Add LLM provider switch, markdown chat UI, and update README

- Dual RAG instances (Ollama + OpenAI) for on-the-fly provider switching
- Provider dropdown in chat UI, /api/providers endpoint
- Markdown rendering for assistant responses
- Server logs include provider and model name for each LLM response
- README: OpenAI setup, add_pdfs, API docs, provider switch

Co-authored-by: Cursor <cursoragent@cursor.com>

server.py

@@ -2,6 +2,7 @@
 FastAPI server for Local RAG with chat GUI.
 Run with: uvicorn server:app --reload
 """
+import os
 from pathlib import Path
 
 from fastapi import FastAPI, HTTPException
@@ -10,18 +11,28 @@ from pydantic import BaseModel
 
 from local_rag import LocalRAG
 
-# LLM provider: "ollama" or "openai"
-LLM_PROVIDER = "openai"
 OLLAMA_MODEL = "gpt-oss:20b"
 OPENAI_MODEL = "gpt-5.2"
-
 VECTORSTORE_PATH = "./vectorstore"
-rag = LocalRAG(
+
+# Dual RAG instances for on-the-fly provider switching
+rag_ollama = LocalRAG(
     vectorstore_path=VECTORSTORE_PATH,
-    llm_provider=LLM_PROVIDER,
+    llm_provider="ollama",
     ollama_model=OLLAMA_MODEL,
     openai_model=OPENAI_MODEL,
 )
+rag_openai = None
+if os.environ.get("OPENAI_API_KEY"):
+    try:
+        rag_openai = LocalRAG(
+            vectorstore_path=VECTORSTORE_PATH,
+            llm_provider="openai",
+            ollama_model=OLLAMA_MODEL,
+            openai_model=OPENAI_MODEL,
+        )
+    except Exception as e:
+        print(f"OpenAI RAG not available: {e}")
 
 app = FastAPI(title="Local RAG Chat", version="1.0.0")
 
@@ -34,6 +45,7 @@ class ChatMessage(BaseModel):
 class ChatRequest(BaseModel):
     message: str
     history: list[ChatMessage] = []  # previous turns for conversation context
+    llm_provider: str = "ollama"  # "ollama" | "openai"
 
 
 class RetrievedChunk(BaseModel):
@@ -58,11 +70,21 @@ def chat_view():
     return HTMLResponse(content=html_path.read_text(encoding="utf-8"))
 
 
+def _get_rag(provider: str):
+    """Return the RAG instance for the given provider. Fall back to Ollama if OpenAI unavailable."""
+    if provider == "openai" and rag_openai is not None:
+        return rag_openai
+    return rag_ollama
+
+
 @app.post("/api/chat", response_model=ChatResponse)
 def chat(request: ChatRequest):
     """Handle a chat message and return the RAG answer."""
     if not request.message or not request.message.strip():
         return ChatResponse(answer="", error="Message cannot be empty")
+    if request.llm_provider == "openai" and rag_openai is None:
+        return ChatResponse(answer="", error="OpenAI not configured. Set OPENAI_API_KEY.")
+    rag = _get_rag(request.llm_provider)
     try:
         chat_history = [{"role": m.role, "content": m.content} for m in request.history]
         result = rag.query_with_history(
@@ -81,7 +103,9 @@ def chat(request: ChatRequest):
                 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")
-        print(f"[RAG] LLM response:\n{answer}")
+        provider_label = "OpenAI" if request.llm_provider == "openai" else "Ollama"
+        model_name = OPENAI_MODEL if request.llm_provider == "openai" else OLLAMA_MODEL
+        print(f"[RAG] LLM response ({provider_label} / {model_name}):\n{answer}")
 
         return ChatResponse(answer=answer, retrieved=retrieved)
     except Exception as e:
@@ -91,10 +115,16 @@ def chat(request: ChatRequest):
 @app.get("/api/health")
 def health():
     """Health check and vector store status."""
-    has_docs = rag.vectorstore is not None
+    has_docs = rag_ollama.vectorstore is not None
     return {"status": "ok", "vectorstore_loaded": has_docs}
 
 
+@app.get("/api/providers")
+def providers():
+    """Return which LLM providers are available."""
+    return {"ollama": True, "openai": rag_openai is not None}
+
+
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=8000)