pydantic-ai-jupyter
Experiment with Pydantic AI Agents interactively in Jupyter notebooks.
Installation
pip install pydantic-ai-jupyter
Or with uv:
uv add pydantic-ai-jupyter
Usage
from pydantic_ai import Agent
from pydantic_ai_jupyter import run_in_jupyter
agent = Agent("openai:gpt-4o-mini")
@agent.tool_plain
def get_weather(city: str) -> str:
return f"Sunny, 22°C in {city}"
# Run with rich display
result = await run_in_jupyter(agent, "What's the weather in Tokyo?")
Features
- Streaming text - See the model's response as it generates
- Streaming tool calls - Watch tool arguments stream in (with providers that support it, like OpenAI)
- Tool results - Styled success and retry results
- Thinking/reasoning - Collapsible display of model thinking
- Error handling - Graceful display of exceptions with tracebacks
Multi-turn conversations
# First turn
result = await run_in_jupyter(agent, "What's the weather in Tokyo?")
# Continue the conversation
result = await run_in_jupyter(
agent,
"What about London?",
message_history=result.all_messages(),
)
Debug mode
Enable debug mode to see all events:
result = await run_in_jupyter(agent, "Hello!", debug=True)
Supported providers
Tool call argument streaming works best with OpenAI, which streams arguments token-by-token. Other providers like Groq and Ollama (via OpenAI-compat) buffer tool calls and send them all at once.
| Provider | Text streaming | Tool call streaming |
|---|---|---|
| OpenAI | ✅ | ✅ |
| Groq | ✅ | ❌ (buffered) |
| Ollama | ✅ | ❌ (buffered) |
Development
See TESTING.md for testing guidelines and PUBLISHING.md for release instructions.
# Install dependencies
uv sync --extra dev
# Run tests
uv run pytest tests/ -v
# Run linting
uv run ruff check .
uv run ruff format .
# Type checking
uv run mypy pydantic_ai_jupyter/
License
BSD 3-Clause
Metadata
Release files for pydantic-ai-jupyter 0.1.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| pydantic_ai_jupyter-0.1.2.tar.gz | 281.3 kB | With provenance | Details for pydantic_ai_jupyter-0.1.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| pydantic_ai_jupyter-0.1.2-py3-none-any.whl | Python 3 | none | any | Details for pydantic_ai_jupyter-0.1.2-py3-none-any.whl |
Total release size: 292.7 kB
Release files / pydantic_ai_jupyter-0.1.2.tar.gz
| Download URL | pydantic_ai_jupyter-0.1.2.tar.gz |
|---|---|
| Size | 281.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d942b123e50357c92b64bf749cc1a4da60949d2d821d5fb40c03f5a0a41c6ac2
|
|
BLAKE2b-256 checksum How to use checksums |
a058ce29cc80fd3b60a8496cd68453c16549b0c009786408f84b7f34e2c5d8d1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 26, 2026.
Transparency logRelease files / pydantic_ai_jupyter-0.1.2-py3-none-any.whl
| Download URL | pydantic_ai_jupyter-0.1.2-py3-none-any.whl |
|---|---|
| Size | 11.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
99fa25612bf75de578b985372fdffe8eccea7303b5ff750df063c67d53d522d3
|
|
BLAKE2b-256 checksum How to use checksums |
66a5773e2e510e714bbef05b24c9458da673cb6fc640f79b713d152088b6bfeb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/6.1.0 CPython/3.13.7
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 26, 2026.
Transparency logSecurity for pydantic-ai-jupyter 0.1.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
Full provenance
Both files in this release have been uploaded with provenance metadata.
Attestation for pydantic_ai_jupyter-0.1.2.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Jan 26, 2026.
Transparency logA note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.