Refa: cleanup synchronous functions in chat_model and implement synchronization for conversation and dialog chats (#11779)

### What problem does this PR solve?

Cleanup synchronous functions in chat_model and implement
synchronization for conversation and dialog chats.

### Type of change

- [x] Refactoring
- [x] Performance Improvement
This commit is contained in:
Yongteng Lei
2025-12-08 09:43:03 +08:00
committed by GitHub
parent 9b8971a9de
commit 51ec708c58
10 changed files with 421 additions and 843 deletions

View File

@ -74,7 +74,7 @@ async def set_api_key():
assert factory in ChatModel, f"Chat model from {factory} is not supported yet."
mdl = ChatModel[factory](req["api_key"], llm.llm_name, base_url=req.get("base_url"), **extra)
try:
m, tc = mdl.chat(None, [{"role": "user", "content": "Hello! How are you doing!"}], {"temperature": 0.9, "max_tokens": 50})
m, tc = await mdl.async_chat(None, [{"role": "user", "content": "Hello! How are you doing!"}], {"temperature": 0.9, "max_tokens": 50})
if m.find("**ERROR**") >= 0:
raise Exception(m)
chat_passed = True
@ -217,7 +217,7 @@ async def add_llm():
**extra,
)
try:
m, tc = mdl.chat(None, [{"role": "user", "content": "Hello! How are you doing!"}], {"temperature": 0.9})
m, tc = await mdl.async_chat(None, [{"role": "user", "content": "Hello! How are you doing!"}], {"temperature": 0.9})
if not tc and m.find("**ERROR**:") >= 0:
raise Exception(m)
except Exception as e: