search

ruoccofabrizio / azure-open-ai-embeddings-qna

A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.
https://azure.microsoft.com/en-us/products/cognitive-services/openai-service
MIT License
846 stars 510 forks source link

Unable to use "history" when calling the ApiQna function #84

Closed briceglase closed 1 year ago

briceglase commented 1 year ago

First, thanks for sharing this great work. For some reason, I keep getting a 500 when executing the below on ApiQnA. Is there any obvious reason? image Here is the detailed error message I’m getting. Note that it works perfectly fine if I remove the “history” attribute from the Body. image

ruoccofabrizio commented 1 year ago

Hi, please pass a tuple as part of the history array in the body.

'history': [
    ("question1", 'answer1')
    ]