Frameworks
LLM application development frameworks such as LangChain and LlamaIndex
LangChain Framework Tutorial
An in-depth tutorial on the LangChain framework, walking through its architecture and core modules—Chains, Agents, and Memory—with hands-on examples. It also covers RAG integration, custom tool development, and debugging strategies, making it a solid starting point for developers ready to move beyond simple prompts and build production-grade LLM applications.
Python AI/ML Libraries Collection
A curated roundup of the most widely used Python libraries for AI and machine learning, covering deep learning frameworks like TensorFlow and PyTorch, classical ML with Scikit-learn, data manipulation with NumPy and Pandas, and emerging tools for LLM integration. Each entry includes a brief description, typical use case, and installation command — a handy reference for practitioners building their ML toolkit.
Hugging Face Transformers Tutorial
The official tutorial for Hugging Face Transformers, the industry-standard library for NLP and computer vision. It covers text classification, tokenisation, translation, image segmentation, and more, with code examples for both PyTorch and TensorFlow backends. Aimed at practitioners who want to leverage pre-trained models or fine-tune them on custom datasets for production use.
LlamaIndex Framework Tutorial
A hands-on tutorial for LlamaIndex, the framework designed for building RAG applications that connect LLMs to custom data sources. It covers data ingestion pipelines, indexing strategies, query engines, and agent-based retrieval, with practical examples for PDF, web, and database connectors. Aimed at developers who want to build domain-specific AI assistants grounded in their own documents.
PyTorch Deep Learning Framework
PyTorch is a leading open-source deep learning framework developed by Meta, known for its dynamic computation graph and Pythonic interface. It powers both cutting-edge AI research and production deployments, with a rich ecosystem of tools for training, debugging, and scaling models across GPUs and TPUs.
vLLM High-Performance Inference Framework
vLLM is a high-throughput inference and serving engine for large language models, using PagedAttention to dramatically improve memory efficiency and throughput. It supports continuous batching, tensor parallelism, and OpenAI-compatible API serving, making it a top choice for deploying LLMs at scale.
Haystack RAG Framework
Haystack is an open-source framework by deepset for building production-ready LLM applications, specializing in retrieval-augmented generation (RAG) and question-answering pipelines. It offers modular components for document processing, embedding, and retrieval that connect easily with models from OpenAI, Hugging Face, and more.
DSPy
DSPy is a framework for programming language models rather than prompting them, by composing modular pipelines and automatically optimizing prompts and weights. Developed at Stanford, it replaces brittle prompt engineering with reproducible, testable programs that adapt across different models and tasks.
Exa
Exa — A search engine built for language models: neural web search that returns semantically relevant pages instead of keyword matches.
Komo
Komo — An AI-powered search portal that blends web results with conversational answers.
Phind
Phind — An AI search engine built for developers, pairing web results with technical answers and code.
privateGPT
privateGPT — Ask questions to your documents without an internet connection, using the power of LLMs.
You.com
You.com — A search engine built on AI that provides users with a customized search experience while keeping their data 100% private.
quivr
quivr — Dump all your files and chat with it using your generative AI second brain using LLMs & embeddings.
Kazimir.ai
Kazimir.ai — A search engine designed to search AI-generated images.
Metaphor
Metaphor — Language model powered search.
Telborg
Telborg — AI for Climate Research, with data exclusively from governments, international institutions and companies.
MemFree
MemFree — Open Source Hybrid AI Search Engine, Instantly Get Accurate Answers from the Internet, Bookmarks, Notes, and Docs.
privateGPT
privateGPT — Ask questions to your documents without an internet connection, using the power of LLMs.
quivr
quivr — Dump all your files and chat with it using your generative AI second brain using LLMs & embeddings.
Refinder AI
Refinder AI — AI-powered universal search and assistant for work.