Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
pareshmishra
/
document-Intelligence-OCR
Like
0
Running
on
Zero
App
Files
Files
Community
Fetching metadata from the HF Docker repository...
main
document-Intelligence-OCR
/
src
26.9 kB
Ctrl+K
Ctrl+K
1 contributor
History:
10 commits
pareshmishra
Streamline prompt for fast sub-5s LLM evaluation
fab4da3
about 2 months ago
__init__.py
Safe
136 Bytes
Initial AI Document Intelligence OCR implementation
about 2 months ago
config.py
Safe
2.07 kB
Update default model to nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
about 2 months ago
document_analyzer.py
Safe
6.01 kB
Gracefully display OCR extracted text when LLM encounters authentication errors
about 2 months ago
nvidia_client.py
Safe
5.14 kB
Optimize LLM latency by disabling chain-of-thought generation for direct JSON extraction
about 2 months ago
ocr_service.py
Safe
8.37 kB
Optimize OCR pre-warming and RapidOCR execution order
about 2 months ago
prompts.py
Safe
1.38 kB
Streamline prompt for fast sub-5s LLM evaluation
about 2 months ago
schemas.py
Safe
3.82 kB
Build OCR document intelligence V1
about 2 months ago
