mirror of
https://github.com/lancedb/lancedb.git
synced 2026-10-15 08:12:26 +00:00
Jack YeandBrendan Clement
47b7babc08
Move the public website pages into `docs/web` beside the SDK, with
shared navigation and executable example sources in `docs/web-tests`.
The combined website is assembled by
[lancedb/docs#355](https://github.com/lancedb/docs/pull/355), with six
Enterprise replacements from
[lancedb/sophon#7681](https://github.com/lancedb/sophon/pull/7681).
This includes Function guidance, runnable Quickstarts, regenerated
snippets, production contact/demo fixes, the legacy SQL route, and the
LeRobot redirect. LeRobot remains attributed to Geneva; all 34 Geneva
pages remain in the docs repository until Function officially launches.
Materialized-view guidance follows the full rebuild refresh introduced
by #4373: local refresh writes the complete result, has no `full`
argument, supports `source_version`, and no longer requires stable row
IDs. Deployment SQL refresh options and stable-ID setup are qualified by
version/configuration. Function input guidance distinguishes ordinary
stored columns from computed inputs supported by newer deployments.
**Validation:** independently accepted local checks include 95 Python
tests (real Enterprise excluded), eight TypeScript tests, Rust
Quickstart, snippet parity, typos, deterministic assembly, Mint
validation and links/anchors/redirects. The combined baseline retains
all 181 production routes and 17 legacy redirects. Examples ran locally
against source-built Python SDK 0.40.0b13; existing GitHub workflows do
not run `docs/web-tests`. New main at `069b2f7d` is 0.41.0b0 and adds
computed Function inputs; that SDK was not exercised by the accepted
tests. Latest prose corrections receive focused site validation.
**Merge/rollout:** merge this and #7681 before #355's combined CI, which
reads producer `main`. This is migration infrastructure: section
overlays, source-owned skills and automatic versioned paired releases
remain follow-ups. The current manual publisher is transitional. Hosted
validation, a supported SDK/Enterprise release pair and a real
Enterprise walkthrough remain pending.
Production Mintlify watches `lancedb/docs:deploy-freeze`, directory
`docs`; preserve that source through review. The separate SDK GitHub
Pages reference workflow rebuilds on main merges.
**Updated-head CI (9a50f8db):**
[Typos](https://github.com/lancedb/lancedb/actions/runs/37654185443/job/112904990558),
[PR
title](https://github.com/lancedb/lancedb/actions/runs/37654179507/job/112904974595)
and
[Aikido](https://app.aikido.dev/featurebranch/scan/215386145?groupId=74229)
pass. Critical findings in the example lockfiles were patched: all Sharp
copies use 0.35.5, protobufjs 7.6.6, tar 7.5.22, quinn-proto 0.11.19,
zerovec 0.11.8 and zerovec-derive 0.11.6. The SDK's product dependencies
are unchanged. The revised lockfiles pass eight TypeScript examples,
HuggingFace decode/resize/crop/rescale/normalize plus AVIF roundtrip,
and Rust Quickstart. Aikido passing does not mean every advisory is
cleared; npm still reports 29 high and five moderate advisories in the
example dependency graph. No scanner bypass or suppression was added.
The Function prose correction passes combined/standalone Mint,
deterministic assembly, routes and assets. The revised 325-file site
checksum is
`175bec06864abb400dd292e667ba93448c0479b8359fd7bf6146afabf9040647`. This
PR remains open for independent review; further merges are on hold.
---------
Co-authored-by: Brendan Clement <brendan.clement@lancedb.com>
49 lines
3.1 KiB
Plaintext
49 lines
3.1 KiB
Plaintext
---
|
|
title: "Kiln AI"
|
|
sidebarTitle: "Kiln"
|
|
|
|
---
|
|
|
|
[**Kiln**](https://kiln.tech) is a free tool for building production-ready AI systems, combining an intuitive desktop application and an open-source Python library. It supports RAG pipelines, evaluations, agents, MCP tool-calling, synthetic data generation, and fine-tuning. Kiln provides deep integration with LanceDB for vector search, full-text search (BM25), and hybrid search.
|
|
|
|
## Quick Start: Build a RAG Pipeline in 5 Minutes with Kiln and LanceDB {#quick-start-build-a-rag-pipeline-in-5-minutes-with-kiln-and-lancedb}
|
|
|
|
Watch the [quick start overview on Vimeo](https://vimeo.com/1119945690).
|
|
|
|
Kiln's [app](https://kiln.tech/download) makes it easy to:
|
|
|
|
- Build a RAG pipeline with a simple drag-and-drop interface
|
|
- [Compare](#find-the-best-rag-pipeline-for-your-use-case) search index options (powered by LanceDB), document extractors, embedding models, and chunking strategies
|
|
- Create end-to-end [evaluations](https://docs.kiln.tech/docs/evaluations) to determine which search configuration works best for your use case
|
|
- Load your data from Kiln into [LanceDB Enterprise](/enterprise) for production use
|
|
- Iterate with confidence by evaluating new content, prompts, models, and embeddings in minutes instead of weeks
|
|
|
|
## Find the Best RAG Pipeline for Your Use Case {#find-the-best-rag-pipeline-for-your-use-case}
|
|
|
|
There is no universal best RAG solution—only the best solution for your specific use case. Kiln makes it easy to compare state-of-the-art configurations and find which works best for you.
|
|
|
|
Start with pre-configured templates for state-of-the-art RAG at various performance/quality/cost levels, or experiment with any combination of options:
|
|
|
|
|Area|Technologies|Description|
|
|
|:----|:----|:----|
|
|
|Search Index|LanceDB|Compare LanceDB's vector search, full-text search (BM25), and hybrid search to find the best approach for your use case.|
|
|
|Content|Kiln Document Library|Collaborate on a document library with your team to find the best content for your RAG. Track every revision and tag document sets.|
|
|
|Document Extraction|Gemini, OpenAI GPT, Qwen VL, and more|Find the most accurate document extraction models for converting PDFs, images, audio, video, and other formats into textual data for RAG.|
|
|
|Embeddings|Embedding models from Gemini, OpenAI, Nomic, Qwen, and more|Find the embedding model best suited to your use case.|
|
|
|Chunking|LlamaIndex|Find the ideal chunk size and method.|
|
|
|
|
## Get Started {#get-started}
|
|
|
|
To get started, download the [Kiln App](https://kiln.tech/download), create a project, and navigate to "Docs & Search".
|
|
|
|
See the [Kiln documentation for creating a RAG system](https://docs.kiln.tech/docs/documents-and-search-rag) for details on each step of the process.
|
|
|
|
## More Information {#more-information}
|
|
|
|
- [Kiln Homepage](https://kiln.tech)
|
|
- [Download the Kiln App](https://kiln.tech/download)
|
|
- [Kiln GitHub Repository](https://github.com/Kiln-AI/Kiln)
|
|
- [Building RAG Systems - Kiln Documentation](https://docs.kiln.tech/docs/documents-and-search-rag)
|
|
- [Python Library](https://pypi.org/project/kiln-ai/) or `pip install kiln_ai`
|
|
|