Having repeated key error in my ChatGPT clone

Using Streamlit
1

I am using the latest version of everything.

My App is Deployed here:https://myfirstgpt.streamlit.app/

The git hub repo is here: GitHub - aks-hit/FirstGPT: This is a ChatGPT like LLM using Streamlit

The error message is this:
Script execution error

File "/mount/src/firstgpt/streamlit_app.py", line 5
  client = OpenAI(api_key=st.secrets['OPENAI_API_KEY'],
  ^
SyntaxError: keyword argument repeated: api_key

How to correct it?

2

Don’t repeat the argument api_key.

3

I recommend using a form. Also put your imports at the top.

import streamlit as st
from openai import OpenAI


# Developer's api key is in secrets file.
# dev_api_key = st.secrets['OPENAI_API_KEY']

# Ask the user's api key
with st.form('form'):
    user_api_key = st.text_input('Enter OpenAI API token:', type='password')
    submit = st.form_submit_button('Submit')

if submit:
    if len(user_api_key) == 51 and user_api_key.startswith('sk-'):
        client = OpenAI(api_key=user_api_key)
        st.success('api key is successfully entered')
    else:
        st.error('Your api key is invalid.')
        st.stop()
4

yeah but how ? can you give me the code please.
key is the other word i used in place of Api_key. i have tried different names too but still its the same.
it is giving this error

TypeError: __init__() got an unexpected keyword argument 'key'



2024-01-26 15:42:27.032 Uncaught app exception
5

this too isn’t working…
this is coming NameError: This app has encountered an error. The original error message is redacted to prevent data leaks. Full error details have been recorded in the logs (if you’re on Streamlit Cloud, click on ‘Manage app’ in the lower right of your app).

Traceback:

File "/home/adminuser/venv/lib/python3.9/site-packages/streamlit/runtime/scriptrunner/script_runner.py", line 535, in _run_script
    exec(code, module.__dict__)File "/mount/src/firstgpt/streamlit_app.py", line 37, in <module>
    for response in client.chat.completions.create(model="gpt-3.5-turbo",
6

I cannot give you any code without understanding what you are trying to achieve. Where do you want to retrieve the OpenAI API key from? Streamlit secrets? User input? Something else?

7

In the repo, under your .streamlit folder you have secrets.toml. That is bad.

  • Delete or revoke that key in the openai page.
  • Delete that .streamlit folder.

Another option is to delete or revoke that key in the openai page. Then delete your current repo. Then create a new repo but exclude the .streamlit folder. Do not upload your `.streamlit’ folder with secrets.toml in github public repo or even private repo.

8

The code above alone will not work. It is because of “if submit:” When streamlit reruns the code from top to bottom, the client is no longer visible. To fix that just add:

client = OpenAI(api_key=user_api_key)

Full code with correction

# Ask the user's api key
with st.form('form'):
    user_api_key = st.text_input('Enter OpenAI API token:', type='password')
    submit = st.form_submit_button('Submit')

if submit:
    if len(user_api_key) == 51 and user_api_key.startswith('sk-'):
        client = OpenAI(api_key=user_api_key)
        st.success('api key is successfully entered')
    else:
        st.error('Your api key is invalid.')
        st.stop()

# Make the client visible to other codes below it. 
client = OpenAI(api_key=user_api_key)

# Your other stuff

Fancy api key checking

import openai
from openai import OpenAI
import streamlit as st


# Ask the user's api key and check it.
with st.sidebar:
    with st.form('form'):
        user_api_key = st.text_input('Enter OpenAI API token:', type='password')
        submit = st.form_submit_button('Submit')

    if submit:
        # Check the api key string.
        if len(user_api_key) == 51 and user_api_key.startswith('sk-'):
            # Check the api key authenticity.
            try:
                client = OpenAI(api_key=user_api_key)
                response = client.chat.completions.create(
                    model='gpt-3.5-turbo',
                    messages=[
                        {"role": "system", "content": "You are a helpful assistant."},
                        {"role": "user", "content": "What is new in openai in 3 words?"}
                    ],
                )
            except openai.AuthenticationError as eer:
                st.error(eer)
                st.stop()
            except Exception as uer:
                st.error(f'Unexpected error: {uer}')
                st.stop()
            # Else if no exception is hit, the key is good.
            else:
                st.success('api key is authentic.')
        else:
            st.error('Your api key is invalid.')
            st.stop()

client = OpenAI(api_key=user_api_key)
1 Like
9

this is great everything except this has been resolved
Unexpected error: Error code: 429 - {‘error’: {‘message’: ‘You exceeded your current quota, please check your plan and billing details. For more information on this error, read the docs: https://platform.openai.com/docs/guides/error-codes/api-errors.’, ‘type’: ‘insufficient_quota’, ‘param’: None, ‘code’: ‘insufficient_quota’}}

10

haha ik it’s an api error but thank you very much for your help.

1 Like
11

This topic was automatically closed 2 days after the last reply. New replies are no longer allowed.