Azure OpenAI gpt-4o-mini support unknown model

HHarrison

Hi

Any word on Azure OpenAI gpt-4o-mini support?

"Unknown model 'gpt-4o-mini'. Please provide a valid OpenAI model name in: gpt-4, gpt-4-32k, gpt-4-1106-preview, gpt-4-0125-preview, gpt-4-turbo-preview, gpt-4-vision-preview, gpt-4-1106-vision-preview, gpt-4-turbo-2024-04-09, gpt-4-turbo, gpt-4o, gpt-4o-2024-05-13, gpt-4-0613, gpt-4-32k-0613, gpt-4-0314, gpt-4-32k-0314, gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-3.5-turbo-0125, gpt-3.5-turbo-1106, gpt-3.5-turbo-0613, gpt-3.5-turbo-16k-0613, gpt-3.5-turbo-0301, text-davinci-003, text-davinci-002, gpt-3.5-turbo-instruct, text-ada-001, text-babbage-001, text-curie-001, ada, babbage, curie, davinci, gpt-35-turbo-16k, gpt-35-turbo, gpt-35-turbo-0125, gpt-35-turbo-1106, gpt-35-turbo-0613, gpt-35-turbo-16k-0613"

16 comments

LLogan M

Its already supported

pip install -U llama-index-llms-openai

HHarrison

thats openai, not azure open ai right?

HHarrison

ive tried that and it still doesnt recognise

LLogan M

The utils are in openai

LLogan M

azure extends it

LLogan M

(ignore the broken cicd, its unrelated to this change)

https://github.com/run-llama/llama_index/pull/16335

LLogan M

it like, just published, you should have llama-index-llms-openai==0.2.10 for it to work

HHarrison

thank you

nnvm

hey @Logan M in my code, i was using llamaindex verion 0.9.21 for automerging retriever implementation. after i installed lama-index-llms-openai, getting this error:

Traceback (most recent call last):
File "/home/prakhar/Downloads/doc-retrieve-and-summarize1/app.py", line 6, in <module>
from llama_index.core import Document
.....
.....
from llama_index.core import BaseQueryEngine
ImportError: cannot import name 'BaseQueryEngine' from 'llama_index.core' (/home/prakhar/Downloads/doc-retrieve-and-summarize1/venv/lib/python3.10/site-packages/llama_index/core/init.py)

LLogan M

@nvm with such an old version, I'm not sure. I'd have to go back to that tag on the repo and find the proper import

nnvm

i just upgraded llamaindex to v0.11.something and shifted my code to this latest version but now i'm getting error --> ImportError: cannot import name 'Document' from 'llama_index.core' (unknown location)
do we not have Document method now??

LLogan M

We do, but upgrading from v0.9.x can be messy

LLogan M

Use a fresh venv

nnvm

yes, did the same just now

nnvm

hey @Logan M i'm simply using this line in my code -->

from llama_index.llms.openai import OpenAI
llm_gpt = OpenAI(model="gpt-4o-mini")

error i'm getting:

pydantic_core._pydantic_core.ValidationError: 2 validation errors for OpenAI
logprobs
Field required [type=missing, input_value={'model': 'gpt-4o-mini', ..., 'output_parser': None}, input_type=dict]
For further information visit https://errors.pydantic.dev/2.9/v/missing
default_headers
Input should be a valid dictionary [type=dict_type, input_value=None, input_type=NoneType]
For further information visit https://errors.pydantic.dev/2.9/v/dict_type

LLogan M

I'm not sure what your issue is. A fresh venv works for me 🤔 if you can replicate in Google colab, happy to look further

Add a reply

Find answers from the community

Azure OpenAI gpt-4o-mini support unknown model