zxjyes

### Is there an existing issue for this? - [X] I have searched the existing issues ### Current Behavior 大部分文章长度都会超出maxtoken ### Expected Behavior _No response_ ### Steps To Reproduce 提取较长篇新闻的关键词...

请问，http://localhost:8090/可以打开，遇到这个问题如何解决， openai.error.APIError: Invalid response object from API: 'Internal Server Error' (HTTP response code was 500)

1

import openai openai.api_key = "7c7aa4a3549f5" openai.api_base = "http://localhost:8090/v1" completion = openai.ChatCompletion.create( model="gpt-3.5-turbo", messages=[{"role": "user", "content": "Hello world"}]) print(completion.choices[0].message.content)

[BUG]: can't upload .pdf or .docx files that are only 2~3MB with ollama embedding

1

### How are you running AnythingLLM? Docker (remote machine) ### What happened?  ### Are there known steps to reproduce? some settings:   **the steps to run AnythingLLM** export...

I've called the same knowledge base both through the web side and the api, but the api calls are answering poorly. question is "李俊杰做了什么研究？" The RAG on the web side...

ImportError: flash_attn_2_cuda.cpython-310-x86_64-linux-gnu.so: undefined symbol: _ZN3c105ErrorC2ENS_14SourceLocationENSt7__cxx1112basic_stringIcSt11char_traitsIcESaIcEEE

8

> 我也遇到这个问题，按照版本安装的 > >  > >  > >  > >  _Originally posted by @zxjhellow2 in [#1327](https://github.com/Dao-AILab/flash-attention/issues/1327#issuecomment-2774631611)_ 安装的版本是 flash_attn-2.6.3+cu118torch2.4cxx11abiTRUE-cp310-cp310-linux_x86_64.whl