ClaudeHopper

0 forks

1 stars

Free

What is ClaudeHopper

ClaudeHopper is a specialized Model Context Protocol (MCP) server developed by Arborist-ai. It’s designed to facilitate seamless interaction between advanced AI models, like Claude, and construction documents, drawings, and specifications. Through its use of advanced Retrieval-Augmented Generation (RAG) and hybrid search capabilities, users can easily ask questions about construction documents, locate specific details, and analyze technical specifications. ClaudeHopper is a robust solution for professionals in the construction industry who need to interact with large volumes of complex documents efficiently.

How to Use ClaudeHopper

Using ClaudeHopper is straightforward, even for those who might not be technical experts. To get started, you will need Node.js version 18 or above, the Claude Desktop App, and several AI models provided by Ollama, such as nomic-embed-text, phi4, and clip. For image extraction, Poppler Utils is required.

Quick Start Guide

Download ClaudeHopper and navigate to the installation directory on your desktop.
Run the Setup Script:
```
cd ~/Desktop/claudehopper
chmod +x run_now_preserve.sh
./run_now_preserve.sh
```
This script sets up directories, installs AI models, processes documents, and configures the Claude Desktop App.
Add Your Documents:
- Place drawings in ~/Desktop/PDFdrawings-MCP/InputDocs/Drawings/
- Place specifications in ~/Desktop/PDFdrawings-MCP/InputDocs/TextDocs/
Process Documents: After adding your documents, execute the following command to process them:
```
./process_pdfdrawings.sh
```

Interacting with ClaudeHopper

Once set up, you can ask questions within the Claude Desktop App such as:

"What architectural drawings do we have for the project?"
"Show me the structural details for the foundation system"

Key Features of ClaudeHopper

ClaudeHopper is packed with features that make it an invaluable tool for the construction industry:

Vector-based Search: Optimized for retrieving construction documents like CAD drawings, plans, and specifications using vector search technology.
Visual Search: Allows users to find similar drawings based on textual descriptions, enhancing the ease of locating specific visuals.
Metadata Extraction: Automatically extracts specialized metadata pertinent to construction industry documents, aiding in better organization and retrieval.
Efficient Token Usage: Employs intelligent document chunking and categorization to maximize efficiency in data processing and retrieval.
Secure Local Processing: Ensures security by storing and processing documents locally, without needing to transfer sensitive information over networks.
Support for Multiple Disciplines: Capable of handling a variety of drawing types and construction disciplines, including structural, civil, and architectural.

ClaudeHopper also includes robust image search functionalities, allowing users to test this feature through a simple script that checks dependencies, seeds the database, and runs test queries against image data. Additionally, its technical architecture processes documents through multiple stages, including analysis, metadata extraction, content chunking, and vector embedding, to ensure comprehensive and efficient document handling.

Node.js 18+ License: MIT ClaudeHopper is a specialized Model Context Protocol (MCP) server that enables Claude and other LLMs to interact directly with construction documents, drawings, and specifications through advanced RAG (Retrieval-Augmented Generation) and hybrid search. Ask questions about your construction drawings, locate specific details, and analyze technical specifications with ease.

✨ Features

🔍 Vector-based search for construction document retrieval optimized for CAD drawings, plans, and specs
🖼️ Visual search to find similar drawings based on textual descriptions
🏢 Specialized metadata extraction for construction industry document formats
📊 Efficient token usage through intelligent document chunking and categorization
🔒 Security through local document storage and processing
📈 Support for various drawing types and construction disciplines (Structural, Civil, Architectural, etc.)

🚀 Quick Start

Prerequisites

Node.js 18+
Ollama for local AI models
Required models: nomic-embed-text, phi4, clip
Claude Desktop App
For image extraction: Poppler Utils (pdfimages command)

One-Click Setup

Download ClaudeHopper
Run the setup script:

cd ~/Desktop/claudehopper
chmod +x run_now_preserve.sh
./run_now_preserve.sh

This will:

Create the necessary directory structure
Install required AI models
Process your construction documents
Configure the Claude Desktop App to use ClaudeHopper

Adding Documents

Place your construction documents in these folders:

Drawings: ~/Desktop/PDFdrawings-MCP/InputDocs/Drawings/
Specifications: ~/Desktop/PDFdrawings-MCP/InputDocs/TextDocs/ After adding documents, run:

./process_pdfdrawings.sh

🏗️ Using ClaudeHopper with Claude

Try these example questions in the Claude Desktop App:

"What architectural drawings do we have for the project?"
"Show me the structural details for the foundation system"
"Find drawings that show a concrete foundation with dimensions"
"Search for lift station layout drawings"
"What are the specifications for interior paint?"
"Find all sections discussing fire protection systems"

🛠️ Technical Architecture

ClaudeHopper uses a multi-stage pipeline for processing construction documents:

Document Analysis: PDF documents are analyzed for structure and content type
Metadata Extraction: AI-assisted extraction of project information, drawing types, disciplines
Content Chunking: Intelligent splitting of documents to maintain context
Image Extraction: Identification and extraction of drawing images from PDFs
Vector Embedding: Creation of semantic representations for text and images
Database Storage: Local LanceDB storage for vector search capabilities

👀 Testing the Image Search

To test the image search functionality, you can use the provided test script:

# Make the test script executable
chmod +x test_image_search.sh
# Run the test script
./test_image_search.sh

This will:

Build the application
Check for required dependencies (like pdfimages)
Seed the database with images from your drawings directory
Run a series of test queries against the image search You can also run individual test commands:

# Run the test with the default database location
npm run test:image:verbose
# Run the test with a specific database location
node tools/test_image_search.js /path/to/your/database

📝 Available Search Tools

ClaudeHopper provides several specialized search capabilities:

catalog_search: Find documents by project, discipline, drawing type, etc.
chunks_search: Locate specific content within documents
all_chunks_search: Search across the entire document collection
image_search: Find drawings based on visual similarity to textual descriptions Examples of using the image search feature can be found in the image_search_examples.md file.

📜 License

This project is licensed under the MIT License - see the LICENSE file for details.

How to Use

To use the ClaudeHopper, follow these steps:

Visit https://github.com/Arborist-ai/ClaudeHopperhttps://github.com/Arbori...
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using ClaudeHopper capabilities within your Claude conversations

Additional Information

Created

March 5, 2025

Company

Arborist-ai

Related MCP Servers

Start building your own MCP Server

Interested in creating your own MCP Server? Check out the official documentation and resources.

Learn More