Database for AI powered by a storage format optimized for deep-learning applications.
75
Evaluation — 75%
↑ 1.59xAgent success when using this tile
{
"context": "This criteria evaluates how effectively an engineer uses the deeplake package's dataset management APIs to implement basic dataset lifecycle operations including creation, opening, existence checking, and deletion.",
"type": "weighted_checklist",
"checklist": [
{
"name": "Uses deeplake.create()",
"description": "Correctly uses the deeplake.create() function to create new datasets, passing the path parameter appropriately.",
"max_score": 25
},
{
"name": "Uses deeplake.open()",
"description": "Correctly uses the deeplake.open() function to open existing datasets for read-write access.",
"max_score": 25
},
{
"name": "Uses deeplake.exists()",
"description": "Correctly uses the deeplake.exists() function to check if a dataset exists at a given path, returning boolean values.",
"max_score": 25
},
{
"name": "Uses deeplake.delete()",
"description": "Correctly uses the deeplake.delete() function to permanently remove datasets from storage.",
"max_score": 25
}
]
}Install with Tessl CLI
npx tessl i tessl/pypi-deeplakedocs
evals
scenario-1
scenario-2
scenario-3
scenario-4
scenario-5
scenario-6
scenario-7
scenario-8
scenario-9
scenario-10