athenaintel 0.1.1604

Athena Intelligence Python Library

Athena Intelligence Python Library

The Athena Intelligence Python Library provides convenient access to the Athena Intelligence API from applications written in Python.

The library includes type definitions for all request and response fields, and offers both synchronous and asynchronous clients powered by httpx.

Installation

Add this dependency to your project's build file:

pip install athenaintel
# or
poetry add athenaintel

Usage

Simply import Athena and start making calls to our API.

from athena import GeneralAgentConfig, GeneralAgentRequest, InputMessage
from athena.client import Athena

client = Athena(
  api_key="YOUR_API_KEY" # Defaults to ATHENA_API_KEY
)

response = client.agents.general.invoke(
    request=GeneralAgentRequest(
        config=GeneralAgentConfig(enabled_tools=[]),
        messages=[
            InputMessage(
                role="user",
                content="Summarize what Athena Intelligence does in one paragraph.",
            )
        ],
    )
)

print(response.messages[-1].content)

Async Client

The SDK also exports an async client so that you can make non-blocking calls to our API.

import asyncio

from athena import GeneralAgentConfig, GeneralAgentRequest, InputMessage
from athena.client import AsyncAthena

client = AsyncAthena(
  api_key="YOUR_API_KEY" # Defaults to ATHENA_API_KEY
)

async def main() -> None:
    response = await client.agents.general.invoke(
      request=GeneralAgentRequest(
          config=GeneralAgentConfig(enabled_tools=[]),
          messages=[
              InputMessage(
                  role="user",
                  content="Summarize what Athena Intelligence does in one paragraph.",
              )
          ],
      )
    )
    print("Received message", response)

asyncio.run(main())

Long-running workflows

For long-running AOP executions, start the execution asynchronously and check the thread status with the returned thread ID:

from athena import AopExecuteRequestIn
from athena.client import Athena

client = Athena(api_key="...")

execution = client.aop.execute_async(
    request=AopExecuteRequestIn(
        asset_id="YOUR_AOP_ASSET_ID",
        user_inputs={"company": "Athena Intelligence"},
    )
)

status = client.threads.get_status(execution.thread_id)

Athena Module

All of the models are nested within the Athena module. Let IntelliSense guide you!

Exception Handling

All errors thrown by the SDK will be subclasses of ApiError.

from athena.core import ApiError

try:
  client.users.me()
except ApiError as e: # Handle all API errors
  print(e.status_code)
  print(e.body)

Advanced

Timeouts

By default, requests time out after 60 seconds. You can configure this with a timeout option at the client or request level.

from athena.client import Athena

client = Athena(
    # All timeouts are 20 seconds
    timeout=20.0,
)

# Override timeout for a specific method
client.users.me(request_options={"timeout_in_seconds": 20})

Custom HTTP client

You can override the httpx client to customize it for your use-case. Some common use-cases include support for proxies and transports.

import httpx

from athena.client import Athena

client = Athena(
    http_client=httpx.Client(
        proxy="http://my.test.proxy.example.com",
        transport=httpx.HTTPTransport(local_address="0.0.0.0"),
    ),
)

Beta Status

This SDK is in Preview, and there may be breaking changes between versions without a major version update.

To ensure a reproducible environment (and minimize risk of breaking changes), we recommend pinning a specific package version.

Contributing

While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!

On the other hand, contributions to the README are always very welcome!