hayhooks

Easily deploy Haystack pipelines as REST APIs and MCP Tools.

GitHub Stars

109

User Rating

Not Rated

Favorites

0

Views

39

Forks

28

Issues

15

Installation
Difficulty
Intermediate
Estimated Time
10-20 minutes
Requirements
Python 3.7以上
Haystack 最新版

Installation

Installation

Prerequisites

Please specify required software and versions:
Python: 3.7 or higher
Haystack: Latest version

Installation Steps

1. Clone Repository

bash
git clone https://github.com/deepset-ai/hayhooks.git
cd hayhooks

2. Install Dependencies

bash
pip install -r requirements.txt

3. Start Server

bash
python -m hayhooks

Troubleshooting

Common Issues

Issue: Server won't start Solution: Check Python version and reinstall dependencies. Issue: Haystack is not installed correctly Solution: Recheck Haystack installation instructions.

Configuration

Configuration

Basic Configuration

Environment Variables

Set the following environment variables as needed:
bash
export API_KEY="your-api-key"
export DEBUG="true"

Configuration Example

Basic Configuration

json
{
  "mcpServers": {
    "hayhooks": {
      "command": "python",
      "args": ["-m", "hayhooks"],
      "env": {
        "API_KEY": "your-api-key"
      }
    }
  }
}

Examples

Examples

Basic Usage

Programmatic Usage

python
import requests

def call_mcp_tool(tool_name, params):
    response = requests.post(
        'http://localhost:3000/mcp/call',
        json={
            'tool': tool_name,
            'parameters': params
        }
    )
    return response.json()

Usage example

result = call_mcp_tool('analyze', { 'input': 'sample data', 'options': {'format': 'json'} })

Use Cases

Deployment and utilization of Haystack pipelines in AI development environments
API operations via chat using Claude Desktop
Exposing Haystack pipelines through Cursor
Calling MCP tools from automation scripts