[Bug]: unnecessary auto-increment calculations in the tokens statistics of the chat model

[yqwang96]

Is there an existing issue for the same bug?

• I have checked the existing issues.

Branch name

main

Commit ID

aaaa

Other environment information

No response

Actual behavior

In the chat_streamly method of the Base class in \rag\llm\chat_model.py, there is an unnecessary auto-increment in the calculation of total_tokens;

Expected behavior

No response

Steps to reproduce

total_tokens += 1
                if not hasattr(resp, "usage") or not resp.usage:
                    total_tokens = (
                                total_tokens
                                + num_tokens_from_string(resp.choices[0].delta.content)
                        )
                elif isinstance(resp.usage, dict):
                    total_tokens = resp.usage.get("total_tokens", total_tokens)
                else:
                    total_tokens = resp.usage.total_tokens

Additional information

No response