VectorAdmin – An open-source vector database management system
Hey HN, At Mintplex Labs are building developer tools for AI applications. One area we encountered frustration was the use of Vector Databases like Pinecone, Chroma, QDrant, or Weaviate to "unlock" long-term memory and contextual answers. It is nearly impossible to manage this data when in use for production. The craziest thing was how you cannot atomically CRUD any vectors in most of these vector databases. Let alone easily copy, clone, or migrate data or entire indexes without paying for re-embedding - among other things. With VectorAdmin you get a database level UI with the ability to…
What it does
In the maker’s words, at launch
Hey HN, At Mintplex Labs are building developer tools for AI applications. One area we encountered frustration was the use of Vector Databases like Pinecone, Chroma, QDrant, or Weaviate to "unlock" long-term memory and contextual answers. It is nearly impossible to manage this data when in use for production. The craziest thing was how you cannot atomically CRUD any vectors in most of these vector databases. Let alone easily copy, clone, or migrate data or entire indexes without paying for re-embedding - among other things. With VectorAdmin you get a database level UI with the ability to easily search for embeddings and atomically manage them on top of being a general tool suite for those using vector databases with LLMs. Some things we have unlocked with Vector Admin: - Upload data directly into the vector db via a text doc or PDF - One click sync of entire existing vector databases - Migrating entire db's to another provider to escape vendor lock in - Ability to duplicate collections/namespaces to create dev-environments off production data at no cost - Be able to finally reset a vector database (provider agnostic) and soon, be able to detect "drift" in semantic search results and catch it early before your production system starts providing wild context snippets. VectorAdmin is open-source or hosted and has a 3-day trial. We really want HN's feedback on the issues or problem you are having wrangling the actual data in a vector database while building any LLM application.
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
Launched alongside, October 2023
the whole month →
Nudge 2.0▲1,051In-app experiences to activate, retain, & understand users
Growth · 2023 · nudgenow.com
Unlock AI magic for elevated customer engagement, fast
AI · 2023 · tiledesk.com
- OD
Effortlessly discover API behaviour with a Chrome extension that automatically generates OpenAPI specifications in real time for any app or website.
Dev tools · 2023 · github.com