chtlp

data-juicer

A one-stop data processing system to make data higher-quality, juicier, and more digestible for (multimodal) LLMs! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷为大模型提供更高质量、更丰富、更易”消化“的数据！

LaVIT

LaVIT: Empower the Large Language Model to Understand and Generate Visual Content

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

DB-GPT

AI Native Data App Development framework with AWEL(Agentic Workflow Expression Language) and Agents

langfuse

🪢 Open source LLM engineering platform: Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23

DataX

DataX是阿里云DataWorks数据集成的开源版本。

sglang

SGLang is a structured generation language designed for large language models (LLMs). It makes your interaction with models faster and more controllable.

bisheng

Bisheng is an open LLM devops platform for next generation AI applications.

guidance-for-custom-search-of-an-enterprise-knowledge-base-with-amazon-opensearch-service

vanna

🤖 Chat with your SQL database 📊. Accurate Text-to-SQL Generation via LLMs using RAG 🔄.

setfit

Efficient few-shot learning with Sentence Transformers

guardrails

Adding guardrails to large language models.

fastText

Library for fast text representation and classification.

WikiChat

WikiChat stops the hallucination of large language models by retrieving data from Wikipedia.

papermage

library supporting NLP and CV research on scientific papers

streaming-llm

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

splade

SPLADE: sparse neural search (SIGIR21, SIGIR22)

distilabel

⚗️ distilabel is a framework for synthetic data and AI feedback for AI engineers that require high-quality outputs, full data ownership, and overall efficiency.

quokka

Making data lake work for time series

ray-llm

RayLLM - LLMs on Ray

rivet

The open-source visual AI programming environment and TypeScript library

openllmetry

Open-source observability for your LLM application, based on OpenTelemetry

pdf2htmlEX

Convert PDF to HTML without losing text or format.

UniIR

Official code for paper "UniIR: Training and Benchmarking Universal Multimodal Information Retrievers" (ECCV 2024)

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

instill-core

🔮 Instill Core is a full-stack AI infrastructure tool for data, model and pipeline orchestration, designed to streamline every aspect of building versatile AI-first applications

GPTs

leaked prompts of GPTs

phoenix

AI Observability & Evaluation

dingo

A multi-modal vector database that supports upserts and vector queries using unified SQL (MySQL-Compatible) on structured and unstructured data, while meeting the requirements of high concurrency and ultra-low latency.

xyflow

React Flow | Svelte Flow - Powerful open source libraries for building node-based UIs with React (https://reactflow.dev) or Svelte (https://svelteflow.dev). Ready out-of-the-box and infinitely customizable.