API Reference
This comprehensive API reference covers all the core components, decorators, and utilities available in the Foomstack framework.
Core Decorators
@workflow
The function to be decorated as a workflow
The decorated workflow function with enhanced execution capabilities
from foomstack import workflow
@workflow
def my_workflow(input_data: str) -> str:
# Your workflow logic here
pass
The function to be decorated as a transformer
The decorated transformer function with caching and tracing
from foomstack import transformer
@transformer
def process_text(text: str) -> Dict[str, Any]:
# Your transformation logic here
pass
Core Classes
WorkflowResult
Whether the workflow execution was successful
The result data from the workflow execution
Error message if the workflow failed
Total execution time in seconds
Detailed execution trace for debugging
Provider Classes
OpenAIProvider
OpenAI API key for authentication
The OpenAI model to use for completions
Sampling temperature between 0 and 2
Configured OpenAI client instance
from foomstack.providers import OpenAIProvider
provider = OpenAIProvider(
api_key="your-api-key",
model="gpt-4",
temperature=0.8
)
response = await provider.complete("Hello, world!")
AnthropicProvider
Anthropic API key for authentication
model
str
default:"claude-3-sonnet-20240229"
The Anthropic model to use for completions
Sampling temperature between 0 and 1
Configured Anthropic client instance
Utility Functions
cache_result
Time to live in seconds for cached results
key_func
Optional[Callable]
default:"None"
Custom function to generate cache keys
from foomstack.utils import cache_result
@cache_result(ttl=1800) # Cache for 30 minutes
def expensive_computation(data: str) -> Dict:
# Expensive operation here
return result
parallel_map
Function to apply to each item
Maximum number of concurrent workers
List of results in the same order as input items
from foomstack.utils import parallel_map
def process_item(item: str) -> int:
return len(item)
items = ["hello", "world", "parallel", "processing"]
results = await parallel_map(process_item, items)
# Results: [5, 5, 8, 10]
Configuration Classes
FoomstackConfig
Dictionary of configured providers by name
Configured caching backend
Whether tracing is enabled
Maximum number of retries for failed operations
Global timeout for operations in seconds
Error Classes
WorkflowError
Human-readable error message
Name of the workflow that failed
Name of the step that failed
Full Python traceback for debugging
ProviderError
Human-readable error message
Name of the provider that failed
HTTP status code if applicable
Seconds to wait before retrying
Constants
DEFAULT_MODEL_TIMEOUT
DEFAULT_MODEL_TIMEOUT = 300 # 5 minutes
MAX_RETRY_ATTEMPTS
Maximum number of retry attempts for failed operations.
CACHE_DEFAULT_TTL
CACHE_DEFAULT_TTL = 3600 # 1 hour
Examples
See our examples section for complete working code samples demonstrating these APIs in action.
