docling 0.41.2

DocumentConverter and format backends for docling.rs (a Rust port of docling).
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72

[package]
name = "docling"
description = "DocumentConverter and format backends for docling.rs (a Rust port of docling)."
version.workspace = true
edition.workspace = true
license.workspace = true
repository.workspace = true
homepage.workspace = true
readme.workspace = true
keywords.workspace = true
categories.workspace = true
rust-version.workspace = true
# The 25 MB output-regression corpus under tests/ is dev-only — keep it out of
# the published crate (and under crates.io's size limit). benches/ reference that
# corpus by path, so they're dev-only too.
exclude = ["tests", "benches"]

[features]
# Optional headless-browser HTML pre-render (the `--use-web-browser` flag /
# `DocumentConverter::use_web_browser`). Off by default so the standard build
# stays pure-Rust with no browser/runtime dependency; enable with
# `--features web-browser`. Drives the system Chromium over the DevTools
# protocol purely from Rust (no Node/Playwright) via `headless_chrome`.
web-browser = ["dep:headless_chrome"]
# Tokenization-aware chunking (docling-core's HybridChunker + HF tokenizer).
chunking = ["docling-core/chunking"]
# GPU execution providers for the PDF/image ML pipeline (#74) — pass-through
# to docling-pdf; select at runtime with DOCLING_RS_EP (default: cpu).
cuda = ["docling-pdf/cuda"]
tensorrt = ["docling-pdf/tensorrt"]
directml = ["docling-pdf/directml"]
coreml = ["docling-pdf/coreml"]

[dependencies]
calamine = { version = "0.26", features = ["dates"] }
csv = "1.4.0"
headless_chrome = { version = "1.0", optional = true }
docling-asr = { path = "../docling-asr", version = "0.41.2" }
docling-core = { path = "../docling-core", version = "0.41.2" }
docling-pdf = { path = "../docling-pdf", version = "0.41.2" }
image = { version = "0.25", default-features = false, features = ["png", "jpeg", "gif", "bmp", "tiff", "webp"] }
mail-parser = "0.11"
pulldown-cmark = { version = "0.13.4", default-features = false }
quick-xml = "0.37"
# Data-parallel fan-out over independent OOXML parts (XLSX sheets, PPTX
# slides) — see the profile in the module docs of `backend/xlsx.rs`.
rayon = "1.10"
regex = "1.11"
roxmltree = "0.20"
scraper = "0.27.0"
serde_json = "1"
# Blocking HTTP client for fetching remote <img src> images when image fetching
# is enabled (DocumentConverter::fetch_images). 3.x matches the version `ort`
# already pulls in (so the graph keeps a single ureq); it needs Rust 1.85, which
# this crate already requires transitively via docling-pdf → ort.
ureq = "3"
zip = { version = "2.2", default-features = false, features = ["deflate"] }

[[example]]
name = "convert"
path = "examples/convert.rs"

[[example]]
name = "stream"
path = "examples/stream.rs"

[dev-dependencies]
criterion = "0.5"

[[bench]]
name = "parse"
harness = false