外观
本页尚未翻译
本页内容仍为英文原文，源自官方文档 integrations/ai/kiln。中文翻译正在分批进行中。
Kiln AI
Kiln 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
Watch the quick start overview on Vimeo.
Kiln's app makes it easy to:
- Build a RAG pipeline with a simple drag-and-drop interface
- Compare search index options (powered by LanceDB), document extractors, embedding models, and chunking strategies
- Create end-to-end evaluations to determine which search configuration works best for your use case
- Load your data from Kiln into LanceDB 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
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
To get started, download the Kiln App, create a project, and navigate to "Docs & Search".
See the Kiln documentation for creating a RAG system for details on each step of the process.