Skip to main content
The framework provides comprehensive error handling for all LLM operations.

​
ModelHTTPError

HTTP errors during model requests: 
from upsonic import Agent, Task
from upsonic.models.openai import OpenAIChatModel
from upsonic.utils.package.exception import ModelHTTPError

try:
    model = OpenAIChatModel(model_name="gpt-4o")
    agent = Agent(model=model)
    task = Task("Hello")
    result = agent.do(task)
except ModelHTTPError as e:
    print(f"Status Code: {e.status_code}")
    print(f"Model: {e.model_name}")
    print(f"Body: {e.body}")

​
UserError

Configuration or usage errors: 
from upsonic.models.openai import OpenAIChatModel
from upsonic.utils.package.exception import UserError

try:
    model = OpenAIChatModel(model_name="invalid-model-name")
except UserError as e:
    print(f"Error: {e}")

​
UnexpectedModelBehavior

Unexpected model responses: 
from upsonic.models.openai import OpenAIChatModel
from upsonic.models.settings import ModelSettings
from upsonic.models import ModelRequestParameters
from upsonic.utils.package.exception import UnexpectedModelBehavior

try:
    model_settings = ModelSettings(max_tokens=2048)
    model_request_parameters = ModelRequestParameters()
    async with model.request_stream(messages, model_settings, model_request_parameters) as stream:
        pass
except UnexpectedModelBehavior as e:
    print(f"Unexpected behavior: {e}")

​
Rate Limit Handling

Rate limit handling with exponential backoff retry: 
import asyncio
from upsonic import Agent, Task
from upsonic.utils.package.exception import ModelHTTPError

async def request_with_retry(agent, task, max_retries=3):
    for attempt in range(max_retries):
        try:
            return agent.do(task)
        except ModelHTTPError as e:
            if e.status_code == 429:  # Rate limit
                wait_time = 2 ** attempt  # Exponential backoff
                print(f"Rate limited. Waiting {wait_time}s...")
                await asyncio.sleep(wait_time)
            else:
                raise
    raise Exception("Max retries exceeded")

​
Token Limit Handling

Context length exceeded handling: 
from upsonic import Agent, Task
from upsonic.models.openai import OpenAIChatModel
from upsonic.models.settings import ModelSettings
from upsonic.utils.package.exception import ModelHTTPError

try:
    settings = ModelSettings(max_tokens=4096)
    model = OpenAIChatModel(model_name="gpt-4o")
    agent = Agent(model=model, settings=settings)
    result = agent.do(very_long_task)
except ModelHTTPError as e:
    if "context_length_exceeded" in str(e.body):
        print("Input too long, consider truncating")

​
Invalid Response Handling

Structured output validation: 
from pydantic import BaseModel, ValidationError
from upsonic.models.openai import OpenAIChatModel

class ResponseFormat(BaseModel):
    answer: str
    confidence: float

try:
    model = OpenAIChatModel(model_name="gpt-4o")
    model = model.with_structured_output(ResponseFormat)
    result = await model.ainvoke("What is AI?")
except ValidationError as e:
    print(f"Invalid response format: {e}")

​
Global Error Handling

Disable model requests for testing: 
from upsonic import Agent, Task
from upsonic.models import override_allow_model_requests

with override_allow_model_requests(False):
    try:
        result = agent.do(task)
    except RuntimeError as e:
        print("Model requests are disabled")