Python client library for Modal, a serverless cloud computing platform that enables developers to run Python code in the cloud with on-demand access to compute resources.
85
{
"context": "This evaluation assesses how well the engineer uses Modal's dynamic batching capability (@modal.batched decorator) along with web endpoint functionality to build an efficient image classification service. The focus is on proper implementation of batching for performance optimization.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Modal App Creation",
"description": "Creates a modal.App instance to define the application",
"max_score": 10
},
{
"name": "Batched Decorator Usage",
"description": "Uses the @modal.batched decorator on the classification function to enable dynamic batching of inputs",
"max_score": 30
},
{
"name": "Batch Parameters",
"description": "Configures batching parameters (max_batch_size and/or wait_ms) appropriately for the use case",
"max_score": 15
},
{
"name": "Batch Input/Output",
"description": "Implements the batched function to correctly accept a list of inputs and return a list of outputs matching the batch semantics",
"max_score": 25
},
{
"name": "Web Endpoint",
"description": "Uses @modal.web_endpoint or @modal.fastapi_endpoint decorator to expose the service as an HTTP endpoint",
"max_score": 10
},
{
"name": "Function Decorator",
"description": "Uses @app.function() decorator (or equivalent) to define the serverless function with appropriate configuration",
"max_score": 10
}
]
}Install with Tessl CLI
npx tessl i tessl/pypi-modaldocs
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10