Skip to main content

langfuse_pydantic_ai

This is a third-party package, not officially maintained by Langfuse. If Langfuse requires for this package, feel free to contact me.

A simple wrapper, send trace to langfuse when using pydantic-ai

Install

pip install langfuse-pydantic-ai

Usage

TL;DR

from langfuse_pydantic_ai import observed_agent

agent = observed_agent(agent)

Full example:

import asyncio

from pydantic_ai.agent import Agent
from langfuse.decorators import observe
from langfuse_pydantic_ai import observed_agent

@observe # Add this decorator to span a trace
async def main():
    agent = Agent(
        "google-gla:gemini-1.5-flash",
        # Register a static system prompt using a keyword argument to the agent.
        # For more complex dynamically-generated system prompts, see the example below.
        system_prompt="Be concise, reply with one sentence.",
    )
    agent = observed_agent(agent)
    result = await agent.run('Where does "hello world" come from?')
    print(result.output)


if __name__ == "__main__":
    asyncio.run(main())

If using custom model, use observed_model instead

from pydantic_ai.agent import Agent
from langfuse_pydantic_ai import observed_model

model = observed_model(model)
agent = Agent(model=model)

If using agent factory function, use @use_observed_agent directly

from pydantic_ai.agent import Agent
from langfuse_pydantic_ai import use_observed_agent

@use_observed_agent
def init_agent() -> Agent:
    return Agent(
        "google-gla:gemini-1.5-flash",
        # Register a static system prompt using a keyword argument to the agent.
        # For more complex dynamically-generated system prompts, see the example below.
        system_prompt="Be concise, reply with one sentence.",
    )

Configuration via environment variables:

LANGFUSE_HOST=<langfuse_host>
LANGFUSE_PUBLIC_KEY=<langfuse_public_key>
LANGFUSE_SECRET_KEY=<langfuse_secret_key>

Develop

Install pre-commit before commit

pip install pre-commit
pre-commit install

Install package locally

pip install -e .[test]

Run unit-test before PR

pytest -v

Metadata

Release files for langfuse-pydantic-ai 0.2.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for langfuse-pydantic-ai 0.2.1
File Size Uploaded Provenance
langfuse_pydantic_ai-0.2.1.tar.gz 14.6 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for langfuse-pydantic-ai 0.2.1
File Interpreter ABI Platform
langfuse_pydantic_ai-0.2.1-py3-none-any.whl Python 3 none any Details

Total release size: 19.0 kB

Release files / langfuse_pydantic_ai-0.2.1.tar.gz

Download URL langfuse_pydantic_ai-0.2.1.tar.gz
Size 14.6 kB
Tags Source
SHA-256 checksum
How to use checksums
ba7374a42f5864a0d3f893793af8842836db16d7db3fbe5f412aac284f9c27fe
BLAKE2b-256 checksum
How to use checksums
1f9e8d530251d719dc69715001a9bda966b5476909fc5abaa05c76e8c3c94f85
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.9

Release files / langfuse_pydantic_ai-0.2.1-py3-none-any.whl

Download URL langfuse_pydantic_ai-0.2.1-py3-none-any.whl
Size 4.4 kB
Tags Python 3
SHA-256 checksum
How to use checksums
80d7a3ccc8f99405a4f979332700d4163b124540c0f557b55f7dc65ee466cc09
BLAKE2b-256 checksum
How to use checksums
91850082faeb5292e6dadb52b530989b87bd28831abc6eca0b42991dcfd30236
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.12.9

Security for langfuse-pydantic-ai 0.2.1

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.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A 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.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page