0

I am currently working on the Azure OpenAI+Cognitive Search Chatbot Demo. And as I try to run the demo locally, I kept getting this error message when using openAI API:

Error: Unable to get resource information. {"error":{"code":"InternalServerError","message": "Unable to get resource information."}} 500 {'error': {'code': 'InternalServerError', 'message': 'Unable to get resource information.'}} {'Content-Length': '89', 'Content-Type': 'application/json', 'x-ms-client-request-id': 'Not-Set', 'apim-request-id': 'edbe2b70-ae2d-44d5-b786-286e18f72e44', 'Strict-Transport-Security': 'max-age=31536000; includeSubDomains; preload', 'x-content-type-options': 'nosniff', 'Date': 'Tue, 01 Aug 2023 08:00:55 GMT'}

I have checked .env and printed out all the parameters, and all of them are correct. And it can also run on Azure's app service. The problem only occurred when I tried to run locally.

1 Answer 1

0

Error: Unable to get resource information. {"error":{"code":"InternalServerError","message": "Unable to get resource information."}} 500 {'error': {'code': 'InternalServerError', 'message': 'Unable to get resource information.'}}

The above Internalservererror occurs in open-ai due to region problems and may be incorrect in the API key and API endpoint.

I tried the same code locally to run Azure OpenAI+Cognitive Search Chatbot Demo.

Code:

import os
import requests
import json
import openai
from azure.search.documents import SearchClient
from azure.core.credentials import AzureKeyCredential

# Set up OpenAI API
openai.api_key = "xxxxx"
openai.api_base = "https://xxxxx.openai.azure.com/"
openai.api_type = 'azure'
openai.api_version = '2023-05-15'

# Set up Azure Cognitive Search
search_service_name = "xxxx"
index_name = "xxxxx"
admin_key = "xxxxxxx"
credential = AzureKeyCredential(admin_key)
client = SearchClient(endpoint=f"https://{search_service_name}.search.windows.net/", index_name=index_name, credential=credential)

def search_index(query):
    search_results = client.search(search_text=query)
    return list(search_results)

def generate_response(prompt):
    response = openai.Completion.create(
        engine="deployment1", #text-davinci-002
        prompt=prompt,
        max_tokens=1024,
        n=1,
        stop=None,
        temperature=0.5,
    )
    return response.choices[0]['text'].replace('\n', '').replace(' .', '.').strip()


def handle_input(input_text):
    search_results = search_index(input_text)
    if len(search_results) > 0:
        return search_results[0]['content']
    else:
        prompt = f"Q: {input_text}\nA:"
        response = generate_response(prompt)
        return response


def run_chatbot():
    print("Welcome to the Azure OpenAI+Cognitive Search Chatbot Demo!")
    while True:
        # Get user input
        user_input = input("You: ")
        # Handle user input and generate response
        response = handle_input(user_input)
        # Print response
        print("Chatbot:", response)


run_chatbot()

Output:

Welcome to the Azure OpenAI+Cognitive Search Chatbot Demo!
You: dhoni
Chatbot: Dhoni is a former Indian cricketer and the current captain of the Indian national cricket team. He is considered one of the greatest cricket captains of all time.

enter image description here

Reference:

Sign up to request clarification or add additional context in comments.

Comments

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.