feat: stabilize rag chat conversations and auto title sync

fastapi_modules/fastapi_leaudit/rag_engine/question_chains.py

@@ -4,7 +4,7 @@ import json
 
 import httpx
 
-from fastapi_modules.fastapi_leaudit.rag_engine.config import RAG_CONFIG
+from fastapi_modules.fastapi_leaudit.rag_engine.config import RAG_CONFIG, build_openai_chat_completions_url
 
 
 async def generate_followups(query: str, answer: str) -> list[str]:
@@ -15,7 +15,7 @@ async def generate_followups(query: str, answer: str) -> list[str]:
     )
     async with httpx.AsyncClient(timeout=30.0) as client:
         resp = await client.post(
-            f"{RAG_CONFIG['LLM_BASE_URL'].rstrip('/')}" + "/chat/completions",
+            build_openai_chat_completions_url(RAG_CONFIG["LLM_BASE_URL"]),
             json={
                 "model": RAG_CONFIG["LLM_MODEL"],
                 "messages": [{"role": "user", "content": prompt}],