mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-23 14:38:35 +00:00
lancedb-gatefixer[bot]
9e8f1c1a6d
## Summary - expose `memory_limit` and `num_workers` on the Python FTS configuration for local builds - forward both build-only settings to the Lance inverted-index builder - add an end-to-end regression proving the configured memory budget reaches the native build ## Root cause LanceDB 0.26.1 pinned Lance 1.0.1. That Lance version used an FTS partition-merge path whose retained data made memory grow with merge progress on very large indexes. Upstream Lance [#5754](https://github.com/lance-format/lance/pull/5754) changed partition merging to stream its inputs, reducing peak memory by about 25%. Lance [#6174](https://github.com/lance-format/lance/pull/6174) then removed the old merge phase, compressed posting lists during construction, reduced indexing memory by about 60%, and introduced a total build `memory_limit` for bounded workers. Current `main` pins Lance 11.0.0-beta.3, which contains those architectural fixes. This PR does not duplicate or claim the upstream leak fix; it addresses the remaining Python API gap. ## This repair LanceDB Python did not expose the native FTS builder resource controls. `memory_limit` now sets the total local-build budget in MiB, divided among effective workers, and `num_workers` controls build parallelism. Both are build-only settings and do not affect remote builds or persisted index configuration. ## Validation - `cargo check --quiet --features remote --tests --examples` - `cargo fmt --all` - `uv run --project python --extra tests --extra dev ruff check .` - `uv run --project python --extra tests --extra dev ruff format --check python/python/lancedb/index.py python/python/tests/test_fts.py` - `uv run --project python --extra tests pytest python/tests/test_fts.py -q` (51 passed) Fixes #2923 <!-- lance-gatekeeper-fix:v1 agent=a1ceedf74531e0212cb6f1ebf9390a26 generation=1 --> --------- Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
52 lines
1.5 KiB
TOML
52 lines
1.5 KiB
TOML
[package]
|
|
name = "lancedb-python"
|
|
version = "0.38.0-beta.3"
|
|
publish = false
|
|
edition.workspace = true
|
|
description = "Python bindings for LanceDB"
|
|
license.workspace = true
|
|
repository.workspace = true
|
|
keywords.workspace = true
|
|
categories.workspace = true
|
|
rust-version = "1.91.0"
|
|
|
|
[lib]
|
|
name = "_lancedb"
|
|
crate-type = ["cdylib"]
|
|
|
|
[dependencies]
|
|
arrow = { workspace = true, features = ["pyarrow"] }
|
|
async-trait.workspace = true
|
|
bytes.workspace = true
|
|
lancedb.workspace = true
|
|
datafusion-common.workspace = true
|
|
lance-core.workspace = true
|
|
lance-namespace.workspace = true
|
|
lance-namespace-impls.workspace = true
|
|
lance-io.workspace = true
|
|
env_logger.workspace = true
|
|
log.workspace = true
|
|
# Maturin enables extension-module mode for Python builds. Keeping it out of
|
|
# Cargo features lets Rust unit tests link against libpython.
|
|
pyo3 = { version = "0.28", features = ["abi3-py310", "chrono"] }
|
|
chrono.workspace = true
|
|
pyo3-async-runtimes = { version = "0.28", features = [
|
|
"attributes",
|
|
"tokio-runtime",
|
|
] }
|
|
pin-project.workspace = true
|
|
futures.workspace = true
|
|
serde.workspace = true
|
|
serde_json.workspace = true
|
|
snafu.workspace = true
|
|
tokio.workspace = true
|
|
libc = "0.2"
|
|
|
|
[build-dependencies]
|
|
pyo3-build-config = { version = "0.28", features = ["abi3-py310"] }
|
|
|
|
[features]
|
|
default = ["remote", "lancedb/aws", "lancedb/gcs", "lancedb/azure", "lancedb/dynamodb", "lancedb/oss", "lancedb/huggingface", "lancedb/cos", "lancedb/goosefs", "lancedb/metrics-otel"]
|
|
fp16kernels = ["lancedb/fp16kernels"]
|
|
remote = ["lancedb/remote"]
|