Show HN: Ask Relevance – no-code GPT QA on data, managed Vector search and GPT (relevanceai.com)

Hey all, we've seen increasing interest for leveraging GPT's capability but basing it off of your own data so we launched a new feature "Ask Relevance" a little while ago and our users have loved it. There have been some great tutorials on how you can do this and we thought we'd share our approach with the community as we believe it's very accessible.

Under the hood, it's using vector search to extract relevant content from the dataset and then using that to feed it into GPT. The post features a video where you can see it in action answering specific questions about the Relevance AI platform. This technique is great as it avoids costly fine-tuning and works around the token length limits.

You can get started without code by uploading a CSV, vectorising the data and using Ask Relevance from the dashboard. If you'd like to then integrate it into your docs/blogs/anywhere else you can grab the API request - which automatically generates the vector for the input query, retrieves the top N results and passes it over to GPT before returning the response.

This is all powered by our platform which enables running AI workflows, at-scale on any data without code and managing your own infrastructure.