mirror of
https://github.com/seaweedfs/seaweedfs.git
synced 2026-10-27 23:40:41 +01:00
Chris LuandDevin
7388d0d4fc
* vector: scaffold the seaweed-vector workspace Standalone cargo workspace for the vector query engine, mirroring the seaweed-worker layout: own lockfile, same lint policy, path dependencies across the two trees since there is no common root manifest. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * vector: resolve a table's vector layout VectorTable::resolve finds the vector column (explicit name, else the column named vector, else the sole fixed-size float list), the optional key column, and the metadata columns a query can project. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * vector: flat and indexed top-k, key lookup query::flat runs an exact scan (use_index(false)); query::ann lets Lance split the query between index segments and a flat pass over fragments no index covers yet, so rows written after the last index build stay eligible. Both honour a metadata filter and return the raw _distance in the query's metric. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * vector: reject a non-utf8 or non-identifier key column An explicit --key-column naming a non-UTF8 field made hits() silently report row ids as keys, and get() interpolated the name into a SQL filter verbatim. Require Utf8 at resolve and in hits(), and require a plain identifier before building the IN predicate. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * vector: fall back to row id on a null key keys.value() on a null slot fabricates an empty-string key; a row with no key reports its row id instead, matching the no-key-column case. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * vector: quote the key column in the IN filter A Utf8 key column named e.g. document-key made the predicate parse as subtraction, and an identifier interpolated unquoted is injectable. Backtick-quote it and double its inner backticks; double quotes are string literals in the filter dialect, not identifiers. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> * vector: project only the columns a hit needs The knn projection pulled every metadata column — including other vector columns — although Hit returns none of them. Filters still evaluate off the scan path, so restrict the output to the key and the scoring columns. Generated with [Devin](https://devin.ai) Co-Authored-By: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Devin <158243242+devin-ai-integration[bot]@users.noreply.github.com>
35 lines
889 B
TOML
35 lines
889 B
TOML
[package]
|
|
name = "weed-vector-core"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
description = "Vector query engine over SeaweedFS Lance table buckets"
|
|
|
|
[lib]
|
|
name = "weed_vector_core"
|
|
|
|
[dependencies]
|
|
# The catalog client and dataset-opening helper the maintenance worker uses.
|
|
# A path dependency because the two trees are separate cargo workspaces with
|
|
# no common root manifest.
|
|
weed-lance-worker = { path = "../../../seaweed-worker/crates/lance" }
|
|
lance = { version = "10", default-features = false, features = ["aws"] }
|
|
lance-index = "10"
|
|
lance-linalg = "10"
|
|
lance-table = "10"
|
|
arrow-array = "58"
|
|
arrow-schema = "58"
|
|
roaring = "0.11"
|
|
anyhow.workspace = true
|
|
futures = "0.3"
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
tokio.workspace = true
|
|
tracing.workspace = true
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3"
|
|
|
|
[lints]
|
|
workspace = true
|