Claude Code Plugins

Community-maintained marketplace

Feedback

processor

@SIslamMun/Phagocyte
0
0

Process documents into RAG database. Use when user wants to chunk, embed, or index files into a vector database for semantic search.

Install Skill

1Download skill
2Enable skills in Claude

Open claude.ai/settings/capabilities and find the "Skills" section

3Upload to Claude

Click "Upload skill" and select the downloaded ZIP file

Note: Please verify skill by going through its instructions before using it.

SKILL.md

name processor
description Process documents into RAG database. Use when user wants to chunk, embed, or index files into a vector database for semantic search.

Document Processing

This skill helps you process documents, codebases, and papers into a searchable RAG (Retrieval-Augmented Generation) database using LanceDB.

Quick Start

# 1. Check that services are running
uv run processor check

# 2. Process files into database
uv run processor process ./input -o ./lancedb

# 3. Verify results
uv run processor stats ./lancedb

Common Use Cases

Process a codebase

uv run processor process ./my-project -o ./code_db --content-type code

Process papers/documents

uv run processor process ./papers -o ./papers_db

Incremental updates (skip unchanged files)

uv run processor process ./input -o ./lancedb --incremental

High-quality embeddings (slower, better retrieval)

uv run processor process ./input -o ./lancedb --text-profile high --code-profile high

Embedding Profiles

Type Profile Model Dimensions Use Case
text low Qwen3-Embedding-0.6B 1024 Fast, good quality
text medium Qwen3-Embedding-4B 2560 Balanced
text high Qwen3-Embedding-8B 4096 Maximum quality
code low jina-code-0.5b 896 Fast code search
code high jina-code-1.5b 1536 Best code search

Key Options

Option Values Description
--embedder ollama, transformers Embedding backend
--text-profile low, medium, high Text embedding quality
--code-profile low, high Code embedding quality
--table-mode separate, unified, both Table organization
--incremental/--full - Skip unchanged files
--content-type auto, code, paper, markdown Force content detection

MCP Server

Start the processor MCP server for programmatic access:

uv run processor-mcp

Configure in Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "processor": {
      "command": "uv",
      "args": ["run", "processor-mcp"],
      "cwd": "/path/to/processor"
    }
  }
}

Available MCP Tools

  • process_documents - Process files into LanceDB
  • check_services - Check backend availability
  • setup_models - Download embedding models
  • get_db_stats - Database statistics
  • export_db - Export database

Troubleshooting

"Model not found" error

uv run processor setup  # Download required models

Ollama not running

ollama serve  # Start Ollama server

Check available models

uv run processor check