Find answers from the community

Updated 2 months ago

SOmeoby help please

Plain Text

completion_response = model.complete("To infinity, and")
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
.venv\Lib\site-packages\text_generation\client.py", line 154, in chat
    raise parse_error(resp.status_code, payload)
          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  ext_generation\errors.py", line 81, in parse_error
    message = payload["error"]
              ~~~~~~~^^^^^^^^^
KeyError: 'error'

6 comments

LLogan M

what LLM is this? Looks like an issue in some 3rd party dependency

ddrewskidang

Was using the vllm custom image on hf

ddrewskidang

Ohh should I use vllm llama index Llm then lol

LLogan M

Maybe? This seems like an issue in the text-generation package thouvh

LLogan M

I know they just added vllm, maybe there's some bugs

ddrewskidang

Gotcha gotcha yeah was using TGI vllm custom image they added. Damn it huggingface

Add a reply