Skip to main content

Agentic AI coding partner for IPython and Jupyter

Project description

🧠 JupyterPilot AI

JupyterPilot AI (jupyterpilot-ai) is a lightweight, provider-agnostic AI coding partner for IPython and Jupyter. It brings natural language code generation (%do) and automated error healing (%fix) to your notebook.


🚀 Features

  • %do : Transform instructions into Python code instantly.
  • %fix: Post-mortem self-healing for your last error.
  • %review: Analyze the previous cell and get optimization suggestions or code reviews.
  • Context Awareness: Remembers your last 3 cells for accurate variable usage.
  • Data Observer (New): Automatically detects Pandas DataFrames, SQL engines, and MongoDB databases to provide schema context to the AI.
  • Hybrid Support: Switch between local Ollama and cloud GPT-4o/Claude via LiteLLM.

📥 Installation

pip install jupyterpilot-ai

Enable Data Observer (Optional)

To enable automatic schema detection for Pandas, SQL, and MongoDB, install the data extras:

pip install "jupyterpilot-ai[data]"

Enable the Extension

Add this to any cell in your notebook or your IPython startup script:

%load_ext jupyterpilot_ai

⚙️ Configuration

JupyterPilot AI looks for a configuration file at ~/.jupyterpilot/config.json.

Switching Modes

To switch between local and paid models, simply change the "mode" value in your config file:

{
    "mode": "cloud", 
    "local": {
        "url": "http://localhost:11434/api/generate",
        "model": "qwen2.5-coder:7b"
    },
    "cloud": {
        "provider": "openai",
        "model": "gpt-4o",
        "api_key": "sk-..."
    },
    "custom_jar_ai": {
        "url": "",
        "model": "",
        "api_key": ""
    }
}
  • Local Mode ("mode": "local"):

    • Uses Ollama by default.
    • Requires Ollama to be running (ollama run qwen2.5-coder:7b).
    • You can customize the url and model in the local block.
  • Cloud Mode ("mode": "cloud"):

    • Uses LiteLLM to connect to paid providers.
    • Supports OpenAI, Anthropic (Claude), Google (Gemini), etc.
    • Specify your provider, model, and api_key.
  • Custom Jar AI Mode ("mode": "custom_jar_ai"):

    • Connect to your custom AI API endpoint directly.
    • Set your custom url, model, and api_key.

🛠️ Usage

  • %do plot a sine wave
  • %fix (after an error)
  • %review (to review the last run cell)

📬 Contact

Wajoud Noorani - Wajoudnoorani59@gmail.com


📄 License

MIT

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

jupyterpilot_ai-0.3.0.tar.gz (8.1 kB view details)

Uploaded Source

Built Distribution

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

jupyterpilot_ai-0.3.0-py3-none-any.whl (7.8 kB view details)

Uploaded Python 3

File details

Details for the file jupyterpilot_ai-0.3.0.tar.gz.

File metadata

  • Download URL: jupyterpilot_ai-0.3.0.tar.gz
  • Upload date:
  • Size: 8.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.13.5

File hashes

Hashes for jupyterpilot_ai-0.3.0.tar.gz
Algorithm Hash digest
SHA256 f3fd8347d1e0029f8ce406254ed5886d52dbd66e5f0d4e8080bf5a817543bc0f
MD5 2b3e5cd533dd78f7700ac428ebce75b5
BLAKE2b-256 c21c31e532d025faa69471b15838b3b49ce0033e54b4d2fa423ec1bbef7422ea

See more details on using hashes here.

File details

Details for the file jupyterpilot_ai-0.3.0-py3-none-any.whl.

File metadata

File hashes

Hashes for jupyterpilot_ai-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 c7d1208367a5b565852d1e9e39ab631f7b52305d7a4bb36cf390d2f9bdf7c8a7
MD5 d954b2de31312333c21281dd1ae3d056
BLAKE2b-256 3daa18351ba27ffd77f92daf2bc8862b0e36fcb1a11ab7d5fee29a9671cb7ed1

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