Query routes: POST /queries, GET /queries/{id}
- Query models: QueryRequest, QueryResponse, RetrievedChunk
- Added QueryError exception class
- Added STEP 1-6 logging for full traceability

src/benchmarking/__init__.py

@@ -0,0 +1 @@
+"""Benchmarking module: query pipeline and evaluation."""