refactor(backend): update ingest and query routers

Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent)

Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>

backend/app/routers/ingest.py

@@ -17,6 +17,7 @@ SUPPORTED_EXTENSIONS = {".pdf", ".docx", ".txt"}
 @router.post("/ingest", response_model=IngestResponse)
 async def ingest_document(file: UploadFile = File(...)):
     """Ingest a document into the RAG system."""
+    from app.core.config import get_settings
     from app.services.rag import RAGService
     from app.utils.chunking import TokenChunkingStrategy
     from app.utils.metadata import extract_metadata
@@ -30,6 +31,7 @@ async def ingest_document(file: UploadFile = File(...)):
             detail=f"Unsupported file format: {file_ext}. Supported: {', '.join(sorted(SUPPORTED_EXTENSIONS))}",
         )
 
+    settings = get_settings()
     temp_path = None
     try:
         with tempfile.NamedTemporaryFile(delete=False, suffix=file_ext) as tmp:
@@ -51,7 +53,7 @@ async def ingest_document(file: UploadFile = File(...)):
         else:
             text = ""
 
-        chunker = TokenChunkingStrategy(chunk_size=1000, overlap=200)
+        chunker = TokenChunkingStrategy(chunk_size=settings.chunk_size, overlap=settings.chunk_overlap)
         chunks = chunker.chunk(text)
 
         if not chunks:
@@ -59,7 +61,7 @@ async def ingest_document(file: UploadFile = File(...)):
 
         metadata = extract_metadata(temp_path, chunks)
 
-        rag = RAGService()
+        rag = RAGService(settings=settings)
         document_id = rag.ingest_document(temp_path, chunks, metadata)
 
         logger.info("Ingested %s: %d chunks, doc_id=%s", filename, len(chunks), document_id)

backend/app/routers/query.py

@@ -4,7 +4,8 @@ import logging
 from fastapi import APIRouter, HTTPException
 
 from app.core.config import get_settings
-from app.models.ingest import QueryRequest, QueryResponse, SourceMetadata
+from app.models.query import QueryRequest, QueryResponse
+from app.models.common import SourceMetadata
 from app.services.llm_client import LLMClient
 from app.services.query_decomposer import QueryDecomposer
 from app.services.relevance_filter import RelevanceFilter
@@ -18,14 +19,6 @@ NO_RESULTS_ANSWER = "I could not find any relevant information to answer your qu
 
 @router.post("/query", response_model=QueryResponse)
 async def query(request: QueryRequest):
-    """Execute the 3-step RAG query pipeline.
-
-    Pipeline:
-    1. QueryDecomposer: Extract keywords from question
-    2. RAGService.retrieve: Get relevant chunks from ChromaDB
-    3. RelevanceFilter: Score and filter chunks by relevance
-    4. RAGService.generate_response: Generate bullet-point answer
-    """
     if not request.question or not request.question.strip():
         raise HTTPException(status_code=400, detail="Question is required")
 
@@ -33,21 +26,23 @@ async def query(request: QueryRequest):
 
     try:
         llm_client = LLMClient(settings)
+        rag = RAGService(llm_client=llm_client, settings=settings)
 
         logger.info("Query: %s", request.question)
         decomposer = QueryDecomposer(llm_client)
-        keywords = decomposer.decompose(request.question)
+        keywords = await decomposer.decompose(request.question)
         logger.info("Keywords: %s", keywords)
 
-        rag = RAGService(llm_client=llm_client)
+        chunks = rag.retrieve(keywords, n_results=settings.retrieval_n_results)
-        chunks = rag.retrieve(keywords, n_results=10)
 
         if not chunks:
             return QueryResponse(keywords=keywords, answer=NO_RESULTS_ANSWER, sources=[])
 
         chunks_for_filter = [(text, meta) for text, meta, _dist in chunks]
         relevance_filter = RelevanceFilter(llm_client)
-        filtered = relevance_filter.filter(request.question, chunks_for_filter, threshold=7.0)
+        filtered = await relevance_filter.filter(
+            request.question, chunks_for_filter, threshold=settings.relevance_threshold
+        )
 
         if not filtered:
             return QueryResponse(keywords=keywords, answer=NO_RESULTS_ANSWER, sources=[])
@@ -55,7 +50,7 @@ async def query(request: QueryRequest):
         chunk_texts = [chunk for chunk, _meta in filtered]
         chunk_metadata = [meta for _chunk, meta in filtered]
 
-        answer = rag.generate_response(request.question, chunk_texts, chunk_metadata)
+        answer = await rag.generate_response(request.question, chunk_texts, chunk_metadata)
         logger.info("Answer generated: %d chars, %d sources", len(answer), len(filtered))
 
         sources = [