@@ -570,7 +570,7 @@ dependencies = [
"libc",
"pin-project",
"redox_syscall 0.2.16",
- "xattr 0.2.3",
+ "xattr",
]
[[package]]
@@ -903,15 +903,6 @@ dependencies = [
"wyz",
]
-[[package]]
-name = "blas-src"
-version = "0.8.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "bb48fbaa7a0cb9d6d96c46bac6cedb16f13a10aebcef1c4e73515aaae8c9909d"
-dependencies = [
- "openblas-src",
-]
-
[[package]]
name = "block"
version = "0.1.6"
@@ -1190,15 +1181,6 @@ version = "0.1.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a2698f953def977c68f935bb0dfa959375ad4638570e969e2f1e9f433cbf1af6"
-[[package]]
-name = "cblas-sys"
-version = "0.1.4"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b6feecd82cce51b0204cf063f0041d69f24ce83f680d87514b004248e7b0fa65"
-dependencies = [
- "libc",
-]
-
[[package]]
name = "cc"
version = "1.0.83"
@@ -4604,8 +4586,6 @@ version = "0.15.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "adb12d4e967ec485a5f71c6311fe28158e9d6f4bc4a447b474184d0f91a8fa32"
dependencies = [
- "cblas-sys",
- "libc",
"matrixmultiply",
"num-complex 0.4.4",
"num-integer",
@@ -4990,32 +4970,6 @@ version = "0.3.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "624a8340c38c1b80fd549087862da4ba43e08858af025b236e509b6649fc13d5"
-[[package]]
-name = "openblas-build"
-version = "0.10.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "eba42c395477605f400a8d79ee0b756cfb82abe3eb5618e35fa70d3a36010a7f"
-dependencies = [
- "anyhow",
- "flate2",
- "native-tls",
- "tar",
- "thiserror",
- "ureq",
- "walkdir",
-]
-
-[[package]]
-name = "openblas-src"
-version = "0.10.8"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "38e5d8af0b707ac2fe1574daa88b4157da73b0de3dc7c39fe3e2c0bb64070501"
-dependencies = [
- "dirs 3.0.2",
- "openblas-build",
- "vcpkg",
-]
-
[[package]]
name = "openssl"
version = "0.10.57"
@@ -6490,18 +6444,6 @@ dependencies = [
"webpki 0.22.1",
]
-[[package]]
-name = "rustls-native-certs"
-version = "0.6.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a9aace74cb666635c918e9c12bc0d348266037aa8eb599b5cba565709a8dff00"
-dependencies = [
- "openssl-probe",
- "rustls-pemfile",
- "schannel",
- "security-framework",
-]
-
[[package]]
name = "rustls-pemfile"
version = "1.0.3"
@@ -6820,7 +6762,6 @@ dependencies = [
"ai",
"anyhow",
"async-trait",
- "blas-src",
"client",
"collections",
"ctor",
@@ -6834,7 +6775,6 @@ dependencies = [
"log",
"ndarray",
"node_runtime",
- "openblas-src",
"ordered-float",
"parking_lot 0.11.2",
"picker",
@@ -7712,17 +7652,6 @@ version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "55937e1799185b12863d447f42597ed69d9928686b8d88a1df17376a097d8369"
-[[package]]
-name = "tar"
-version = "0.4.40"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b16afcea1f22891c49a00c751c7b63b2233284064f11a200fc624137c51e2ddb"
-dependencies = [
- "filetime",
- "libc",
- "xattr 1.0.1",
-]
-
[[package]]
name = "target-lexicon"
version = "0.12.11"
@@ -8797,21 +8726,6 @@ version = "0.7.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "a156c684c91ea7d62626509bce3cb4e1d9ed5c4d978f7b4352658f96a4c26b4a"
-[[package]]
-name = "ureq"
-version = "2.7.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0b11c96ac7ee530603dcdf68ed1557050f374ce55a5a07193ebf8cbc9f8927e9"
-dependencies = [
- "base64 0.21.4",
- "flate2",
- "log",
- "native-tls",
- "once_cell",
- "rustls-native-certs",
- "url",
-]
-
[[package]]
name = "url"
version = "2.4.1"
@@ -9865,15 +9779,6 @@ dependencies = [
"libc",
]
-[[package]]
-name = "xattr"
-version = "1.0.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f4686009f71ff3e5c4dbcf1a282d0a44db3f021ba69350cd42086b3e5f1c6985"
-dependencies = [
- "libc",
-]
-
[[package]]
name = "xmlparser"
version = "0.13.5"
@@ -1,5 +1,3 @@
-extern crate blas_src;
-
use crate::{
parsing::{Span, SpanDigest},
SEMANTIC_INDEX_VERSION,
@@ -440,25 +438,24 @@ impl VectorDatabase {
.filter_map(|row| row.ok())
.collect::<Vec<(usize, Embedding)>>();
- let batch_n = 250;
+ let batch_n = 1000;
let mut batches = Vec::new();
let mut batch_ids = Vec::new();
let mut batch_embeddings: Vec<f32> = Vec::new();
deserialized_rows.iter().for_each(|(id, embedding)| {
batch_ids.push(id);
batch_embeddings.extend(&embedding.0);
+
if batch_ids.len() == batch_n {
- let array =
- Array2::from_shape_vec((batch_ids.len(), 1536), batch_embeddings.clone());
+ let embeddings = std::mem::take(&mut batch_embeddings);
+ let ids = std::mem::take(&mut batch_ids);
+ let array = Array2::from_shape_vec((batch_ids.len(), 1536), embeddings);
match array {
Ok(array) => {
- batches.push((batch_ids.clone(), array));
+ batches.push((ids, array));
}
Err(err) => log::error!("Failed to deserialize to ndarray: {:?}", err),
}
-
- batch_ids = Vec::new();
- batch_embeddings = Vec::new();
}
});