Skip to content

Commit

Permalink
refactor: improve posting cursor (#32)
Browse files Browse the repository at this point in the history
## bench

machine: 8 vCPU, 32 GB, AMD Ryzen 7 7700, hyper-v Virtualization

VectorChord-bm25 (unicode tokenizer)
| dataset | topk | qps | NDCG@10 |
| ---- | -- | -- | ---- |
| trec-covid | 10 | 175.19 | 0.64728 |
| trec-covid | 1000 | 51.87 | 0.64665 |
| webis-touche2020 | 10 | 121.26 | 0.33956 |
| webis-touche2020 | 1000 | 45.83 | 0.33956 |
| fiqa | 10 | 303.44 | 0.25465 |
| fiqa | 1000 | 61.45 | 0.25465 |

elastic-search
| dataset | topk | qps | NDCG@10 |
| ---- | -- | -- | ---- |
| trec-covid | 10 | 138.73 | 0.68803 |
| trec-covid | 1000 | 48.77 | 0.68803 |
| webis-touche2020 | 10 | 182.16 | 0.34707 |
| webis-touche2020 | 1000 | 38.07 | 0.34707 |
| fiqa | 10 | 326.91 | 0.25364 |
| fiqa | 1000 | 60.07 | 0.25364 |

---------

Signed-off-by: Mingzhuo Yin <[email protected]>
  • Loading branch information
silver-ymz authored Jan 24, 2025
1 parent 988c77e commit f9fb146
Show file tree
Hide file tree
Showing 22 changed files with 1,223 additions and 874 deletions.
6 changes: 6 additions & 0 deletions Cargo.toml
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,8 @@ name = "pgrx_embed_vchord_bm25"
path = "./src/bin/pgrx_embed.rs"

[features]
pg12 = ["pgrx/pg12"]
pg13 = ["pgrx/pg13"]
pg14 = ["pgrx/pg14"]
pg15 = ["pgrx/pg15"]
pg16 = ["pgrx/pg16"]
Expand All @@ -34,6 +36,7 @@ tantivy-stemmers = { version = "0.4.0", features = [
thiserror = "2"
tokenizers = { version = "0.20", default-features = false, features = ["onig"] }

bincode = "1.3.3"
generator = "0.8.4"
lending-iterator = "0.1.7"
serde = { version = "1.0.217", features = ["derive"] }
Expand All @@ -59,3 +62,6 @@ codegen-units = 8
missing_safety_doc = "allow"
new_without_default = "allow"
not_unsafe_ptr_arg_deref = "allow"

[lints.rust]
unexpected_cfgs = { level = "warn", check-cfg = ['cfg(pgrx_embed)'] }
Loading

0 comments on commit f9fb146

Please sign in to comment.