Pdfsearch Zed

🚀 PDF Search for Zed

A document search extension designed for Zed, enabling semantic search on PDF documents and using the results in Zed's AI assistant.

🚀 Quick Start

Prerequisites

The current version requires the following:

1. An OpenAI API key (for generating embeddings).
2. uv installed on the system.

Note: Although the current implementation requires an OpenAI API key to generate embeddings, we plan to implement self - contained alternatives in future versions. Community feedback will help us prioritize improvements.

Steps

1. Clone the repository:

git clone https://github.com/freespirit/pdfsearch-zed.git

2. Set up the Python environment for the MCP server:

cd pdfsearch-zed/pdf_rag
uv venv
uv sync

3. Install the development extension to Zed.
4. Build the search database:

cd /path/to/pdfsearch-zed/pdf_rag

echo "OPENAI_API_KEY=sk-..." > src/pdf_rag/.env

# Depending on the document size, this may take a few minutes.
# You can provide multiple files and directories as arguments.
# - Files will be chunked.
# - Files in directories are considered chunked.
uv run src/pdf_rag/rag.py build "file1.pdf" "dir1" "file2.md" ...

5. Configure Zed:

"context_servers": {
    "pdfsearch-context-server": {
        "settings": {
            "extension_path": "/path/to/pdfsearch-zed"
        }
    }
}

💻 Usage Examples

Basic Usage

1. Open Zed's AI assistant panel.
2. Enter /pdfsearch followed by your search query.
3. The extension will search the PDFs and add relevant parts to the AI assistant's context.

📚 Documentation

Future Improvements

• [x] Self - contained vector storage
• [ ] Self - contained embeddings
• [ ] Automatic index building on first run
• [ ] Configurable result size
• [x] Support for multiple PDF files
• [x] Optional: Support for file formats other than PDFs

Project Structure

• pdf_rag/: Python - based MCP server implementation
• src/: Zed extension code
• extension.toml and Cargo.toml: Zed extension configuration files

Known Limitations

• Manual index building is required before first use.
• External services (OpenAI) are needed.

⚠️ Important Note

Although the current implementation requires an OpenAI API key to generate embeddings, we plan to implement self - contained alternatives in future versions. Community feedback will help us prioritize improvements.