content-extractor-rl-cli 1.0.0

RL-based article extraction from HTML using Deep Q-Networks and heuristic fallback
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

# crates/content-extractor-rl-cli/Cargo.toml

[package]
name = "content-extractor-rl-cli"
version.workspace = true
edition.workspace = true
authors.workspace = true
license.workspace = true
description.workspace = true
repository.workspace = true
homepage.workspace = true
documentation.workspace = true
keywords.workspace = true
categories.workspace = true
readme = "../../README.md"
publish = true

[[bin]]
name = "content-extractor-rl"
path = "src/main.rs"

[dependencies]
content-extractor-rl = { path = "../content-extractor-rl", version="1.0.0", features = ["cuda", "mlflow-rs"] }
clap.workspace = true
anyhow.workspace = true
tracing.workspace = true
tracing-subscriber.workspace = true
serde_json.workspace = true
tokio = { version = "1.52", features = ["full"] }
walkdir = "2.5"
indicatif = "0.18.4"
bzip2 = "0.6.1"
rand.workspace = true
tracing-appender = "0.2.5"
chrono = { version = "0.4", features = ["serde"] }
rayon = "1.12.0"
algorithm = "0.1.18"

[features]
default = []
cuda = ["content-extractor-rl/cuda"]
mlflow = ["content-extractor-rl/mlflow-rs"]