jeonsworld
Follow
Starred repositories
All-in-One: Text Embedding, Retrieval, Reranking and RAG in Transformers
A new DSL and server for AI agents and multi-step tasks
Collection of awesome LLM apps with RAG using OpenAI, Anthropic, Gemini and opensource models.
File Parser optimised for LLM Ingestion with no loss ๐ง Parse PDFs, Docx, PPTx in a format that is ideal for LLMs.
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.
๐๐ค Crawl4AI: Crawl Smarter, Faster, Freely. For AI.
๐ฐ Newspaper4k a fork of the beloved Newspaper3k. Extraction of articles, titles, and metadata from news websites.
The lazier way to manage everything docker
Simple, unified interface to multiple Generative AI providers
Flexible and powerful framework for managing multiple AI agents and handling complex conversations
SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.
The paper list of the 86-page paper "The Rise and Potential of Large Language Model Based Agents: A Survey" by Zhiheng Xi et al.
Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.
Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting yoโฆ
An Open Source Toolkit For LLM Distillation
Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
A blazing fast inference solution for text embeddings models
WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)
ํ๊ตญ์ด ๋ฌธ์ฅ ๋ด ๊ด๊ณ ์ถ์ถ์ ํตํ ์ง์ ๊ทธ๋ํ๋ฅผ ๊ตฌ์ถํ๋ ๋ฐฉ๋ฒ์ ๋ํด ์ฐ๊ตฌํ ํ๋ก์ ํธ์ ๋๋ค.
Near-Realtime audio transcription using self-hosted Whisper and WebSocket in Python/JS
Fast, Accurate, Lightweight Python library to make State of the Art Embedding
Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/
Official repository for "Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing". Your efficient and high-quality synthetic data generation pipeline!
