Ask Relevance – no-code GPT QA on data, managed Vector search and GPT
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…
What it does
In the maker’s words, at launch
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.
Does the same job
all alternatives →
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
