azure-open-ai-embeddings-qna
azure-open-ai-embeddings-qna copied to clipboard
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 th...
Hi, The question types comes after answer. Its displayed in an opposite way
langchain version has high/critical vulnerabilities, I would suggest that we upgrade to 0.0.262 or above https://security.snyk.io/package/pip/langchain
Tooltip and the text example could be better, it's hard now to understand how to use this feature.
The system seems to give answer that is not related to the information present into the embedding. For example, give an answer using the wikipedia information
In some use cases, we need to know which page of the PDF document the text referenced by the answer comes from
I dont see da-vinci models any longer . Whats the recommendation to replace this model ? https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/legacy-models
Hi Fabrizio. I saw a post was done on the same error, but no solution was provided. I launched my web-app, but upon loading in ran into an error (pasted...
Hi, I could deploy and create a website where I could upload huge pdfs and ChatGPT model summaries and answers to queries related to the uploaded document. Is it possible...
It would be awesome if I had the ability to upload csv and json files to the documents. Is this functionality feasible to add?