[BUG] <title>python版本调用本地ollama部署的llm,报错找不到模型，但可以正常返回结果

[wangruidedie]

是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?

• [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions

该问题是否在FAQ中有解答？ | Is there an existing answer for this in FAQ?

• [X] 我已经搜索过FAQ | I have searched FAQ

当前行为 | Current Behavior

调用本地ollama部署的llm,报错找不到模型，但可以正常返回结果

期望行为 | Expected Behavior

正常返回结果

运行环境 | Environment

- OS:ubuntu20.04
- NVIDIA Driver:
- CUDA:
- Docker Compose:
- NVIDIA GPU Memory:

QAnything日志 | QAnything logs

2024-09-08 14:01:52,245 Warning: qwen2-q4_0 not found. Using cl100k_base encoding. 2024-09-08 14:01:52,248 Warning: qwen2-q4_0 may update over time. Returning num tokens assuming gpt-3.5-turbo-1106. 2024-09-08 14:01:52,252 Warning: qwen2-q4_0 not found. Using cl100k_base encoding. 2024-09-08 14:01:52,255 Warning: qwen2-q4_0 may update over time. Returning num tokens assuming gpt-3.5-turbo-1106. 2024-09-08 14:01:52,259 Warning: qwen2-q4_0 not found. Using cl100k_base encoding. 2024-09-08 14:01:52,262 Warning: qwen2-q4_0 may update over time. Returning num tokens assuming gpt-3.5-turbo-1106. 2024-09-08 14:01:52,265 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,268 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,271 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,274 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,278 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,281 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,284 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,287 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,290 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,293 Warning: qwen2-q4_0 not found. Using cl100k_base encoding. 2024-09-08 14:01:52,296 Warning: qwen2-q4_0 may update over time. Returning num tokens assuming gpt-3.5-turbo-1106. 2024-09-08 14:01:52,300 Warning: qwen2-q4_0 not found. Using cl100k_base encoding. 2024-09-08 14:01:52,302 Warning: qwen2-q4_0 may update over time. Returning num tokens assuming gpt-3.5-turbo-1106. 2024-09-08 14:01:52,306 limited token nums: 2569 2024-09-08 14:01:52,309 template token nums: 154 2024-09-08 14:01:52,312 query token nums: 21 2024-09-08 14:01:52,315 history token nums: 790 2024-09-08 14:01:52,318 Warning: model not found. Using cl100k_base encoding. 2024-09-08 14:01:52,321 new_source_docs token nums: 2556 2024-09-08 14:01:52,324 history_len: 2 2024-09-08 14:01:52,328 Warning: qwen2-q4_0 not found. Using cl100k_base encoding. 2024-09-08 14:01:52,330 Warning: qwen2-q4_0 may update over time. Returning num tokens assuming gpt-3.5-turbo-1106. 2024-09-08 14:01:52,334 prompt tokens: 2727 2024-09-08 14:01:52,337 streaming: True 2024-09-08 14:01:52,468 OPENAI RES: <openai.Stream object at 0x7f8152841a20>

复现方法 | Steps To Reproduce

No response

备注 | Anything else?

No response