Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
Commits on master
feat(api): introduce virtual model ID and description for model endpoints
f504cff myhloli committed 1 month ago
feat(parse): enhance output path validation and add tests for single and multi-file scenarios
ee87e8e myhloli committed 1 month ago
feat(gradio): implement UUID fallback for insecure contexts and update tests
d34a79e myhloli committed 1 month ago
chore: add .zcodeignore for build artifacts and temporary files
1aa76ac myhloli committed 1 month ago
feat(pdf): implement code span spacing protection and update tight spacing logic
f712c9f myhloli committed 1 month ago
Merge pull request #44 from myhloli/codex/pdf-native-kernel
c422f78 Xiaomeng Zhao committed 1 month ago
ci(pdf): require owned script protocol in installed wheel checks
3992ff9 myhloli committed 1 month ago
perf(pdf): consume native span content without character regrouping
8adde38 myhloli committed 1 month ago
perf: consume native span assignments in shared PDF text filling
646f535 myhloli committed 1 month ago
test: validate snapshot wheels and deterministic rendering failures
c42b884 myhloli committed 1 month ago
ci: verify installed wheel payload without optional archive hash
75c77e2 myhloli committed 1 month ago
test(pdf): validate exact native engine wheels across host platforms
e149025 myhloli committed 1 month ago