https://github.com/nvidia-ai-blueprints/multimodal-pdf-data-extraction
NIM Agent Blueprint for multimodal PDF data extraction for enterprise RAG
https://github.com/nvidia-ai-blueprints/multimodal-pdf-data-extraction
Last synced: 5 months ago
JSON representation
NIM Agent Blueprint for multimodal PDF data extraction for enterprise RAG
- Host: GitHub
- URL: https://github.com/nvidia-ai-blueprints/multimodal-pdf-data-extraction
- Owner: NVIDIA-AI-Blueprints
- Created: 2024-08-22T16:46:31.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-09-24T20:40:48.000Z (about 1 year ago)
- Last Synced: 2024-11-12T20:41:50.183Z (11 months ago)
- Homepage: https://build.nvidia.com/nvidia/multimodal-pdf-data-extraction-for-enterprise-rag
- Size: 2.16 MB
- Stars: 44
- Watchers: 3
- Forks: 9
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
NVIDIA AI Blueprint: Multimodal PDF Data Extraction
Rapidly ingest massive volumes of PDF documents. Extract text, graphs, charts, and tables for highly accurate retrieval.
## Introduction
This blueprint is based on [NVIDIA-Ingest](https://github.com/NVIDIA/nv-ingest) -- a scalable, performance-oriented document content and metadata extraction microservice. It includes support for parsing PDFs, Word and PowerPoint documents, using specialized NVIDIA NIM microservices to find, contextualize, and extract text, tables, charts and images for use in downstream generative applications.
NVIDIA Ingest enables parallel document splitting to rapidly extract data from many documents at the same time.
## Get Started
1. Apply for [Early Access](https://developer.nvidia.com/nemo-microservices).
2. Follow the getting started documentation [here](https://github.com/NVIDIA/nv-ingest).
**NOTE** -- the downloadable blueprint deploys the document ingestion pipeline. It does not include a retrieval pipeline.