Skip to main content

ActAVA SDK: Enterprise AI orchestration platform for healthcare organizations. Commercial offering for paid customers only.

Project description

ActAVA SDK

Enterprise AI orchestration platform for healthcare organizations. Build, deploy, and manage AI agents on ActAVA's managed cloud platform.

Installation

pip install actava

Quick Start

import actava as av
from actava.langchain_openai import ChatOpenAI
from actava.langgraph import StateGraph, END

# Initialize ActAVA with your project credentials
av.init(project="your-project-id", api_key="your-api-key")

# Use LangChain/LangGraph as usual
llm = ChatOpenAI(model="gpt-4o")

def my_function(state):
    return {"result": "processed", **state}

# Create and compile graph
graph = StateGraph(dict)
graph.add_node("process", my_function)
graph.add_edge("process", END)
compiled = graph.compile()

# Export graph for deployment
from actava.graph import export
spec = export(graph)
print(spec.model_dump_json(indent=2))

Features

  • Zero API Changes: Import actava.langchain and actava.langgraph with no code changes
  • Auto Telemetry: Automatic instrumentation with configurable sampling
  • Graph Export: Export LangGraph DAGs to JSON GraphSpec for deployment
  • Runtime Service: FastAPI-based runtime service for local testing and cloud deployment
  • Healthcare Focus: Built with healthcare compliance and security in mind
  • Managed Cloud: Deploy to ActAVA's managed cloud platform with actava-cli

Deployment

Use the ActAVA CLI to deploy your agents to our managed cloud:

# Install CLI
pip install actava-cli

# Initialize project
actava init

# Deploy agent
actava push --manifest agent.manifest.yaml

Documentation

For full documentation, visit docs.actava.ai

Support

License

Proprietary software. Licensed for use by ActAVA customers only.

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

actava-0.1.1.tar.gz (7.0 kB view details)

Uploaded Source

Built Distribution

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

actava-0.1.1-py3-none-any.whl (11.8 kB view details)

Uploaded Python 3

File details

Details for the file actava-0.1.1.tar.gz.

File metadata

  • Download URL: actava-0.1.1.tar.gz
  • Upload date:
  • Size: 7.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.4

File hashes

Hashes for actava-0.1.1.tar.gz
Algorithm Hash digest
SHA256 fe3b23ed6fc895d9829afe909458c83863998469e8094ee3f5a69ba93c59c56c
MD5 9b4b2e246595b7fe384c3dfa37c34189
BLAKE2b-256 14a3c69b58c1bcd024aabd3cc9e175e56d488604bd2afb1b78ebcdc63273406f

See more details on using hashes here.

File details

Details for the file actava-0.1.1-py3-none-any.whl.

File metadata

  • Download URL: actava-0.1.1-py3-none-any.whl
  • Upload date:
  • Size: 11.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.4

File hashes

Hashes for actava-0.1.1-py3-none-any.whl
Algorithm Hash digest
SHA256 60f5b2ee382bfea088a278eb83e350fd5319fed102f4c18b94e26959c6675b7d
MD5 49e737b122f33e438e8991b92c4f7e50
BLAKE2b-256 95ec55779918ae9f70dd42adfe6bd67c6c270f8fb7a29f7e7cb6ec3b70fcb3db

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