An end-to-end vector search engine that handles embedding generation, storage, and retrieval in a single service for text and image search.
Marqo — Tensor Search Engine for AI-Powered Retrieval
An end-to-end vector search engine that handles embedding generation, storage, and retrieval in a single service for text and image search.
Ready-to-run agent install
This asset can be installed after the agent chooses its runtime, checks the plan, and runs the matching command.
npx -y tokrepo@latest install 8c50310e-5e1a-11f1-9bc6-00163e2b0d79 --target codexRun after dry-run confirms the install plan.
Discussion
Related Assets
ggml — Lightweight Tensor Library for Machine Learning in C
ggml is a pure C tensor library optimized for running machine learning models on CPUs and edge devices, providing the foundational compute layer used by llama.cpp, whisper.cpp, and other popular local AI inference tools.
einops — Flexible and Readable Tensor Operations
A library that provides a concise notation for tensor manipulations (reshape, transpose, reduce) that is framework-agnostic, self-documenting, and eliminates the error-prone dimension indexing common in deep learning code.
safetensors — Safe and Fast Tensor Serialization
A simple file format for storing tensors safely and efficiently, designed to eliminate security risks from pickle-based model files.
Text Generation Inference (TGI) — Hugging Face Production LLM Server
TGI is Hugging Face's production-grade LLM inference server. It powers HF Inference Endpoints with continuous batching, tensor parallelism, quantization, and OpenAI-compatible APIs — handling thousands of requests per second.