When using the `llama_index.llms import

PPunkbit

When using the llama_index.llms import OpenAI how to set the log to "debug"?

For getting openai logs seen suggested openai.log = "debug", but doesn't work for my setup.

Here's a snippet:

Plain Text

...
from llama_index.llms import OpenAI
import openai

openai.log = "debug"
app = FastAPI()
loader = SitemapReader()

llm = OpenAI(temperature=0.1, model="gpt-3.5-turbo")
service_context = ServiceContext.from_defaults(llm=llm)

Followed the documentation, from most basics simply set an environment variable for OPEN AI api etc. Happens that I extended my setup to include OpenAI, as I wanted to modify the model, otherwise I wouldn't need it.

So, when someone says to openai.log = "debug", I wonder what they mean in llama index context or setup?

6 comments

TTeemu

Yeah it seems it doesn't work for the latest version of Llamaindex

@WhiteFang_Jr Have you experienced the same with?

Plain Text

openai.log = "debug"

PPunkbit

@Teemu not at all. Thanks for checking.

WWhiteFang_Jr

Yeah @Teemu I'm at 0.8.66, just checked, and debugging did not work.

LLogan M

Dang, that sucks, I guess the new openai client actually did remove that 🤔 there must be some new way to enable it though, those logs were helpful

WWhiteFang_Jr

Got something as logs but it is not giving much information in the new openai client.
Had to set OPENAI_LOG in the environment at the top before the OpenAI import.

Plain Text

import os
os.environ['OPENAI_LOG'] = "debug"

from llama_index.llms import OpenAI

Attachment

LLogan M

hmmm yea, not quite as helpful. Before it logged the entire request. But closer!

Add a reply

Find answers from the community

When using the `llama_index.llms import