Ingest documents into a local ChromaDB vector store and query semantically.
npx skills add https://github.com/Arry8/openclaw-edge --skill rag-store
Please help me install this Agent Skill. Skill: rag-store Source: https://github.com/Arry8/openclaw-edge/tree/main/skills/rag-store Command: npx skills add https://github.com/Arry8/openclaw-edge --skill rag-store
Local RAG store to ingest books, PDFs, and text files and answer questions using semantic search.
Ingest a document into the local RagStore using ragstore.py add and then query with ragstore.py query
High-intent search queries and answers about installing and using this skill.
You can build a local RAG vector store by ingesting PDFs, books, and text files using a Python script that relies on ChromaDB. It stores data locally under ~/.openclaw/ragstore/ and enables fast cross-document retrieval.
Semantic question answering works by querying a local vector store that uses built-in embeddings to match your question against relevant document chunks. It retrieves context across all ingested sources to provide answers.
Yes, ChromaDB is a required dependency for this local document ingestion system. It provides the vector store and built-in embeddings needed to support add, query, list, and remove operations for your collections.
Yes, you can manage multiple document collections locally using a Python CLI. The system supports collection management, allowing you to add, query, list, remove, and delete sources as needed for your knowledge base.
The best way to query across ingested PDF and text documents is using the semantic query function. It searches the local ChromaDB vector store to retrieve relevant chunks and their sources quickly.
A local RAG store with built-in embeddings is limited to the local storage capacity and the built-in embedding model's performance. It is designed for personal knowledge bases from books, PDFs, and text files rather than large-scale enterprise deployments.
HosungYouDownload PDFs, extract text, chunk documents, and create a local ChromaDB vector database.
open-gitagentExecute semantic searches over ingested document collections to retrieve relevant text chunks.
patricio0312revAutomate document embedding pipelines for semantic search.
jonnabioManage vector databases with hybrid search for AI applications.
