Skip to main content

Pydantic AI integration for PathCourse Health — typed agents with autonomous USDC billing on Base L2

Project description

pydantic-ai-pathcourse

Pydantic AI integration for PathCourse Health. Build typed, production-grade agents with autonomous USDC billing on Base L2 — no accounts, no credit cards, no KYC.

Install

pip install pydantic-ai-pathcourse

Quick Start

from pydantic_ai import Agent
from pydantic_ai_pathcourse import PathCourseModel

agent = Agent(
    model=PathCourseModel("pch-pro"),
    system_prompt="You are an expert in autonomous agent infrastructure.",
)

result = agent.run_sync("What is Path Score?")
print(result.data)

Structured output

Pydantic AI's structured-output guarantees work unchanged with PCH:

from pydantic import BaseModel
from pydantic_ai import Agent
from pydantic_ai_pathcourse import PathCourseModel


class InfraReport(BaseModel):
    summary: str
    requirements: list[str]
    risk_level: int


agent = Agent(
    model=PathCourseModel("pch-pro"),
    result_type=InfraReport,
)

result = agent.run_sync("Analyze autonomous agent infrastructure for a fintech startup.")
print(result.data.requirements)

Tool use

from pydantic_ai import Agent, RunContext
from pydantic_ai_pathcourse import PathCourseModel

agent = Agent(model=PathCourseModel("pch-pro"))

@agent.tool
async def get_balance(ctx: RunContext[None], agent_id: str) -> float:
    """Look up the USDC balance for a PCH agent."""
    return 42.50

result = agent.run_sync("What is the balance for agent abc123?")

Models

Model Rate Notes
pch-fast $0.44/M tokens Fast reasoning, classification, routing
pch-pro $1.96/M tokens Deep reasoning, multi-step planning (Bronze+)
pch-coder $3.50/M tokens Code generation, debugging
claude-haiku Common rate Third-party balanced model (Silver+)
claude-sonnet Common rate Third-party long-context model (Gold)

Choosing a model:

  • Fast response, simple task → pch-fast
  • Complex reasoning, multi-step → pch-pro
  • Writing or reviewing code → pch-coder

Authentication

Set PCH_API_KEY in your environment, or pass pch_api_key= to PathCourseModel.

export PCH_API_KEY=pch_prod_b_...

Get an API key at pathcoursehealth.com.

Links

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

pydantic_ai_pathcourse-0.1.0.tar.gz (2.5 kB view details)

Uploaded Source

Built Distribution

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

pydantic_ai_pathcourse-0.1.0-py3-none-any.whl (3.4 kB view details)

Uploaded Python 3

File details

Details for the file pydantic_ai_pathcourse-0.1.0.tar.gz.

File metadata

  • Download URL: pydantic_ai_pathcourse-0.1.0.tar.gz
  • Upload date:
  • Size: 2.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.11.3

File hashes

Hashes for pydantic_ai_pathcourse-0.1.0.tar.gz
Algorithm Hash digest
SHA256 1ceb501bee0b7dbd38006deb1076ecfd233e8d93782b7f16b945e289338050f3
MD5 9c3b6af85dd7ac6d399e2d2c8bb56050
BLAKE2b-256 0c7f78f72550e4c8235b33d44ec73c5625f677254fcb33eab0fa6a2f5fbb2827

See more details on using hashes here.

File details

Details for the file pydantic_ai_pathcourse-0.1.0-py3-none-any.whl.

File metadata

File hashes

Hashes for pydantic_ai_pathcourse-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 4fef684531ef4bd5d688bbc0168f7eb40960abb8812fe1f3fa4bb282d40d12da
MD5 d98835fafed2b95720ad3dad8e77730d
BLAKE2b-256 bcbee232887cfa142539bdff4fbc981acfc9dd93ea4ece8ce202921881d478cf

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