feat: introduce fuzzy search for native indexer (#14109)

This commit is contained in:
DarkSky
2025-12-25 04:40:23 +08:00
committed by GitHub
parent b6dc68eddf
commit e8693a3a25
24 changed files with 237 additions and 537 deletions

View File

@@ -17,10 +17,11 @@ doc-loader = [
"strum_macros",
"text-splitter",
"thiserror",
"tiktoken-rs",
"tree-sitter",
"url",
]
hashcash = ["sha3", "rand"]
hashcash = ["chrono", "sha3", "rand"]
tree-sitter = [
"cc",
"dep:tree-sitter",
@@ -39,24 +40,24 @@ tree-sitter = [
ydoc-loader = ["assert-json-diff", "serde", "serde_json", "thiserror", "y-octo"]
[dependencies]
chrono = { workspace = true }
rand = { workspace = true, optional = true }
sha3 = { workspace = true, optional = true }
assert-json-diff = { workspace = true, optional = true }
chrono = { workspace = true, optional = true }
docx-parser = { workspace = true, optional = true }
infer = { workspace = true, optional = true }
path-ext = { workspace = true, optional = true }
pdf-extract = { workspace = true, optional = true }
rand = { workspace = true, optional = true }
readability = { workspace = true, optional = true, default-features = false }
serde = { workspace = true, optional = true, features = ["derive"] }
serde_json = { workspace = true, optional = true }
sha3 = { workspace = true, optional = true }
strum_macros = { workspace = true, optional = true }
text-splitter = { workspace = true, features = [
"markdown",
"tiktoken-rs",
], optional = true }
thiserror = { workspace = true, optional = true }
tiktoken-rs = { workspace = true, optional = true }
tree-sitter = { workspace = true, optional = true }
tree-sitter-c = { workspace = true, optional = true }
tree-sitter-c-sharp = { workspace = true, optional = true }
@@ -72,11 +73,10 @@ tree-sitter-typescript = { workspace = true, optional = true }
url = { workspace = true, optional = true }
y-octo = { workspace = true, optional = true }
tiktoken-rs = { workspace = true }
[dev-dependencies]
criterion2 = { workspace = true }
rayon = { workspace = true }
criterion = { workspace = true }
rayon = { workspace = true }
tempfile = "3"
[build-dependencies]
cc = { version = "1", optional = true }