Stars
Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.
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.
Python client library for Google Maps API Web Services
Table Transformer (TATR) is a deep learning model for extracting tables from unstructured documents (PDFs and images). This is also the official repository for the PubTables-1M dataset and GriTS ev…
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
⚡FlashRAG: A Python Toolkit for Efficient RAG Research
Explorations into some recent techniques surrounding speculative decoding
Evaluation framework for your Retrieval Augmented Generation (RAG) pipelines
Test your prompts, agents, and RAGs. Use LLM evals to improve your app's quality and catch problems. Compare performance of GPT, Claude, Gemini, Llama, and more. Simple declarative configs with com…
Sailor: Open Language Models for South-East Asia
Evaluate your LLM's response with Prometheus and GPT4 💯
Build AI Assistants with memory, knowledge and tools.
🪢 Open source LLM engineering platform: Observability, metrics, evals, prompt management, playground, datasets. Integrates with LlamaIndex, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
LLM-based Conversational Recommendation Architecture
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Retrieval and Retrieval-augmented LLMs
Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.
Democratizing Internet-scale financial data.
A quick guide (especially) for trending instruction finetuning datasets
An online playground for function calling and sending function calling arguments to a webhook!
Retrieve the source code for any model made available on replicate.com!
LMDeploy is a toolkit for compressing, deploying, and serving LLMs.
Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.
llama3 implementation one matrix multiplication at a time
A programming framework for agentic AI. Discord: https://aka.ms/autogen-dc. Roadmap: https://aka.ms/autogen-roadmap
Python SDK for agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks like CrewAI, Langchain, and Autogen
Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.