How do I install the Memvid RAG skill?

Run npx skillmds@latest add fa-ina-tic/memvid-rag in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Memvid RAG safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Memvid RAG?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Memvid RAG free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Memvid RAG?

fa-ina-tic (@fa-ina-tic) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Memvid RAG by fa-ina-tic — Agent Skill

Name: Memvid RAG
Author: fa-ina-tic

File contents

memvid-rag

A simple local RAG (Retrieval-Augmented Generation) system based on memvid.

Overview

This plugin provides semantic search capabilities for PDF documents using vector embeddings. It enables you to index documents into a local knowledge base and perform semantic queries to retrieve relevant information.

Requirements

Python: memvid-sdk installed (pip install memvid-sdk)
OpenAI API Key: Required for vector embeddings. Set OPENAI_API_KEY environment variable before indexing.
Document parsing libraries: Additional Python libraries are needed depending on the file format:
- PDF: pypdf (uv add pypdf)
- DOCX: python-docx (uv add python-docx)
- XLSX: openpyxl (uv add openpyxl)

Commands

Command	Description
`/memvid-rag:create`	Create a new `knowledge.mv2` index file
`/memvid-rag:index <path>`	Index PDF files into the knowledge base
`/memvid-rag:search <query>`	Search indexed documents semantically
`/memvid-rag:status`	Show current status of the RAG system

Workflow

Create Index: Run /memvid-rag:create to initialize the knowledge base (if not exists)
Index Documents: Use /memvid-rag:index <pdf_path> to add documents
Search: Query with /memvid-rag:search <your question>

Search Options

The search command supports optional parameters:

--k=<number>: Maximum results to return (default: 5)
--mode=<lex|sem|auto>: Search mode (default: auto)
--snippet_chars=<number>: Max characters per snippet (default: 240)
--min_relevancy=<float>: Minimum relevancy threshold
--adaptive=<true|false>: Enable adaptive result count
--file=<path>: Use a custom index file (default: knowledge.mv2; also supported by index)
--query_embedding_model=<model_id>: Must match the model used at index time (default: openai-small)

Example Usage

/memvid-rag:index ./documents/research-paper.pdf
/memvid-rag:search What are the key findings about semantic search?
/memvid-rag:search How does RAG improve LLM accuracy? --k=10 --mode=sem

Data Storage

All indexed data is stored locally in knowledge.mv2 file in the current working directory.

---name: memvid-ragdescription: Local RAG over PDF documents using memvid. Use when the user wants to index documents into a local knowledge base, semantically search previously indexed documents, or check the status of the knowledge base.---# memvid-ragA simple local RAG (Retrieval-Augmented Generation) system based on [memvid](https://github.com/Olow304/memvid-sdk).## OverviewThis plugin provides semantic search capabilities for PDF documents using vector embeddings. It enables you to index documents into a local knowledge base and perform semantic queries to retrieve relevant information.## Requirements- **Python**: memvid-sdk installed (`pip install memvid-sdk`)- **OpenAI API Key**: Required for vector embeddings. Set `OPENAI_API_KEY` environment variable before indexing.- **Document parsing libraries**: Additional Python libraries are needed depending on the file format: - PDF: `pypdf` (`uv add pypdf`) - DOCX: `python-docx` (`uv add python-docx`) - XLSX: `openpyxl` (`uv add openpyxl`)## Commands| Command | Description ||---------|-------------|| `/memvid-rag:create` | Create a new `knowledge.mv2` index file || `/memvid-rag:index <path>` | Index PDF files into the knowledge base || `/memvid-rag:search <query>` | Search indexed documents semantically || `/memvid-rag:status` | Show current status of the RAG system |## Workflow1. **Create Index**: Run `/memvid-rag:create` to initialize the knowledge base (if not exists)2. **Index Documents**: Use `/memvid-rag:index <pdf_path>` to add documents3. **Search**: Query with `/memvid-rag:search <your question>`## Search OptionsThe search command supports optional parameters:- `--k=<number>`: Maximum results to return (default: 5)- `--mode=<lex|sem|auto>`: Search mode (default: auto)- `--snippet_chars=<number>`: Max characters per snippet (default: 240)- `--min_relevancy=<float>`: Minimum relevancy threshold- `--adaptive=<true|false>`: Enable adaptive result count- `--file=<path>`: Use a custom index file (default: `knowledge.mv2`; also supported by index)- `--query_embedding_model=<model_id>`: Must match the model used at index time (default: `openai-small`)## Example Usage```/memvid-rag:index ./documents/research-paper.pdf/memvid-rag:search What are the key findings about semantic search?/memvid-rag:search How does RAG improve LLM accuracy? --k=10 --mode=sem```## Data StorageAll indexed data is stored locally in `knowledge.mv2` file in the current working directory.

Frequently asked questions

Memvid RAG