I compressed 10k PDFs into a 1.4GB video for LLM memory
While building a Retrieval-Augmented Generation (RAG) system, I was frustrated by my vector database consuming 8GB RAM just to search my own PDFs. After incurring $150 in cloud costs, I had an unconventional idea: what if I encoded my documents into video frames? The concept sounded absurd—storing text in video? But modern video codecs have been optimized for compression over decades. So, I converted text into QR codes, then encoded those as video frames, letting H.264/H.265 handle the compression. The results were surprising. 10,000 PDFs compressed down to a 1.4GB video file. Search…
In plain words
This project compresses 10,000 PDFs into a 1.4GB video file by encoding document chunks as QR codes and leveraging video codec compression. It is designed for developers building retrieval systems who want to reduce memory consumption and eliminate cloud costs. The approach uses H.264/H.265 compression to achieve 200MB RAM usage instead of 8GB, with search latency around 900ms, and runs entirely offline without requiring API keys or subscriptions.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
While building a Retrieval-Augmented Generation (RAG) system, I was frustrated by my vector database consuming 8GB RAM just to search my own PDFs. After incurring $150 in cloud costs, I had an unconventional idea: what if I encoded my documents into video frames? The concept sounded absurd—storing text in video? But modern video codecs have been optimized for compression over decades. So, I converted text into QR codes, then encoded those as video frames, letting H.264/H.265 handle the compression. The results were surprising. 10,000 PDFs compressed down to a 1.4GB video file. Search latency was around 900ms compared to Pinecone’s 820ms—about 10% slower. However, RAM usage dropped from over 8GB to just 200MB, and it operates entirely offline without API keys or monthly fees. Technically, each document chunk is encoded into QR codes, which become video frames. Video compression handles redundancy between similar documents effectively. Search works by decoding relevant frame ranges based on a lightweight index. You get a vector database that’s just a video file you can copy anywhere. GitHub: https://github.com/Olow304/memvid
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, May 2025
the whole month →
- C9
Life & fun · 2025 · felixrieseberg.github.io
