Dera – A platform to manage chunks and embeddings for building RAG apps
Hi everyone, my cofounder and I built Dera - a platform to help manage chunks and embeddings. We built this because of the pain points we experienced while building RAG applications for side projects. The biggest pain point we encountered was that we were constantly trying out different chunking strategies, but there’s no easy way to check how the strategies are performing in terms of retrieval when given the same query. We tried searching for a tool for this but couldn’t find any (most LLM dev tools focus on prompts management). We hope this tool will be useful for people building RAG apps.…
In plain words
Dera is a platform for managing chunks and embeddings in retrieval-augmented generation (RAG) applications. It addresses the challenge of testing different chunking strategies by allowing developers to compare how various approaches perform when retrieving results for the same queries. The tool is built for developers constructing RAG apps who need a straightforward way to evaluate and optimize their chunking methods without leaving their workflow.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hi everyone, my cofounder and I built Dera - a platform to help manage chunks and embeddings. We built this because of the pain points we experienced while building RAG applications for side projects. The biggest pain point we encountered was that we were constantly trying out different chunking strategies, but there’s no easy way to check how the strategies are performing in terms of retrieval when given the same query. We tried searching for a tool for this but couldn’t find any (most LLM dev tools focus on prompts management). We hope this tool will be useful for people building RAG apps. Thank you!
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 · 27d ago · cactuscompute.com
Launched alongside, February 2024
the whole month →
MarketingIdeas.com▲1,230Never run out of marketing ideas ever again
Growth · 2024 · marketingideas.com
