Fix miscalculated token count (#9776)

### What problem does this PR solve?

The total token was incorrectly accumulated when using the
OpenAI-API-Compatible api.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Author: biyuhao

rag/llm/chat_model.py

@@ -374,7 +374,7 @@ def chat_streamly_with_tools(self, system: str, history: list, gen_conf: dict =
                         if not tol:
                             total_tokens += num_tokens_from_string(resp.choices[0].delta.content)
                         else:
-                            total_tokens += tol
+                            total_tokens = tol
 
                         finish_reason = resp.choices[0].finish_reason if hasattr(resp.choices[0], "finish_reason") else ""
                         if finish_reason == "length":
@@ -410,7 +410,7 @@ def chat_streamly_with_tools(self, system: str, history: list, gen_conf: dict =
                     if not tol:
                         total_tokens += num_tokens_from_string(resp.choices[0].delta.content)
                     else:
-                        total_tokens += tol
+                        total_tokens = tol
                     answer += resp.choices[0].delta.content
                     yield resp.choices[0].delta.content