Stars
Easily deploy Haystack pipelines as REST APIs and MCP Tools.
Additional packages (components, document stores and the likes) to extend the capabilities of Haystack
🌐 List of all countries with names and ISO 3166-1 codes in all languages and data formats.
Developer APIs to Accelerate LLM Projects
Superduper: End-to-end framework for building custom AI applications and agents.
📋 A list of open LLMs available for commercial use.
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A multilingual version of MS MARCO passage ranking dataset
Accessible large language models via k-bit quantization for PyTorch.
A Python SDK to interact with deepset Cloud
Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform
Convert Notion pages, blocks, or entire lists into any format: Markdown, MDX, JSX, HTML, LaTeX, and more. A powerful Notion conversion engine that lets you write once in Notion and publish seamless…
🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.
24 Lessons, 12 Weeks, Get Started as a Web Developer
A collection of large question answering datasets
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…
🦄 An NLP application just for the lols: built with Haystack to get an overview of what a user is posting about on Twitter
Running large language models on a single GPU for throughput-oriented scenarios.
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
The official Python client for the Hugging Face Hub.
A playbook for systematically maximizing the performance of deep learning models.
A collection of datasets and other resources for legal text processing.
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities