mirror of
https://github.com/lancedb/lancedb.git
synced 2026-08-18 03:58:26 +00:00
Dan Tasse
00c4a7b843
Consolidating skills so we have only one `lancedb` skill, making it
easier to install and work with, vs. installing and using different
skills for "lancedb-column-metadata", "lancedb-branch-ops", etc.
Also deleted lancedb-connect, because the new monoskill uses the
python/TS APIs so it doesn't need extra handholding to connect to the
REST API.
## does it work?
Test 1: do some column metadata operations with 1. no skills, 2. our
previous baseline lancedb skill, 3. the baseline lancedb skill with the
lancedb-column-metadata skill folded in:
```
┌───────────────────────────┬──────────────────────┬────────────────────┬───────────────────────┐
│ eval │ no-skill │ lancedb (original) │ lancedb2-incl-columns │
├───────────────────────────┼──────────────────────┼────────────────────┼───────────────────────┤
│ 2-add-all-metadata-types │ 2.5/5 · 116s · $0.44 │ 0/5 · 154s · $0.60 │ 5/5 · 58s · $0.26 │
├───────────────────────────┼──────────────────────┼────────────────────┼───────────────────────┤
│ 3-delete-one-metadata-key │ 4/4 · 67s · $0.23 │ 4/4 · 100s · $0.45 │ 4/4 · 45s · $0.20 │
├───────────────────────────┼──────────────────────┼────────────────────┼───────────────────────┤
│ TOTAL (per rep avg) │ 6.5/9 · 183s · $0.66 │ 4/9 · 254s · $1.05 │ 9/9 · 103s · $0.46 │
└───────────────────────────┴──────────────────────┴────────────────────┴───────────────────────┘
```
without column-metadata-specific content, it failed because it wrote
keys like `description` instead of `lancedb:description`. That's pretty
undiscoverable without the skill.
Test 2: do some simple branch operations with 1. no skills, 2. our
previous baseline lancedb skill, 3. the combined skill (in this PR):
```
┌───────────────────────────┬────────────────────┬────────────────────┬────────────────────────────────┐
│ eval │ no-skill │ lancedb (original) │ lancedb3-incl-columns-branches │
├───────────────────────────┼────────────────────┼────────────────────┼────────────────────────────────┤
│ 5-create-branch │ 2/2 · 64s · $0.30 │ 2/2 · 57s · $0.34 │ 2/2 · 38s · $0.22 │
├───────────────────────────┼────────────────────┼────────────────────┼────────────────────────────────┤
│ 6-delete-branch │ 2/2 · 38s · $0.21 │ 2/2 · 44s · $0.27 │ 2/2 · 40s · $0.22 │
├───────────────────────────┼────────────────────┼────────────────────┼────────────────────────────────┤
│ 7-switch-branch-and-write │ 1/2 · 96s · $0.49 │ 1/2 · 106s · $0.58 │ 2/2 · 66s · $0.40 │
├───────────────────────────┼────────────────────┼────────────────────┼────────────────────────────────┤
│ TOTAL (per rep avg) │ 5/6 · 199s · $1.00 │ 5/6 · 207s · $1.20 │ 6/6 · 143s · $0.83 │
└───────────────────────────┴────────────────────┴────────────────────┴────────────────────────────────┘
```
Test 3: run everything, with the lancedb (original) skill,
lancedb(original) + all the separate skills, and
lancedb3-incl-columns-branches
```
┌────────────────────────────────┬──────────────────────┬────────────────────────────────┬─────────────────────────────────────────────────────────────────┐
│ eval │ lancedb (original) │ lancedb3-incl-columns-branches │ all-separate (lancedb + connect + column-metadata + branch-ops) │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ 1-pick-column-for-image-search │ 2/2 · 141s · $0.67 │ 2/2 · 128s · $0.43 │ 1/2 · 257s · $0.81 │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ 2-add-all-metadata-types │ 5/5 · 93s · $0.52 │ 5/5 · 54s · $0.30 │ 5/5 · 40s · $0.24 │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ 3-delete-one-metadata-key │ 4/4 · 84s · $0.44 │ 4/4 · 36s · $0.24 │ 4/4 · 28s · $0.20 │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ 4-build-index │ 3/3 · 275s · $0.52 │ 3/3 · 84s · $0.39 │ 3/3 · 68s · $0.50 │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ 5-create-branch │ 2/2 · 39s · $0.31 │ 2/2 · 41s · $0.20 │ 2/2 · 15s · $0.17 │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ 6-delete-branch │ 2/2 · 59s · $0.25 │ 2/2 · 69s · $0.29 │ 2/2 · 26s · $0.17 │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ 7-switch-branch-and-write │ 1/2 · 84s · $0.46 │ 2/2 · 62s · $0.40 │ 2/2 · 27s · $0.23 │
├────────────────────────────────┼──────────────────────┼────────────────────────────────┼─────────────────────────────────────────────────────────────────┤
│ TOTAL │ 19/20 · 774s · $3.17 │ 20/20 · 474s · $2.24 │ 19/20 · 462s · $2.32 │
└────────────────────────────────┴──────────────────────┴────────────────────────────────┴─────────────────────────────────────────────────────────────────┘
```
("lancedb3-incl-columns-branches" is the combined skill in this PR,
all-separate is using the four separate skills.)
For overall performance, it helps to have the specialized skills for
metadata and branching; doesn't really matter whether they're separate
skills or all together. Also doesn't matter much whether it's REST or
Python. So let's merge these skills to make it easier for users.
The Multimodal AI Lakehouse
How to Install ✦ Detailed Documentation ✦ Tutorials and Recipes ✦ Contributors
The ultimate multimodal data platform for AI/ML applications.
LanceDB is designed for fast, scalable, and production-ready vector search. It is built on top of the Lance columnar format. You can store, index, and search over petabytes of multimodal data and vectors with ease. LanceDB is a central location where developers can build, train and analyze their AI workloads.
Demo: Multimodal Search by Keyword, Vector or with SQL
Star LanceDB to get updates!
⭐ Click here ⭐ to see how fast we're growing!
Key Features:
- Fast Vector Search: Search billions of vectors in milliseconds with state-of-the-art indexing.
- Comprehensive Search: Support for vector similarity search, full-text search and SQL.
- Multimodal Support: Store, query and filter vectors, metadata and multimodal data (text, images, videos, point clouds, and more).
- Advanced Features: Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure. GPU support in building vector index.
Products:
- Open Source & Local: 100% open source, runs locally or in your cloud. No vendor lock-in.
- Cloud and Enterprise: Production-scale vector search with no servers to manage. Complete data sovereignty and security.
Ecosystem:
- Columnar Storage: Built on the Lance columnar format for efficient storage and analytics.
- Seamless Integration: Python, Node.js, Rust, and REST APIs for easy integration. Native Python and Javascript/Typescript support.
- Rich Ecosystem: Integrations with LangChain 🦜️🔗, LlamaIndex 🦙, Apache-Arrow, Pandas, Polars, DuckDB and more on the way.
How to Install:
Follow the Quickstart doc to set up LanceDB locally.
API & SDK: We also support Python, Typescript and Rust SDKs
| Interface | Documentation |
|---|---|
| Python SDK | https://lancedb.github.io/lancedb/python/python/ |
| Typescript SDK | https://lancedb.github.io/lancedb/js/globals/ |
| Rust SDK | https://docs.rs/lancedb/latest/lancedb/index.html |
| REST API | https://docs.lancedb.com/api-reference/rest |
Join Us and Contribute
We welcome contributions from everyone! Whether you're a developer, researcher, or just someone who wants to help out.
If you have any suggestions or feature requests, please feel free to open an issue on GitHub or discuss it on our Discord server.
Check out the GitHub Issues if you would like to work on the features that are planned for the future. If you have any suggestions or feature requests, please feel free to open an issue on GitHub.
Contributors
Stay in Touch With Us