openai.error.APIError: Invalid response object from API？

[lonngxiang]

Describe the bug

openai.api_base = "http://localhost:10860/v1/embeddings"

def test_embedding():
    embedding = openai.Embedding.create(model =model,input="hello")
    print(embedding)
    print(embedding["data"][0]["embedding"].shape)
    print(embedding["data"][0]["embedding"])

To Reproduce

Traceback (most recent call last): File "C:\Users\loong.conda\envs\nlp\lib\site-packages\openai\api_requestor.py", line 403, in handle_error_response error_data = resp["error"] KeyError: 'error'

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "D:\llm\NLP\aquila_openai_api_vllm.py", line 54, in test_embedding() File "D:\llm\NLP\aquila_openai_api_vllm.py", line 25, in test_embedding embedding = openai.Embedding.create(model =model,input="你好") File "C:\Users\loong.conda\envs\nlp\lib\site-packages\openai\api_resources\embedding.py", line 33, in create response = super().create(*args, **kwargs) File "C:\Users\loong.conda\envs\nlp\lib\site-packages\openai\api_resources\abstract\engine_apiresource.py", line 153, in create response, , api_key = requestor.request( File "C:\Users\loong.conda\envs\nlp\lib\site-packages\openai\api_requestor.py", line 298, in request resp, got_stream = self._interpret_response(result, stream) File "C:\Users\loong.conda\envs\nlp\lib\site-packages\openai\api_requestor.py", line 707, in _interpret_response self._interpret_response_line( File "C:\Users\loong.conda\envs\nlp\lib\site-packages\openai\api_requestor.py", line 772, in _interpret_response_line raise self.handle_error_response( File "C:\Users\loong.conda\envs\nlp\lib\site-packages\openai\api_requestor.py", line 405, in handle_error_response raise error.APIError( openai.error.APIError: Invalid response object from API: '{"detail":"Not Found"}' (HTTP response code was 404)

Code snippets

No response

OS

centos

Python version

3.10

Library version

0.28.0

[RobertCraigie]

What model are you passing? That is likely the cause of the error you're seeing.

[lonngxiang]

What model are you passing? That is likely the cause of the error you're seeing.

use vllm：

import openai
import json

# Modify OpenAI's API key and API base to use vLLM's API server.
openai.api_key = "EMPTY"
model = "/mnt/data/loong/AquilaChat2-7B"

openai.api_base = "http://localhost:10860/v1"

def test_embedding():
    embedding = openai.Embedding.create(model =model,input="hello")
    print(embedding)
    print(embedding["data"][0]["embedding"].shape)
    print(embedding["data"][0]["embedding"])

[rattrayalex]

This is likely fixed in v1; please give it a try and open a new issue if the problem persists.