Genkit is an open-source framework for building end-to-end AI and RAG pipelines with a clean, TypeScript-first
developer experience. The genkitx-lancedb plugin lets you use LanceDB as a high-performance vector store
inside your Genkit flows, so you can index, search, and retrieve data efficiently as part of your AI
applications.
Adding LanceDB plugin to your genkit instance.You can run this app with the following command:
Copy
genkit start -- tsx --watch src/index.ts
This’ll add LanceDB as a retriever and indexer to the genkit instance. You can see it in the GUI viewTesting retrieval on a sample table
Let’s see the raw retrieval resultsOn running this query, you’ll 5 results fetched from the lancedb table, where each result looks something like this:
Now that we’ve seen how you can use LanceDB for in a genkit pipeline, let’s refine the flow and create a RAG. A RAG flow will consist of an index and a retreiver with its outputs postprocessed an fed into an LLM for final response
You can also create custom retriever flows, utilizing more options and features provided by LanceDB.Now using our retrieval flow, we can ask question about the ingsted PDF
