Pinned
Behind this door we are redefining retrieval for agents. There has never been a better time to build.
Jo Kristian Bergum
15.1K posts
Jo Kristian Bergum
@jobergum
- Billions worth of system prompts are exposed in a single repo. The scale of IP leaks is remarkable in the LLM era.
- The memvid/vector database slop was an amazing honey trap for finding people to mute
- Signed up for Gemini today. The deep research mode with 2.5 Pro is excellent. Cancelled my OpenAI pro subscription.
- 🚀 The Rise of Vision RAG! Launching a complete RAG app that you can deploy to production in minutes! - Hybrid fusion of ColPali + BM25 with @vespaengine - Gemini 1.5 Flash-8B - FastHTML frontend - Runs on Huggingface Spaces Interpretable SERP with snippets + patch
00:00 - This is insane🤯 Announcing HyperDB. Using Hyper Vector Support Machines to separate relevant from irrelevant documents by the support of HW accelerated vector operations 🤯 Probably being added to @langchain by the end of the day.
Want to super-charge your LLM AI agents with the power of knowledge?!? Announcing HyperDB: a blazing-fast semantic search vector database for use with LLM Agents. github.com/jdagdelen/hype… Retweet this and I'll give you early access via DM. Now accepting SAFEs at a $35M cap. - “LLMs will kill Google Search” vibes are so funny, Like G doesn't know about LLMs.
This Post is from an account that no longer exists. Learn more - It's fascinating how a small 3B model like ColPALI can disrupt the PDF extraction industry overnight
- Omg, what a goldmine of a dataset? Millions of midjourney prompts and links to the generated image
- Vector DB Chroma raises $18M at a $75M valuation. Uses hnswlib for vector search. trychroma.com/blog/seed
