cognigraph-chunker/Cargo.toml at main · gedankrayze/cognigraph-chunker · GitHub

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
73
74
75
76
77
78
79
[workspace]
members = [".", "packages/python"]

[package]
name = "cognigraph-chunker"
version = "2.0.0"
edition = "2024"
license = "MIT"

[lib]
name = "cognigraph_chunker"
path = "src/lib.rs"

[[bin]]
name = "cognigraph-chunker"
path = "src/main.rs"

[dependencies]
# Core algorithms (from chunk library)
memchr = "2.8"
daggrs = "0.1"

# CLI
clap = { version = "4.5", features = ["derive"] }
clap_complete = "4.5"

# Serialization
serde = { version = "1.0", features = ["derive"] }
serde_json = "1.0"

# Async runtime
tokio = { version = "1.49", features = ["full"] }

# HTTP client (embedding providers)
reqwest = { version = "0.13", features = ["json", "form"] }

# ONNX Runtime (local embeddings)
ort = { version = "2.0.0-rc.11", features = ["ndarray", "load-dynamic"] }

# Tokenizer (for ONNX models)
tokenizers = "0.22"

# N-dimensional arrays (used by ort)
ndarray = "0.17"

# Unicode sentence segmentation
unicode-segmentation = "1.12"

# Language detection
whatlang = "0.18"

# Unicode script detection (entity heuristics for CJK, etc.)
unicode-script = "0.5"

# Markdown AST parsing
pulldown-cmark = "0.13"

# Web framework
axum = "0.8"
tower-http = { version = "0.6", features = ["cors", "timeout", "limit"] }

# URL parsing (SSRF validation)
url = "2"

# Error handling
anyhow = "1.0"

[profile.release]
strip = true
lto = true
codegen-units = 1
panic = "abort"

[dev-dependencies]
criterion = { version = "0.8", features = ["html_reports"] }

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