Error when invoking OpenAI

Short Course Q&A Building Agentic RAG with LlamaIndex
1

I am trying to run the L2 lab in my local Jupyter notebook. I have the correct version of Python and have used the requirements.txt file that was in the first lesson for setup.

My OpenAi key connects fine to the gpt-3.5-turbo model via another test call.

When I run the following code, however, I get an error shown below:

from llama_index.llms.openai import OpenAI

llm = OpenAI(model="gpt-3.5-turbo")
response = llm.predict_and_call(
    [add_tool, mystery_tool], 
    "Tell me the output of the mystery function on 2 and 9", 
    verbose=True
)

print(str(response))

The error is:

Retrying llama_index.llms.openai.base.OpenAI._chat in 0.974705252265967 seconds as it raised APIConnectionError: Connection error…

This occurs a few times and then the whole call errors out with a long trace.

This is as simple a call as I can think of and it still seems to fail. Any ideas?

Thanks,

2

Did you download all the files required to run the files, if you check other thread it states importing openai resolved this error.

3

Yes, I did load all pre- req libs including OpenAI.

I am curious if any one had got this to work on their own Jupyter lab env.

4

Can you share the screenshot of the error you are talking about

5

Hi Deepti, here is a screen shot:

Screenshot 2024-05-12 at 11.22.27 AM
Screenshot 2024-05-12 at 11.22.27 AM2444×1490 362 KB

6

Also, here is the full error dump.
eeroDump.zip (7.3 KB)

7

So I changed the LLM to use Mistral and that worked straight away. I then on a whim went and created a new OpenAI key (even though the previous key was working fine with another piece of code). Using the new OpenAI key, the code started to work.

Whew! I wish the error message was more explicit. But all working now. Thanks for your help.

2 Likes