A blazing fast inference solution for text embeddings models

MTEB: Massive Text Embedding Benchmark

Fast State-of-the-Art Static Embeddings

🤖 A Python library for learning and evaluating knowledge graph embeddings

A novel Multimodal Large Language Model (MLLM) architecture, designed to structurally align visual and textual embeddings.

AI Inference Operator for Kubernetes. The easiest way to serve ML models in production. Supports VLMs, LLMs, embeddings, and speech-to-text.

Easily compute clip embeddings and build a clip retrieval system with them

A curated set of agent skills for the Venice AI API, providing SKILL.md instructions for agent runtimes like Cursor, Claude, and Codex.

Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or composition recipes that chain existing ones) for the patterns not yet covered. Use when the user asks to analyze their recent work and propose skills based on what they actually do. Requires the screenpipe daemon (https://github.com/screenpipe/screenpipe) running locally on port 3030 — the skill has no other data source and will refuse to run if screenpipe is unreachable. All detection runs locally; only redacted cluster summaries reach the LLM.

A deep dive into embeddings starting from fundamentals

Rust library for generating vector embeddings, reranking locally!