Today SciPhi is open-sourcing Triplex, a SOTA LLM for knowledge graph construction. Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop. Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost.

Autists had a great run, the AI future belongs to ADHD

R2R from sciphi.ai is an open-source agentic retrieval system that transforms RAG with multi-step reasoning across your data and the web. ycombinator.com/launches/N4p…

Happy & sad to think that In 3-6 months I won't be coding anymore

old yc interviews are a goldmine

Open source projects using Ellipsis have earned over 105,787 GitHub Stars!⭐⭐ Thank you for trusting us to review your code! @huan2024 @ActivityWatchIt @WindmillLabs @jxnlco @hyperdxio @skyvernai @erxesHQ @ocolegro @zep_ai @truera_ai @DagWorks @nomicbtc @aloksingh @julep_ai @ShayRonen2 @milosgajdos @boundaryML and so many more... Ellipsis is FREE for most open source projects, DM/email us to get access or install at ellipsis.dev 😎

Some major upgrades to the SciPhi cloud are now live 1.) Free RAG completions through gpt-4o-mini (w/ documented support for other providers like anthropic, openai, etc.) 2.) Fast document ingestion 3.) Agentic RAG 4.) Control and customizability - bring your own docker w/ R2R

A few well projects have gotten into production with R2R & we're enjoying watching telemetry on total RAG requests go up and to the right. If you are using R2R in production we'd love to hear from you!

We are running a new YC batch this fall! Applications are now open: ycombinator.com/blog/yc-fall…

A small, portable vector database powered by SQLite for on-device RAG? 🤯 sqlite-vec is a new vector search SQLite extension written entirely in C with no dependencies, MIT/Apache-2.0 dual licensed.   sqlite-vec queries: - 1 million 128-dimensional vectors in just 17ms - 500,000 with 960-dimensional vectors in 41ms sqlite-vec supports: 💾 Matryoshka embedding slicing 💡 Binary quantization reduces storage by 32x with minimal accuracy loss 🤏🏻 L2, cosine and Hamming distance calculations 🧮 Retrieval against Python List and NP Arrays 🛠️ SDKs for Python, Javascript, Go, Rust, Wasm and more 🧠 local direct embedding with “sqlite-lembed” for gguf models and @ggerganov Llama.CPP ☁️ remote embedding with “sqlite-rembed” for @OpenAI compatible APIs

Yeah cool the old "Python is slow" argument is so clever

Microsoft GraphRAG Alternative and 10x Cheaper? 🚀 Introducing Sciphi/Triplex 💸 10x Cheaper 🤖 AI Knowledge Graph Extraction 🌟 Higher Accuracy 🛠️ Setup with @huggingface 🖥️ Local Run with @ollama 📊 Data Visualisation @neo4j Subscribe: youtube.com/@MervinPraison @sayshrey @ocolegro

I went for a one hour Tesla FSD 12.5 ride with @FuturamaKing. We tried all his biggest problem spots with 12.3.6, and 12.5 seems to have fixed them all. Watch in 4K: youtu.be/AQgFHUr3fFA

推上有个老哥 @ocolegro 将微软最近爆火开源的 GraphRAG 价格打下来了🔥 开源3.8B 端侧模型，价格仅 GPT-4o 的 1/60，构建知识图谱 SOTA LLM - Triplex 来了 📷 在线体验图谱构建 Demo：kg.sciphi.ai @ollama 地址：ollama.com/sciphi/triplex