Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ The table below shows the success rate of the AI functions with different GPT mo

| Description | GPT-4 Result | GPT-3.5-turbo Result | Reason |
|---------------------------|--------------|----------------------|--------|
| Generate fake people | PASSED | FAILED | Incorrect response format |
| Generate fake people | PASSED | PASSED | N/A |
| Generate Random Password | PASSED | PASSED | N/A |
| Calculate area of triangle| FAILED | FAILED | Incorrect float value (GPT-4), Incorrect response format (GPT-3.5-turbo) |
| Calculate the nth prime number | PASSED | PASSED | N/A |
Expand Down
2 changes: 1 addition & 1 deletion test_ai_function.py
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ def run_tests(model):
def test_1(model):
function_string = "def fake_people(n: int) -> list[dict]:"
args = ["4"]
description_string = """Generates n examples of fake data representing people,
description_string = """Generates n examples of fake data representing people in valid JSON format using double quotes not single quotes,
each with a name and an age."""

result_string = ai_functions.ai_function(function_string, args, description_string, model)
Expand Down