Multi-modal RAG with ColQwen in a single line of Code
Hi HN, we're Arnav and Adi, and we're building DataBridge - a multi-modal database built from the ground up with AI use cases in mind. We recently launched support for ColPali-style image embeddings and late-interaction retrieval. We've implemented a hamming distance version of retrieval which helps this approach scale significantly more when compared with the regular late-interaction similarity scoring. These embeddings provide a significantly better retrieval accuracy, with ColQwen achieving around an 89% average score on the ViDoRe benchmark, compared to around 67% for traditional parsing…
What it does
In the maker’s words, at launch
Hi HN, we're Arnav and Adi, and we're building DataBridge - a multi-modal database built from the ground up with AI use cases in mind. We recently launched support for ColPali-style image embeddings and late-interaction retrieval. We've implemented a hamming distance version of retrieval which helps this approach scale significantly more when compared with the regular late-interaction similarity scoring. These embeddings provide a significantly better retrieval accuracy, with ColQwen achieving around an 89% average score on the ViDoRe benchmark, compared to around 67% for traditional parsing and captioning based methods. We're completely open source, and getting started takes less than 10 minutes (get started here: https://databridge.mintlify.app/getting-started). In fact, using these style of embeddings requires just setting `use_colpali=True` in our python SDK while ingesting or retrieving documents. Our long term goal is to make state of the art research in retrieval be as accessible for production use cases as possible, and integrating ColPali is an initial step towards that goal. If there's research that you think is compelling, but haven't been able to integrate into production, let us know: we'd be happy to help. We really appreciate the honest feedback the HN community provides, and so we'd love to hear from you!
Does the same job
all alternatives →- DADataBridge - An open-source, modular, multi-modal RAG solution2024 · github.com · ▲5
For the past few weeks, I've been working on DataBridge, an open-source solution for easy data ingestion and querying. We support text, PDFs, images, and as of recently, we've added a video parser that can analyze and work well over frames and audio. We are also adding object tracking to improve video ingestion and context, and plan to do this for various data types. To get started, you can find the installation section in our docs at https://databridge.gitbook.io/databridge-docs/getting-starte.... There are a bunch of other useful functions and examples available there.…
- SVSuperlinked – Vector Embeddings for Structured and Unstructured Data2024 · github.com · ▲7
Hi HN, I'm Daniel from Superlinked! We have built an open-source framework that improves vector search relevance and usefulness by combining structured metadata with unstructured data in your embeddings. We included self-hostable API server that sits between your data sources and vector database. Docs: https://docs.superlinked.com/ We're launching our cloud offering soon where you can use Superlinked to orchestrate high-performance retrieval for RAG, Search & Recommendation apps in your own cloud. Looking for feedback and happy to answer questions!
- IBI built an offline open-source RAG system DataBridge2025 · github.com · ▲7
Hey HN! Over the past few weeks, I’ve been working on DataBridge, an open-source solution for data ingestion and querying across text, PDFs, images, and videos. In our latest update, we’ve added a fully local deployment option: - No internet required – Runs entirely offline. - Customizable Models – Supports any LLM and embedding model via Ollama (with options for any other private providers) - Extensibility – You can plug in your own models or tools easily. This local-first approach ensures better privacy, security, and flexibility, especially for teams dealing with sensitive data. You can…
- IEInteractively explore your Hugging Face dataset with one line of code2023 · huggingface.co · ▲7
Hey HN, when building ML systems for industrial AI, we have learned that data inspection is critical during the ML development process. We are also big fans of the Hugging Face ecosystem. That is why we built an integration to our data exploration tool Spotlight that allows you to interactively explore Hugging Face datasets with one line of code. Spotlight lets you leverage model results such as predictions and embeddings to gain a deeper understanding in data segments and model failure modes. Currently, many many NLP, CV, Audio and multimodal datasets are supported both locally and on the…
- PFPlayground for comparing embedding models on Wikipedia+book retrieval2023 · embeds.ai · ▲5
Introducing embeds.ai: an embedding playground to compare how embedding models work on a real world use case (retrieval augmented generation for Wikipedia articles + Elad Gil's High growth handbook) A few weeks ago, Shreyan and I were looking for an embedding model to use for RAG. We eventually came across the MTEB leaderboard, but we struggled to understand the benchmark scores. We wanted a tool to test various embedding models with example queries on real-world datasets. After unsuccessfully looking for such a “playground”, we decided to just build one ourselves! We embedded HuggingFace’s…
- WBWe built a better reranker and open sourced it2025 · huggingface.co · ▲6
Hi HN, Our research team just released the best performing and most efficient reranker out there, and it's available now as an open weight model on HuggingFace. Reranker v2 was designed specifically for agentic RAG, supports instruction following (our v1 was the first to introduce this), and is multilingual. Along with this, we're also open source our eval set, which allows you to reproduce our benchmark results. By releasing these datasets, we are also advancing instruction-following reranking evaluation, where high-quality benchmarks are currently limited. Please give it a try and let us…
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 2025
the whole month →
Screen Studio 3.0▲1,833Beautiful screen recordings with instant shareable links
Growth · 2025 · screen.studio
- IG
I was at FB/Meta from late 2013 to early 2023, mostly working in the compiler/runtime spaces. I got hit in the spring 2023 layoff wave. I immediately started making games in my newfound free time (a lifelong interest, and I even worked in AA(A?) back ca. ~2000), and in October 2023 I stumbled upon the idea of a roguelike pachinko/plinko game inspired by Luck Be A Landlord. Things snowballed quickly, I started talking to publishers, then worked like crazy through all of 2024, almost the hardest I've ever worked in my career, and launched the game in December 2024. It's sold…
Work · 2025
- IB
i wanted to change the habit of reaching for my phone in the morning and doomscrolling away an hour so i built an app to help me. now i have to literally touch grass before accessing my most distracting apps the app is built in swiftui, uses the screen time apis provided by apple and google vision to recognise grass or not i'd love to get your thoughts on the concept.
Life & fun · 2025 · touchgrass.now