Skip to main content

PromptBook is a powerful and flexible prompt management library designed for AI-driven workflows

Project description

📚 PromptBook

📝 Overview

PromptBook is a powerful and flexible prompt management library designed for AI-driven workflows. It allows users to create, manage, and execute prompts efficiently, including pre-prompts and post-prompts. The library integrates seamlessly with Ollama, enabling contextual AI conversations across multiple prompts.

🚀 Features

  • Create & Manage Prompt Books: Organize prompts in structured prompt books.
  • Pre & Post-Prompt Execution: Automatically process dependent prompts before and after the main prompt.
  • Variable Substitution: Dynamically replace placeholders with user-defined or default values.
  • Ollama Integration: Run prompts in AI models while maintaining context across multiple prompts.
  • Git-Based Prompt Cloning: Clone prompt books from Git repositories for shared collaboration.
  • Customizable Configuration: Modify API settings, debugging options, and more via config.yaml.

📥 Installation

pip install promptbook

🔧 Configuration

After installation, a config.yaml file can be created in the project root to customize settings:

ollama:
  model: "llama3:2b"
  stream: true
  debug: false
  api_url: "http://localhost:11434/api/chat"
  tags_url: "http://localhost:11434/api/tags"

📖 Usage

1️⃣ Running a Prompt

To execute a prompt from a prompt book:

promptbook run test-prompt

2️⃣ Creating a New Prompt Book

To create a new prompt book:

promptbook create-book

The CLI will guide you through setting up the book structure and an initial prompt file.

3️⃣ Cloning a Prompt Book from GitHub

promptbook clone https://github.com/username/promptbook-repo.git

4️⃣ Debugging API Calls

Enable debug mode in config.yaml:

debug: true

5️⃣ Running a Prompt with Ollama

Each item in a prompt list will be executed sequentially while maintaining conversation context.

promptbook run my-prompt

Example output:

💬 Sending: What is the capital of France?
🧠 Ollama Response: The capital of France is Paris.

📂 File Structure

my-promptbook/
├── prompt-book.yaml  # Book metadata
├── prompts/
│   ├── test-prompt.prompt
│   ├── another-prompt.prompt

🛠 Development & Contribution

  1. Clone the repository:
    git clone https://github.com/yourusername/promptbook.git
    cd promptbook
    
  2. Install dependencies:
    pip install -e .
    
  3. Run tests:
    pytest tests/
    

📜 License

This project is licensed under the MIT License.

✨ Credits

Developed by Sharfuddin Shawon.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

promptbook-0.5.0.tar.gz (8.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

promptbook-0.5.0-py3-none-any.whl (10.0 kB view details)

Uploaded Python 3

File details

Details for the file promptbook-0.5.0.tar.gz.

File metadata

  • Download URL: promptbook-0.5.0.tar.gz
  • Upload date:
  • Size: 8.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.1

File hashes

Hashes for promptbook-0.5.0.tar.gz
Algorithm Hash digest
SHA256 a8b02ec7edaebdccd3365bd9a6ca585ca4d767d3ea46e304f5b2001fc3bc3ea8
MD5 0d4ae9b1f54783cfd0ad06c910fd4163
BLAKE2b-256 f80b1b2f46deec6a7f5eaa159e663ae1daf264ef43a777f6a7ae7295aa7ab766

See more details on using hashes here.

File details

Details for the file promptbook-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: promptbook-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 10.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.13.1

File hashes

Hashes for promptbook-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 60975c581e22622dea4ceaeec75448ab3644f4f673d3b07a97457f23102aa248
MD5 2e9dc7184e2d78897518a88bbcaa1d47
BLAKE2b-256 d4c5837cb41a5b10efcf58a3bd28c971822cf48297676c151025cad345e026c4

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page