Installation Install the Tracia SDK using pip:
Requirements
Python 3.10+
Dependencies: httpx, pydantic, litellm
Configuration Initialize the Tracia client with your API key:
from tracia import Tracia client = Tracia( api_key = "tr_your_api_key_here" )
Configuration Options Option Type Required Description api_keystrYes Your Tracia API key (starts with tr_) base_urlstrNo Override the API base URL (default: https://app.tracia.io) on_span_errorCallable[[Exception, str], None]No Callback for background span submission failures
Environment Variables We recommend storing your API key in environment variables:
TRACIA_API_KEY = tr_your_api_key_here
import os from tracia import Tracia client = Tracia( api_key = os.environ[ "TRACIA_API_KEY" ])
Never commit API keys to version control. Use environment variables or a secrets manager.
Context Manager The SDK supports context managers for automatic resource cleanup:
with Tracia( api_key = "tr_your_api_key" ) as client: result = client.run_local( model = "gpt-4o" , messages = [{ "role" : "user" , "content" : "Hello!" }] ) print (result.text) # Resources cleaned up automatically
Async Context Manager async with Tracia( api_key = "tr_your_api_key" ) as client: result = await client.arun_local( model = "gpt-4o" , messages = [{ "role" : "user" , "content" : "Hello!" }] ) print (result.text)
Async Support Every method has both sync and async variants. Async methods use the a prefix:
from tracia import Tracia client = Tracia( api_key = "tr_your_api_key" ) # Sync result = client.run_local( model = "gpt-4o" , messages = [ ... ]) prompts = client.prompts.list() # Async result = await client.arun_local( model = "gpt-4o" , messages = [ ... ]) prompts = await client.prompts.alist()
Type Exports The SDK exports all types for type checking:
from tracia import ( Tracia, TraciaSession, TraciaError, TraciaErrorCode, Eval, # Streaming LocalStream, AsyncLocalStream, # Core types LLMProvider, TokenUsage, FinishReason, # Message types LocalPromptMessage, ContentPart, TextPart, ToolCallPart, # Tool types ToolDefinition, ToolCall, ToolChoice, # Run local types RunLocalInput, RunLocalResult, StreamResult, # Span types Span, ListSpansOptions, ListSpansResult, EvaluateOptions, EvaluateResult, # Prompt types Prompt, PromptListItem, PromptMessage, CreatePromptOptions, UpdatePromptOptions, RunOptions, RunResult, )
Next Steps
Prompts SDK Manage and run prompts stored in Tracia
Run Local Execute prompts directly against LLM providers
