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

the LLM vulnerability scanner

Adding guardrails to large language models.

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

The open-source visual AI programming environment and TypeScript library

Drag & drop UI to build your customized LLM flow

Langflow is a low-code app builder for RAG and multi-agent AI applications. It’s Python-based and agnostic to any model, API, or database.

This series will take you on a journey from the fundamentals of NLP and Computer Vision to the cutting edge of Vision-Language Models.

Kickstart your LLMOps initiative with a flexible, robust, and productive Python package.

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

Synthetic data generation for tabular data

AWS Certified Solutions Architect – Professional (SAP-C02) Notes

Welcome to the AWS Certified Solutions Architect - Associate (AWS-SAA) Cheat Sheet repository!

Unified Training of Universal Time Series Forecasting Transformers

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

Benchmarking library for RAG

Code from blog 'Searching by Music: Leveraging Vector Search for Music Information Retrieval'

emr-apache-iceberg-workshop

Large Language Model Text Generation Inference

This repository contains a collection of notebooks that shows how to implement things such as CDC, SCD2, ML pipelines using Apache Iceberg & Spark

GLM-4-Voice | 端到端中英语音对话模型

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

A pytorch quantization backend for optimum

Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM