oneDAL is a C++ and DPC++ library for accelerated machine learning routines on tabular data, governed by the UXL Foundation.
Open source
24 alternativesLance
Lance provides an open lakehouse format for multimodal AI, with vector indexing and data versioning.
About Lance
Lance is an open lakehouse format for multimodal AI. It includes a file format, a table format, and a catalog specification for building a lakehouse on top of object storage for AI workflows. The project describes it as suited to building search engines and feature stores, to large-scale ML training that needs high-performance I/O and random access, and to storing and querying images, videos, audio, text, and embeddings.
The project lists vector similarity search, full-text search (BM25), and SQL analytics over the same dataset, along with data versioning with time travel, tags, and branches. It works with Pandas, DuckDB, Polars, PyArrow, Ray, Spark, and other tools. The project is in active development and releases frequently. Its SDK and API follow semantic versioning, and production data should be written with a stable data_storage_version, since the next file format alias is marked unstable.
Key features
- Hybrid search combining vector similarity, BM25 full-text search, and SQL on one dataset
- Random access the project states is 100x faster than Parquet or Iceberg
- Stores images, videos, audio, text, and embeddings in one format with blob encoding
- Adds columns with backfilled values without full table rewrites
- Automatic versioning with ACID transactions, time travel, tags, and branches
- Integrations with Pandas, Polars, DuckDB, PyArrow, Spark, Ray, Trino, and Flink
Best for: Machine learning engineers and data teams building search engines, feature stores, or large-scale ML training pipelines over multimodal data.
Good for
- Open source, with the repository publicly available on GitHub
- Combines vector, full-text, and SQL search over the same dataset
- Versioning and time travel are built in, according to the project, without extra infrastructure
Watch out for
- The project is in active development and releases frequently
- The next file format alias is unstable and should not be used for production data
- Older Lance releases may not understand file format versions introduced later, so mixed versions require pinning data_storage_version
Lance at a glance
- Website
- github.com/eto-ai/lance
- Category
- AI & Machine Learning › AI Data & Analytics
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Lance alternatives
Tools and sites you could use instead, ranked by how closely they match.
This project profiles data quality and supports exploratory analysis of Pandas and Spark DataFrames.
Open source
24 alternatives
Cleanlab provides a Python library for data quality and machine learning with messy real world data and labels.
Open source
24 alternatives
Optimus supports agile data preparation workflows across Pandas, Dask, cuDF, Vaex, and PySpark.
Open source
24 alternatives
DVC tracks data versions and machine learning experiments for collaborative development.
Open source
24 alternatives
BambooAI analyzes data with a language model in a persistent Python kernel and supports web and Docker workflows.
Open source
24 alternativesPopular in AI Data & Analytics
Well-known listings from the same topic.
Dotgetdot.aiForvioforvio.comFluidAI Medicalfluidai.mdApache Zeppelinzeppelin.apache.orgSola Securitysola.securityQuadraticquadratichq.com
Lance FAQ
Which file format version should be used for production data?
Write production data with a stable data_storage_version. The next file format alias is unstable and is meant only for experimentation.
Do SDK updates affect file compatibility?
SDK and API compatibility is separate from file format compatibility. SDK and API changes follow semantic versioning. Once a dataset is written with a stable data_storage_version, future releases are stated to continue reading it.
How is Lance installed?
The project lists pip install pylance as the installation command. A preview release can be installed with the --pre option.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.