Ingest and search text and images in LanceDB using the lancer CLI.
npx skills add https://github.com/lanej/dotfiles --skill lancer
Please help me install this Agent Skill. Skill: lancer Source: https://github.com/lanej/dotfiles/tree/main/claude/skills/lancer Command: npx skills add https://github.com/lanej/dotfiles --skill lancer
This Skill overcomes the limitations of keyword-based search, which often fails to capture the true meaning of queries, and the challenge of effectively searching multi-modal content (text and images). It provides a powerful semantic search solution for your knowledge base.
Ingest all markdown documents from the './documentation/' directory into a table named 'docs', then search that table for "installation guide".
High-intent search queries and answers about installing and using this skill.
Semantic search finds documents by meaning and context rather than exact keyword matches. This Skill uses LanceDB with embedding models to understand query intent across text and images, returning contextually relevant results even when phrasing differs from your documents.
Yes, this Skill supports multi-modal search across text and images. Ingest diverse formats—markdown, PDF, JPG, PNG, GIF, and others—into a single LanceDB table, then search all content types simultaneously using natural language queries.
Use the lancer CLI to ingest documents from a directory, specifying chunk size, overlap, and embedding models. The Skill automatically processes text and image formats, generates embeddings, and indexes them in LanceDB for immediate semantic search.
Supported formats include text files, markdown, PDF, SQL, and images: JPG, PNG, GIF, BMP, WebP, TIFF, SVG, and ICO. The Skill handles chunking and embedding for all formats automatically during ingestion.
Yes, this Skill includes MCP server integration, allowing you to run semantic search directly within Claude Desktop and other MCP clients for seamless document and image retrieval workflows.
The Skill's search functionality accepts metadata filters through CLI options, enabling you to narrow results by document properties while maintaining semantic relevance across filtered subsets.
mikkelkrogsholmIngest PDFs, Markdown, HTML, and plain text into Bookstrap knowledge bases with semantic chunking and embeddings.
ollieb89Automate Retrieval-Augmented Generation pipelines for LLM applications.
vecearBuild document embedding and retrieval pipelines for scalable semantic search.
DbillionaerEngineer vector database solutions for semantic search and RAG applications.
