Skip to main content
The Agnost AI Python SDK can be configured during initialization to enable debug logging and customize behavior.

​
Basic Configuration

Initialize the SDK with your organization ID: 
import agnost

# Default configuration
agnost.init("your-org-id")

# With debug logging
agnost.init("your-org-id", debug=True)

​
Configuration Options

​
SDK Initialization (agnost.init)

ParameterTypeRequiredDefaultDescription
org_idstrRequired-Your organization ID from the Agnost AI dashboard
debugboolNoFalseEnable debug logging for troubleshooting

​
Begin/End Tracking (agnost.begin)

Start interaction with agnost.begin():
ParameterTypeRequiredDefaultDescription
user_idstrNo""Identifier for the user
agent_namestrNo"default"Name of the AI agent or model
inputstrNoNoneInput text or prompt (can also set later with set_input())
conversation_idstrNoNoneID to group related messages in a conversation
propertiesdictNoNoneAdditional metadata as key-value pairs
Complete interaction with interaction.end():
ParameterTypeRequiredDefaultDescription
outputstrNoNoneOutput or response from the AI agent
successboolNoTrueWhether the interaction was successful
latencyintNoAuto-calculatedExecution time in milliseconds (auto-calculated from begin time if not provided)

​
User Identification (agnost.identify)

ParameterTypeRequiredDefaultDescription
user_idstrRequired-Identifier for the user
traitsdictRequired-User characteristics (e.g., name, email, plan, role)

​
Debug Mode

Enable debug mode to see detailed logging of SDK operations: 
import agnost

agnost.init("your-org-id", debug=True)

# Now all tracking operations will log debug information
agnost.track(
    user_id="user_123",
    input="Hello",
    output="Hi there!"
)
# Logs: [Agnost AI] Tracking event for user_123...
Debug mode is useful for troubleshooting integration issues and verifying events are being sent correctly.

​
Next Steps