mu-ref/pdf-inspector
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(vision): add OCR routing (#358)

Browse Source 
* feat(vision): add OCR routing

* fix(vision): serialize model acquisition

* refactor(vision): name routed OCR results
This commit is contained in:
Abimael Martell
2026-08-16 23:55:52 -07:00
committed by GitHub
parent 12d30b43b0
commit e460a45f73
6 changed files with 838 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Cargo.toml
+4
View File
@@ -62,6 +62,9 @@ sha2 = { version = "0.11", optional = true }
image = { version = "0.25.6", default-features = false, optional = true }
oar-ocr = { version = "0.9.1", default-features = false, features = ["simd"], optional = true }
ort = { version = "=2.0.0-rc.13", default-features = false, features = ["load-dynamic"], optional = true }
# HTTPS-only streaming downloader for pinned model artifacts. Kept separate
# from model-cache so offline and package-managed deployments avoid HTTP/TLS.
ureq = { version = "3.4", default-features = false, features = ["rustls", "platform-verifier"], optional = true }
[target.'cfg(all(windows, not(target_arch = "wasm32")))'.dependencies]
windows-sys = { version = "0.61", features = ["Win32_Storage_FileSystem"], optional = true }
@@ -80,6 +83,7 @@ default = []
python = ["pyo3"]
vision = []
model-cache = ["vision", "dep:dirs", "dep:fs2", "dep:sha2", "dep:windows-sys"]
model-download = ["model-cache", "dep:ureq"]
ocr-oar = ["model-cache", "dep:image", "dep:oar-ocr", "dep:ort"]
render-pdfium = ["vision", "dep:firecrawl-pdfium"]