NVIDIA Ingest is an early access 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.
Apache License 2.0
92
stars
42
forks
source link
[DOC]: Update documentation for direct extraction via low level library interface #220
How would you describe the priority of this documentation request
None
Please provide a link or source to the relevant docs
README.md
Describe the problems in the documentation
Adds instructions to include table_data_extract, and chart_data_extract tasks to a job spec when attempting to use OCR extraction for tables/charts.
(Optional) Propose a correction or improvement
No response