Spaces:

Duplicated from DataEyond/Agentic-Service-Data-Eyond

DataEyond
/

Agentic-Service-Data-Eyond-Catalog

Sleeping

App Files Files Community

Agentic-Service-Data-Eyond-Catalog / src /knowledge_parsing

127 kB

Ctrl+K

Ctrl+K

5 contributors

History: 30 commits

sofhiaazzhr's picture

Claude Opus 4.8

[NOTICKET] feat(knowledge-parsing): read MISTRAL_API_KEY through app settings

85c9c28 about 2 months ago

README.md

11.8 kB
[NOTICKET] docs(knowledge): reflect Mistral OCR as the primary parser about 2 months ago
__init__.py

783 Bytes
[NOTICKET] feat(knowledge-parsing): document parsing half of the knowledge pipeline 2 months ago
checks.py

8.98 kB
[NOTICKET] refactor(knowledge-parsing): English throughout the module 2 months ago
config.py

7.82 kB
[NOTICKET] feat(knowledge-parsing): wire Mistral OCR backend end-to-end about 2 months ago
contracts.py

12.6 kB
[NOTICKET] feat(knowledge-parsing): add 1-based page_no (S6b) about 2 months ago
manifest.py

3.1 kB
[NOTICKET] refactor(knowledge-parsing): English throughout the module 2 months ago
mistral_ocr.py

4.23 kB
[NOTICKET] feat(knowledge-parsing): read MISTRAL_API_KEY through app settings about 2 months ago
normalize.py

17 kB
[NOTICKET] feat(knowledge-parsing): commit the reference artifact, and stop the stamp churning about 2 months ago
normalize_mistral.py

17.5 kB
[NOTICKET] feat(knowledge-parsing): Mistral OCR block normalizer (section default) about 2 months ago
parse.py

12.2 kB
[NOTICKET] feat(knowledge-parsing): wire Mistral OCR backend end-to-end about 2 months ago
render.py

12.1 kB
[NOTICKET] refactor(knowledge-parsing): English throughout the module 2 months ago
report.py

4.56 kB
[NOTICKET] docs(knowledge-parsing): settle determinism; finish the English pass 2 months ago
run.py

14.7 kB
[NOTICKET] feat(knowledge-parsing): parse_one() single-doc entry point + doc_id param (N9) about 2 months ago