refactor: replace headless_chrome with lighter alternatives

This commit is contained in:
Per Stark
2026-06-21 18:15:54 +02:00
parent 87e6fa14b2
commit 588e616baf
19 changed files with 6440 additions and 639 deletions
+20 -7
View File
@@ -7,13 +7,18 @@ members = [
"ingestion-pipeline",
"retrieval-pipeline",
"json-stream-parser",
"evaluations"
"evaluations",
]
resolver = "3"
[workspace.dependencies]
anyhow = "1.0.94"
async-openai = { version = "0.41.1", features = ["chat-completion", "embedding", "audio", "model"] }
async-openai = { version = "0.41.1", features = [
"chat-completion",
"embedding",
"audio",
"model",
] }
async-stream = "0.3.6"
async-trait = "0.1.88"
axum-htmx = "0.7.0"
@@ -27,7 +32,6 @@ chrono = { version = "0.4.39", features = ["serde"] }
config = "0.15.4"
dom_smoothie = "0.10.0"
futures = "0.3.31"
headless_chrome = "1.0.17"
include_dir = "0.7.4"
mime = "0.3.17"
mime_guess = "2.0.5"
@@ -35,7 +39,7 @@ minijinja-autoreload = "2.5.0"
minijinja-contrib = { version = "2.6.0", features = ["datetime", "timezone"] }
minijinja-embed = { version = "2.8.0" }
minijinja = { version = "2.5.0", features = ["loader", "multi_template"] }
reqwest = {version = "0.12.12", features = ["charset", "json"]}
reqwest = { version = "0.12.12", features = ["charset", "json"] }
serde_json = "1.0.128"
serde = { version = "1", features = ["derive"] }
sha2 = "0.10.8"
@@ -61,14 +65,24 @@ bytes = "1.7.1"
state-machines = "0.9"
pdf-extract = "0.9"
lopdf = "0.32"
fastembed = { version = "5.2.0", default-features = false, features = ["hf-hub-native-tls", "ort-load-dynamic"] }
pdfium-auto = "0.3"
pdfium-render = "0.8"
servo-fetch = "0.13"
tendril = "0.4"
image = { version = "0.25", default-features = false, features = ["png"] }
fastembed = { version = "5.2.0", default-features = false, features = [
"hf-hub-native-tls",
"ort-load-dynamic",
] }
[profile.dist]
inherits = "release"
lto = "thin"
[workspace.lints.rust]
unexpected_cfgs = { level = "warn", check-cfg = ["cfg(feature, values(\"inspect\"))"] }
unexpected_cfgs = { level = "warn", check-cfg = [
"cfg(feature, values(\"inspect\"))",
] }
[workspace.lints.clippy]
# Performance-focused lints
@@ -118,4 +132,3 @@ needless_raw_string_hashes = "allow"
multiple_bound_locations = "allow"
cargo_common_metadata = "allow"
multiple-crate-versions = "allow"