Edward Kim issues

Results 32 issues of


                                            Edward Kim

update library mode test to match example script output

## Description ## Checklist - [ ] I am familiar with the [Contributing Guidelines](https://github.com/NVIDIA/nv-ingest/blob/main/CONTRIBUTING.md). - [ ] New or existing tests cover these changes. - [ ] The documentation is...

Enable multimodal embeddings with vlm-embed model

Enable Ingestor to save results to disk

## Description Resolves #722 This PR introduces a new capability to the nv-ingest-client.Ingestor class, allowing users to save the results of an ingestion process directly to disk. This is particularly...

[perf] Enable Ingestor to save results to disk

update the ingest_async api to mirror the existing sycn api

[FEA]: Deduplicate images that match any tables or charts

### Is this a new feature, an improvement, or a change to existing functionality? New Feature ### How would you describe the priority of this feature request Significant improvement ###...

feature request

Add pdf extraction strategy for docx and pptx

## Description This PR enhances the extraction capabilities for Microsoft Office documents (`.docx` and `.pptx`) by introducing LibreOffice into the container environment. It introduces two major features: 1. OLE object...

Add optional FastAPI server for open-source NR-OCR

## Description ```shell docker compose -f docker-compose.yaml -f docker-compose.oss-ocr.yaml \ --profile table-structure --profile retrieval up -d --build ``` If you get rate-limited by Hugging Face, add your HF token in...

Install the headless version of opencv

Ingest in chunks

## Description This PR introduces a new method `ingest_in_chunks` to the Ingestor class. ### Before Currently, users who need to process very large datasets that don't fit on disk must...