RAG conversational application for requirement gathering purpose.

Aravindakshan, Vineeth 20 Reputation points
2024-06-05T10:53:16.1366667+00:00

Im trying to create a conversational RAG service using Azure search and Azure Open AI, It works generally on answering the user questions based on content from the document. But the use case I'm trying to accomplish is uploading a requirement questionaire document and the open ai/chatbot should ask user requirement questions from the document to gather the response and summarize it. This use case doesn't works the way I envision. Is this something possible with Azure open ai + ai search or it can only answer based on the uploaded documents and cannot ask question to steer the conversation for a requirement gathering scenario.

Azure AI Search
Azure AI Search
An Azure search service with built-in artificial intelligence capabilities that enrich information to help identify and explore relevant content at scale.
834 questions
Azure
Azure
A cloud computing platform and infrastructure for building, deploying and managing applications and services through a worldwide network of Microsoft-managed datacenters.
1,059 questions
Azure OpenAI Service
Azure OpenAI Service
An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
2,543 questions
0 comments
Accepted answer
  1. Grmacjon-MSFT 17,286 Reputation points
    2024-06-05T16:31:40.9833333+00:00

    Hi @Aravindakshan, Vineeth the current capabilities of Azure OpenAI and Azure Search are more focused on answering questions based on the content of uploaded documents. They are not inherently designed to ask questions to steer a conversation or gather requirements.

    Azure Search is primarily designed for indexing and searching through documents. While it can be used to retrieve relevant information based on user queries, it doesn't inherently have the capability to ask clarifying questions or hold a conversation. On the other hand, Azure OpenAI's capabilities lie in generating text, translating languages, and writing different kinds of creative content. While it can be fine-tuned on specific datasets, it might not be ideal for actively asking questions and guiding a conversation flow in the way you envision for requirement gathering.

    Two recommendations:

    1.It might be helpful to look into Azure QnA Bot Maker. QnA Maker is a cloud-based Natural Language Processing (NLP) service that allows you to create a natural conversational layer over your data. It is used to find the most appropriate answer for any input from your custom knowledge base (KB) of information.

    • QnA Maker is commonly used to build conversational client applications, which include social media applications, chat bots, and speech-enabled desktop applications.
    • QnA Maker doesn't store customer data. All customer data (question answers and chat logs) is stored in the region the customer deploys the dependent service instances in. For more details on dependent services see here.

    2.You could try using a Hybrid Approach:

    • Leverage Azure Search to index your requirement questionnaire document.
    • Develop a custom logic layer that analyzes the document structure and identifies key questions or prompts related to each requirement section.
    • Use Azure OpenAI to generate summaries of user responses based on the identified requirement sections.
    • This approach requires more development effort but offers more control over the conversation flow.

    Hope that helps.

    Grace

0 additional answers

Sort by: Most helpful
Most helpful Newest Oldest