“embeddings”

Semantic code search engine powered by vector embeddings

All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Neum AI is a best-in-class framework for managing vector embeddings at large scale.

A vector index built on TurboQuant with Rust and Python bindings

Crawls web pages and documents, extracts text content, generates embeddings for summaries and answers questions.

Langchain-Chatchat is a local knowledge-based RAG and Agent application for LLMs like ChatGLM, Qwen and Llama.

Proactive context-aware AI partner

大模型应用开发实战一：RAG技术全栈指南

Memory library for building stateful agents

Less Code, Lower Barrier, Faster Deployment

LLM-powered knowledge curation and report generation

Unified platform to evaluate and improve Generative AI applications

Unified multimodal backend for AI data apps