added OpenAI support and markdown in the chat window

server.py

@@ -10,10 +10,18 @@ from pydantic import BaseModel
 
 from local_rag import LocalRAG
 
-# Initialize RAG once at startup
-VECTORSTORE_PATH = "./vectorstore"
+# LLM provider: "ollama" or "openai"
+LLM_PROVIDER = "openai"
 OLLAMA_MODEL = "gpt-oss:20b"
-rag = LocalRAG(vectorstore_path=VECTORSTORE_PATH, ollama_model=OLLAMA_MODEL)
+OPENAI_MODEL = "gpt-5.2"
+
+VECTORSTORE_PATH = "./vectorstore"
+rag = LocalRAG(
+    vectorstore_path=VECTORSTORE_PATH,
+    llm_provider=LLM_PROVIDER,
+    ollama_model=OLLAMA_MODEL,
+    openai_model=OPENAI_MODEL,
+)
 
 app = FastAPI(title="Local RAG Chat", version="1.0.0")
 
@@ -64,15 +72,16 @@ def chat(request: ChatRequest):
         answer = result["answer"]
         retrieved = result.get("retrieved", [])
 
-        # Server-side console trace: log retrieved chunks before LLM answer
+        # Server-side console trace: shorter chunk logs + raw LLM response
         if retrieved:
-            print(f"\n[RAG] Retrieved {len(retrieved)} chunk(s) for query: {request.message[:80]!r}")
+            print(f"\n[RAG] Retrieved {len(retrieved)} chunk(s)")
             for i, chunk in enumerate(retrieved):
                 content = chunk.get("content", "")
-                preview = (content[:1000] + "...") if len(content) > 1000 else content
-                print(f"  [{i + 1}] source={chunk.get('source', '')} page={chunk.get('page')} | {preview!r}")
+                preview = (content[:80] + "...") if len(content) > 80 else content
+                print(f"  [{i + 1}] {chunk.get('source', '')} p.{chunk.get('page', '?')} s={chunk.get('score')} | {preview!r}")
         else:
-            print(f"\n[RAG] Retrieved 0 chunks for query: {request.message[:80]!r}")
+            print(f"\n[RAG] Retrieved 0 chunks")
+        print(f"[RAG] LLM response:\n{answer}")
 
         return ChatResponse(answer=answer, retrieved=retrieved)
     except Exception as e: