{ "edges": [ { "arrows": "to", "from": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]", "id": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]", "to": "agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]" }, { "arrows": "to", "from": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]", "id": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]", "to": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]" } ], "nodes": [ { "color": "grey", "data": { "category": [ "retrieval", "general" ], "cutoff": 60, "dependencies": [ "TestSearch" ], "eval_id": "525001ed-8b45-4405-9e56-ce4423314294", "ground": { "answer": "\u00a325.89", "eval": { "type": "file" }, "files": [ ".txt" ], "should_contain": [ "25.89" ], "should_not_contain": [] }, "info": { "description": "Specifies specific website to retrieve website from.", "difficulty": "basic", "side_effects": [] }, "name": "TestBasicRetrieval", "task": "Write the price of the book in this url 'http://books.toscrape.com/catalogue/meditations_33/index.html' to a .txt file." }, "id": "agbenchmark/generate_test.py::TestBasicRetrieval::test_method[challenge_data0]", "label": "BasicRetrieval", "shape": "dot" }, { "color": "grey", "data": { "category": [ "interface" ], "cutoff": 120, "dependencies": [ "TestWriteFile" ], "eval_id": "6390114a-531d-4743-a51b-50ba6ff8da43", "ground": { "answer": "This is a Heading\nThis is a paragraph.", "eval": { "type": "file" }, "files": [ ".txt" ], "should_contain": [ "Heading", "paragraph" ], "should_not_contain": [ "The", "the" ] }, "info": { "description": "Tests if an llm can search", "difficulty": "interface", "side_effects": [ "" ] }, "name": "TestSearch", "task": "Open 'https://silennaihin.com/random/plain.html' and paste all of the text on the page in a .txt file" }, "id": "agbenchmark/generate_test.py::TestSearch::test_method[challenge_data0]", "label": "Search", "shape": "dot" }, { "color": "grey", "data": { "category": [ "interface" ], "cutoff": 60, "dependencies": [], "eval_id": "81b64bf9-2b6a-4ac8-bcd2-8bfe36244ac0", "ground": { "answer": "The word 'Washington', printed to a .txt file named anything", "eval": { "type": "file" }, "files": [ ".txt" ], "should_contain": [ "Washington" ], "should_not_contain": [] }, "info": { "description": "Tests the agents ability to write to a file", "difficulty": "interface", "side_effects": [ "" ] }, "name": "TestWriteFile", "task": "Write the word 'Washington' to a .txt file" }, "id": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]", "label": "WriteFile", "shape": "dot" } ] }