Python Package: Functions

Below are the core functionalities you'll use when working with our Python client library. You can interact with your agents in two main ways:

1. Using the Agent class – for easy messaging, file uploads, and streaming.
2. Using legacy standalone functions – if you prefer a more functional style.

PYTHON
Copy
from agent_client import Agent

API_KEY = "YOUR_API_KEY"
AGENT_ID = "YOUR_AGENT_ID"

# Create an Agent instance
agent = Agent(
    agent_id=AGENT_ID,
    api_key=API_KEY,
    base_url="https://api.levangie-laboratories.com"
)

# Send a message
response = agent.message("Hello, Agent!")
print("Response:", response)

# Upload a file
with open("my_local_file.txt", "rb") as f:
    upload_resp = agent.upload_file("agent_data/file.txt", f)
    print("Upload response:", upload_resp)

# Stream responses (requires async websockets in the background)
# Provide a callback that handles each chunk of streamed data

def handle_streamed_data(data):
    print("Stream received:", data)

agent.start_streaming(callback=handle_streamed_data)

# Do something else...
# When finished, stop streaming:
agent.stop_streaming()

PYTHON
Copy
from agent_client import send_operation, upload_file

API_KEY = "YOUR_API_KEY"
AGENT_ID = "YOUR_AGENT_ID"
BASE_URL = "https://api.levangie-laboratories.com"

# Send an operation (e.g., message)
resp = send_operation(
    operation="message",
    params={"text": "Hello via operation!"},
    api_key=API_KEY,
    agent_id=AGENT_ID,
    base_url=BASE_URL
)
print("Operation response:", resp)

# Upload a file
with open("./localfile.txt", "rb") as f:
    up_resp = upload_file(
        api_key=API_KEY,
        agent_id=AGENT_ID,
        file_path="/agent_data/uploaded.txt",
        file_to_upload=f,
        base_url=BASE_URL
    )
print("Upload file response:", up_resp)

The package also supports account and usage queries:

• client.get_credits(): Check total remaining credits
• client.get_agents(): List all your agents
• client.get_total_stats(): View total usage stats
• client.get_agent_stats(agent_id): View usage for a specific agent

These calls can help you monitor and control costs.