Top AI Models Library: LLMs, Agents & Dev Tools
Curated reviews of mainstream AI models, agents, and dev tools — capabilities, use cases, and how they compare.
Tag: Embedding & RAG
50 article(s) found · Clear tag
TalkLikeYou — In-Depth Review of the Open-Source Real-Time Digital Human Framework from the Institute of Automation, Chinese Academy of Sciences
TalkLikeYou is an open-source real-time digital human (talking head) generation framework developed by the Institute of Automation, Chinese Academy of Sciences. Its core capability lies in generating ...
OpenViking – ByteDance's Open-Source AI Agent Context Database
OpenViking is an open-source AI Agent context database developed by ByteDance's Volcano Engine. Its core idea is to unify the Agent's memory, knowledge RAG, and skills within a custom `viking://` virt...
R2T2 – In-Depth Review of NetEase Youdao's Open-Source Low-Latency True Streaming Speech Recognition Model
R2T2 (Real Real-Time Transcription) is a low-latency true streaming speech recognition model open-sourced by NetEase Youdao, built upon the Qwen3-ASR architecture. It employs an append-only mechanism ...
Ok Work – Baidu's AI On-the-Go Office Tool
Ok Work is Baidu's lightweight AI on-the-go office tool, running in the form of a WeChat Mini Program, targeting students and new professionals, and focusing on fragmented office scenarios. The produc...
Jev Search: Open Source AI Search Engine, Achieving Intent Parsing and Multi-Engine Aggregation Based on the Jev Model
Jev Search is an open-source AI search engine frontend developed by the Search1API team. Its core functionality lies in leveraging the Jev structured decision model introduced by the TypeSafe team, en...
WebCraftBench – A Benchmark for AI Web Page Generation Introduced by Tencent in Collaboration with Tsinghua University
WebCraftBench is a benchmark for evaluating the quality of AI-generated web applications, introduced jointly by Tencent HunYuan, Tsinghua University, and Peking University. It aims to address the indu...
Xiaomi-CocktailASR-1: In-Depth Evaluation of a Target Speaker ASR Model Based on an End-to-End LLM Architecture
Xiaomi-CocktailASR-1 is Xiaomi's open-source Target Speaker ASR (TS-ASR) large model, designed using an end-to-end LLM architecture. It uses a reference speech as a speaker embedding prompt to accurat...
Deep Dive into RAG (Retrieval Augmented Generation) for Large Models: From Basic Workflows to Advanced Retrieval Architectures and Optimization
I want to explain RAG (Retrieval Augmented Generation) from the basics to advanced concepts, as it has become one of the most popular solutions for deploying large models in real-world applications. I
EchoWM – Interactive Audio-Visual World Model Open-Sourced by JD.com
EchoWM is an interactive audio-visual world model open-sourced by the JD.com Exploration Research Institute. It continues the native audio-visual generation capabilities of JoyAI-Echo, allowing users ...
teamai-cli – Tencent's Open-Source AI Team Collaboration CLI Tool
TeamAI CLI is an open-source MIT-licensed command-line tool developed by Tencent, designed to uniformly manage a team's AI programming configuration system. This tool centralizes AI collaboration reso...
Subscribe to AI Model Reviews
Get in-depth reviews the moment a new AI model drops. Know its capabilities and use cases.
We never share your email. Unsubscribe anytime.