NVIDIA Ingest is a set of microservices for parsing hundreds of thousands of complex, messy unstructured PDFs and other enterprise documents into metadata and text to embed into retrieval systems.

🏡 Open source home automation that puts local control and privacy first.

NIM Agent Blueprint for multimodal PDF extraction

Scalable toolkit for data curation

Apache NiFi

Generative AI reference workflows optimized for accelerated infrastructure and microservice architecture.

🔍 LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d…

Apache Arrow DataFusion Python Bindings

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

LlamaIndex (formerly GPT Index) is a data framework for your LLM applications

⚡ Building applications with LLMs through composability ⚡

A generative AI extension for JupyterLab

Apache Arrow DataFusion and Ballista query engines

Fast multi-threaded, hybrid-out-of-core query engine focussing on DataFrame front-ends

cuDF - GPU DataFrame Library

PandasAI is the Python library that integrates Gen AI into pandas, making data analysis conversational

Distributed SQL Engine in Python using Dask

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applicat…

Extensible SQL Lexer and Parser for Rust

NeMo: a toolkit for conversational AI

Enable non-Ubiquiti cameras to work with Unifi NVR

JSON Schema -> Rust type converter

Parallel computing with task scheduling