If I have 300-400 PDF files (50-100 pages per file) for different laptops models, with hardware repair instructions, and I want to query instruction for a specific model. What is the best option to store this files, create one index for each file, or store all of them in a big index ?
@Logan M I'm seeking advice on handling a specific scenario in a ticketing system environment. We have multiple documents, each with its own distinct role and content. Here's a brief overview:
-Process Workflow Document: Details the step-by-step procedures for handling tickets. -Service Level Agreement (SLA) Document: Contains the SLA details and guidelines. -Major Incident Procedures Document: Outlines the approach for handling major incidents. -Change Management Process Document: Describes the process for managing changes in the system. The challenge arises when a question or issue touches on aspects covered in multiple documents. For instance, if there's a ticket that breaches the SLA, I need to understand the process for addressing this breach across these documents.
My question is: How can I effectively query or extract relevant information from all these documents and put different questions simultaneously ? Is there a specific method that can cross-reference and provide insights from multiple documents based on a single query, and generate different questions for each document..?
For example, if someone asks, "What's the procedure when a ticket breaches the SLA?" I'd like to automatically pull information from the SLA document about the breach implications and then from the Process Workflow and Major Incident Procedures documents for the next steps.
Any insights, or strategies to manage this type of cross-document querying ? Is SubQuestionQueryEngine an option or what you recommend ? Thank you
