aiverify-moonshot 0.5.0__tar.gz → 0.6.0__tar.gz

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/.github/workflows/integration-test.yaml

@@ -110,7 +110,7 @@ jobs:
       run: |
         source venv/bin/activate
         pip install nltk
-        python -c "import nltk; nltk.download('stopwords')"
+        python -c "import nltk; nltk.download('stopwords');nltk.download('averaged_perceptron_tagger'); nltk.download('omw');nltk.download('universal_tagset'); nltk.download('wordnet');nltk.download('punkt')"
     
     - name: Setup Moonshot UI
       run: |

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/.github/workflows/pypi-deployment.yaml

@@ -76,7 +76,7 @@ jobs:
         name: python-package-distributions
         path: dist/
     - name: Sign the dists with Sigstore
-      uses: sigstore/gh-action-sigstore-python@v2.1.1
+      uses: sigstore/gh-action-sigstore-python@latest
       with:
         inputs: >-
           ./dist/*.tar.gz

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/PKG-INFO

@@ -1,12 +1,15 @@
-Metadata-Version: 2.3
+Metadata-Version: 2.4
 Name: aiverify-moonshot
-Version: 0.5.0
+Version: 0.6.0
 Summary: AI Verify advances Gen AI testing with Project Moonshot.
 Project-URL: Repository, https://github.com/aiverify-foundation/moonshot
 Project-URL: Documentation, https://aiverify-foundation.github.io/moonshot/
 Project-URL: Issues, https://github.com/aiverify-foundation/moonshot/issues
 Author-email: AI Verify Foundation <info@aiverify.sg>
 License: Apache-2.0
+License-File: AUTHORS.md
+License-File: LICENSE.md
+License-File: NOTICES.md
 Classifier: Development Status :: 3 - Alpha
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python :: 3
@@ -26,7 +29,7 @@ Requires-Dist: xxhash>=3.5.0
 Provides-Extra: all
 Requires-Dist: cmd2>=2.4.3; extra == 'all'
 Requires-Dist: dependency-injector>=4.41.0; extra == 'all'
-Requires-Dist: fastapi>=0.112.2; extra == 'all'
+Requires-Dist: fastapi>=0.115.4; extra == 'all'
 Requires-Dist: rich>=13.8.0; extra == 'all'
 Requires-Dist: typing-extensions>=4.12.2; extra == 'all'
 Requires-Dist: uvicorn>=0.30.6; extra == 'all'
@@ -35,7 +38,7 @@ Requires-Dist: cmd2>=2.4.3; extra == 'cli'
 Requires-Dist: rich>=13.8.0; extra == 'cli'
 Provides-Extra: web-api
 Requires-Dist: dependency-injector>=4.41.0; extra == 'web-api'
-Requires-Dist: fastapi>=0.112.2; extra == 'web-api'
+Requires-Dist: fastapi>=0.115.4; extra == 'web-api'
 Requires-Dist: typing-extensions>=4.12.2; extra == 'web-api'
 Requires-Dist: uvicorn>=0.30.6; extra == 'web-api'
 Description-Content-Type: text/markdown
@@ -44,7 +47,7 @@ Description-Content-Type: text/markdown
 
 ![Moonshot Logo](https://github.com/aiverify-foundation/moonshot/raw/main/misc/aiverify-moonshot-logo.png)
 
-**Version 0.5.0**
+**Version 0.6.0**
 
 A simple and modular tool to evaluate any LLM application.
 

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/README.md

@@ -2,7 +2,7 @@
 
 ![Moonshot Logo](https://github.com/aiverify-foundation/moonshot/raw/main/misc/aiverify-moonshot-logo.png)
 
-**Version 0.5.0**
+**Version 0.6.0**
 
 A simple and modular tool to evaluate any LLM application.
 

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/cli/benchmark/cookbook.py

@@ -37,7 +37,8 @@ from moonshot.integrations.cli.cli_errors import (
     ERROR_BENCHMARK_RUN_COOKBOOK_ENDPOINTS_VALIDATION_1,
     ERROR_BENCHMARK_RUN_COOKBOOK_NAME_VALIDATION,
     ERROR_BENCHMARK_RUN_COOKBOOK_NO_RESULT,
-    ERROR_BENCHMARK_RUN_COOKBOOK_NUM_OF_PROMPTS_VALIDATION,
+    ERROR_BENCHMARK_RUN_COOKBOOK_PROMPT_SELECTION_PERCENTAGE_RANGE_VALIDATION,
+    ERROR_BENCHMARK_RUN_COOKBOOK_PROMPT_SELECTION_PERCENTAGE_VALIDATION,
     ERROR_BENCHMARK_RUN_COOKBOOK_RANDOM_SEED_VALIDATION,
     ERROR_BENCHMARK_RUN_COOKBOOK_RESULT_PROC_MOD_VALIDATION,
     ERROR_BENCHMARK_RUN_COOKBOOK_RUNNER_PROC_MOD_VALIDATION,
@@ -212,11 +213,12 @@ def run_cookbook(args) -> None:
     The cookbooks are run against the specified endpoints, and the results are processed and displayed.
 
     Args:
-        args: A namespace object from argparse. It should have the following attributes:
+        args (argparse.Namespace): The arguments provided to the command line interface.
+        Expected keys are:
             name (str): The name of the cookbook runner.
             cookbooks (str): A string representation of a list of cookbooks to run.
             endpoints (str): A string representation of a list of endpoints to run.
-            num_of_prompts (int): The number of prompts to run.
+            prompt_selection_percentage (int): The percentage of prompts to run.
             random_seed (int): The random seed number for reproducibility.
             system_prompt (str): The system prompt to use.
             runner_proc_module (str): The runner processing module to use.
@@ -248,10 +250,19 @@ def run_cookbook(args) -> None:
         ):
             raise TypeError(ERROR_BENCHMARK_RUN_COOKBOOK_ENDPOINTS_VALIDATION)
 
-        if isinstance(args.num_of_prompts, bool) or not isinstance(
-            args.num_of_prompts, int
+        if isinstance(args.prompt_selection_percentage, bool) or not isinstance(
+            args.prompt_selection_percentage, int
+        ):
+            raise TypeError(
+                ERROR_BENCHMARK_RUN_COOKBOOK_PROMPT_SELECTION_PERCENTAGE_VALIDATION
+            )
+        elif (
+            args.prompt_selection_percentage < 1
+            or args.prompt_selection_percentage > 100
         ):
-            raise TypeError(ERROR_BENCHMARK_RUN_COOKBOOK_NUM_OF_PROMPTS_VALIDATION)
+            raise ValueError(
+                ERROR_BENCHMARK_RUN_COOKBOOK_PROMPT_SELECTION_PERCENTAGE_RANGE_VALIDATION
+            )
 
         if isinstance(args.random_seed, bool) or not isinstance(args.random_seed, int):
             raise TypeError(ERROR_BENCHMARK_RUN_COOKBOOK_RANDOM_SEED_VALIDATION)
@@ -297,7 +308,7 @@ def run_cookbook(args) -> None:
         async def run():
             await cb_runner.run_cookbooks(
                 cookbooks,
-                args.num_of_prompts,
+                args.prompt_selection_percentage,
                 args.random_seed,
                 args.system_prompt,
                 args.runner_proc_module,
@@ -436,9 +447,20 @@ def _display_cookbooks(cookbooks_list):
     table.add_column("Cookbook", justify="left", width=78)
     table.add_column("Contains", justify="left", width=20, overflow="fold")
     for idx, cookbook in enumerate(cookbooks_list, 1):
-        id, name, description, recipes, *other_args = cookbook.values()
+        (
+            id,
+            name,
+            tags,
+            categories,
+            description,
+            recipes,
+            *other_args,
+        ) = cookbook.values()
         idx = cookbook.get("idx", idx)
-        cookbook_info = f"[red]ID: {id}[/red]\n\n[blue]{name}[/blue]\n{description}"
+        cookbook_info = f"[red]ID: {id}[/red]\n\n[blue]{name}[/blue]\n\n{description}"
+        cookbook_info += (
+            f"\n\n[blue]Tags: {tags}[/blue]\n[blue]Categories: {categories}[/blue]\n"
+        )
         recipes_info = display_view_list_format("Recipes", recipes)
         table.add_section()
         table.add_row(str(idx), cookbook_info, recipes_info)
@@ -459,11 +481,11 @@ def _display_view_cookbook(cookbook_info):
     Returns:
         None
     """
-    id, name, description, recipes = cookbook_info.values()
+    id, name, tags, categories, description, recipes = cookbook_info.values()
     recipes_list = api_read_recipes(recipes)
     if recipes_list:
         table = Table(
-            title=f'Cookbook "{name}"',
+            title=f'Cookbook: "{name}"\n Tags: {tags}\n Categories: {categories}\n',
             show_lines=True,
             expand=True,
             header_style="bold",
@@ -471,6 +493,7 @@ def _display_view_cookbook(cookbook_info):
         table.add_column("No.", width=2)
         table.add_column("Recipe", justify="left", width=78)
         table.add_column("Contains", justify="left", width=20, overflow="fold")
+
         for recipe_id, recipe in enumerate(recipes_list, 1):
             (
                 id,
@@ -718,7 +741,11 @@ run_cookbook_args.add_argument("name", type=str, help="Name of cookbook runner")
 run_cookbook_args.add_argument("cookbooks", type=str, help="List of cookbooks to run")
 run_cookbook_args.add_argument("endpoints", type=str, help="List of endpoints to run")
 run_cookbook_args.add_argument(
-    "-n", "--num_of_prompts", type=int, default=0, help="Number of prompts to run"
+    "-n",
+    "--prompt_selection_percentage",
+    type=int,
+    default=100,
+    help="Percentage of prompts to run",
 )
 run_cookbook_args.add_argument(
     "-r", "--random_seed", type=int, default=0, help="Random seed number"

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/cli/benchmark/recipe.py

@@ -40,7 +40,8 @@ from moonshot.integrations.cli.cli_errors import (
     ERROR_BENCHMARK_RUN_RECIPE_ENDPOINTS_VALIDATION_1,
     ERROR_BENCHMARK_RUN_RECIPE_NAME_VALIDATION,
     ERROR_BENCHMARK_RUN_RECIPE_NO_RESULT,
-    ERROR_BENCHMARK_RUN_RECIPE_NUM_OF_PROMPTS_VALIDATION,
+    ERROR_BENCHMARK_RUN_RECIPE_PROMPT_SELECTION_PERCENTAGE_RANGE_VALIDATION,
+    ERROR_BENCHMARK_RUN_RECIPE_PROMPT_SELECTION_PERCENTAGE_VALIDATION,
     ERROR_BENCHMARK_RUN_RECIPE_RANDOM_SEED_VALIDATION,
     ERROR_BENCHMARK_RUN_RECIPE_RECIPES_VALIDATION,
     ERROR_BENCHMARK_RUN_RECIPE_RECIPES_VALIDATION_1,
@@ -293,11 +294,12 @@ def run_recipe(args) -> None:
     The recipes are run against the specified endpoints, and the results are processed and displayed.
 
     Args:
-        args: A namespace object from argparse. It should have the following attributes:
+        args (argparse.Namespace): The arguments provided to the command line interface.
+        Expected keys are:
             name (str): The name of the recipe runner.
             recipes (str): A string representation of a list of recipes to run.
             endpoints (str): A string representation of a list of endpoints to run.
-            num_of_prompts (int): The number of prompts to run.
+            prompt_selection_percentage (int): The percentage of prompts to run.
             random_seed (int): The random seed number for reproducibility.
             system_prompt (str): The system prompt to use.
             runner_proc_module (str): The runner processing module to use.
@@ -329,10 +331,19 @@ def run_recipe(args) -> None:
         ):
             raise TypeError(ERROR_BENCHMARK_RUN_RECIPE_ENDPOINTS_VALIDATION)
 
-        if isinstance(args.num_of_prompts, bool) or not isinstance(
-            args.num_of_prompts, int
+        if isinstance(args.prompt_selection_percentage, bool) or not isinstance(
+            args.prompt_selection_percentage, int
+        ):
+            raise TypeError(
+                ERROR_BENCHMARK_RUN_RECIPE_PROMPT_SELECTION_PERCENTAGE_VALIDATION
+            )
+        elif (
+            args.prompt_selection_percentage < 1
+            or args.prompt_selection_percentage > 100
         ):
-            raise TypeError(ERROR_BENCHMARK_RUN_RECIPE_NUM_OF_PROMPTS_VALIDATION)
+            raise ValueError(
+                ERROR_BENCHMARK_RUN_RECIPE_PROMPT_SELECTION_PERCENTAGE_RANGE_VALIDATION
+            )
 
         if isinstance(args.random_seed, bool) or not isinstance(args.random_seed, int):
             raise TypeError(ERROR_BENCHMARK_RUN_RECIPE_RANDOM_SEED_VALIDATION)
@@ -377,7 +388,7 @@ def run_recipe(args) -> None:
         async def run():
             await rec_runner.run_recipes(
                 recipes,
-                args.num_of_prompts,
+                args.prompt_selection_percentage,
                 args.random_seed,
                 args.system_prompt,
                 args.runner_proc_module,
@@ -809,7 +820,11 @@ run_recipe_args.add_argument("name", type=str, help="Name of recipe runner")
 run_recipe_args.add_argument("recipes", type=str, help="List of recipes to run")
 run_recipe_args.add_argument("endpoints", type=str, help="List of endpoints to run")
 run_recipe_args.add_argument(
-    "-n", "--num_of_prompts", type=int, default=0, help="Number of prompts to run"
+    "-n",
+    "--prompt_selection_percentage",
+    type=int,
+    default=100,
+    help="Percentage of prompts to run",
 )
 run_recipe_args.add_argument(
     "-r", "--random_seed", type=int, default=0, help="Random seed number"

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/cli/benchmark/result.py

@@ -190,7 +190,7 @@ def _display_results(results_list):
         recipes = metadata["recipes"]
         cookbooks = metadata["cookbooks"]
         endpoints = metadata["endpoints"]
-        num_of_prompts = metadata["num_of_prompts"]
+        prompt_selection_percentage = metadata["prompt_selection_percentage"]
         random_seed = metadata["random_seed"]
         system_prompt = metadata["system_prompt"]
         idx = result.get("idx", idx)
@@ -200,7 +200,9 @@ def _display_results(results_list):
         recipes_info = display_view_list_format("Recipes", recipes)
         cookbooks_info = display_view_list_format("Cookbooks", cookbooks)
         endpoints_info = display_view_list_format("Endpoints", endpoints)
-        prompts_info = display_view_str_format("Number of Prompts", num_of_prompts)
+        prompts_info = display_view_str_format(
+            "Prompt Selection Percentage", prompt_selection_percentage
+        )
         seed_info = display_view_str_format("Seed", random_seed)
         system_prompt_info = display_view_str_format("System Prompt", system_prompt)
 

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/cli/cli_errors.py

@@ -52,8 +52,11 @@ ERROR_BENCHMARK_RUN_COOKBOOK_ENDPOINTS_VALIDATION = (
 ERROR_BENCHMARK_RUN_COOKBOOK_ENDPOINTS_VALIDATION_1 = (
     "The 'endpoints' argument must evaluate to a list of strings."
 )
-ERROR_BENCHMARK_RUN_COOKBOOK_NUM_OF_PROMPTS_VALIDATION = (
-    "The 'num_of_prompts' argument must be an integer."
+ERROR_BENCHMARK_RUN_COOKBOOK_PROMPT_SELECTION_PERCENTAGE_VALIDATION = (
+    "The 'prompt_selection_percentage' argument must be an integer."
+)
+ERROR_BENCHMARK_RUN_COOKBOOK_PROMPT_SELECTION_PERCENTAGE_RANGE_VALIDATION = (
+    "The 'prompt_selection_percentage' argument must be between 1 - 100."
 )
 ERROR_BENCHMARK_RUN_COOKBOOK_RANDOM_SEED_VALIDATION = (
     "The 'random_seed' argument must be an integer."
@@ -278,8 +281,11 @@ ERROR_BENCHMARK_RUN_RECIPE_ENDPOINTS_VALIDATION = (
 ERROR_BENCHMARK_RUN_RECIPE_ENDPOINTS_VALIDATION_1 = (
     "The 'endpoints' argument must evaluate to a list of strings."
 )
-ERROR_BENCHMARK_RUN_RECIPE_NUM_OF_PROMPTS_VALIDATION = (
-    "The 'num_of_prompts' argument must be an integer."
+ERROR_BENCHMARK_RUN_RECIPE_PROMPT_SELECTION_PERCENTAGE_VALIDATION = (
+    "The 'prompt_selection_percentage' argument must be an integer."
+)
+ERROR_BENCHMARK_RUN_RECIPE_PROMPT_SELECTION_PERCENTAGE_RANGE_VALIDATION = (
+    "The 'prompt_selection_percentage' argument must be between 1 - 100."
 )
 ERROR_BENCHMARK_RUN_RECIPE_RANDOM_SEED_VALIDATION = (
     "The 'random_seed' argument must be an integer."

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/cli/common/dataset.py

@@ -5,13 +5,12 @@ from rich.console import Console
 from rich.table import Table
 
 from moonshot.api import (
+    api_convert_dataset,
     api_delete_dataset,
+    api_download_dataset,
     api_get_all_datasets,
     api_get_all_datasets_name,
-    api_convert_dataset, 
-    api_download_dataset
 )
-
 from moonshot.integrations.cli.cli_errors import (
     ERROR_BENCHMARK_DELETE_DATASET_DATASET_VALIDATION,
     ERROR_BENCHMARK_LIST_DATASETS_FIND_VALIDATION,
@@ -19,12 +18,12 @@ from moonshot.integrations.cli.cli_errors import (
     ERROR_BENCHMARK_LIST_DATASETS_PAGINATION_VALIDATION_1,
     ERROR_BENCHMARK_VIEW_DATASET_DATASET_FILENAME_VALIDATION,
 )
-
 from moonshot.integrations.cli.common.display_helper import display_view_str_format
 from moonshot.integrations.cli.utils.process_data import filter_data
 
 console = Console()
 
+
 def list_datasets(args) -> list | None:
     """
     List all available datasets.
@@ -155,6 +154,7 @@ def delete_dataset(args) -> None:
     except Exception as e:
         print(f"[delete_dataset]: {str(e)}")
 
+
 def convert_dataset(args) -> None:
     """
     Convert an existing dataset to a new format.
@@ -350,8 +350,7 @@ download_dataset_args.add_argument(
     type=literal_eval,
     help=(
         "Params of the new dataset in dictionary format. For example: \n"
-        "1. For 'csv' method: \"{'csv_file_path': '/path/to/your/file.csv'}\"\n"
-        "2. For 'hf' method: \"{'dataset_name': 'cais_mmlu', 'dataset_config': 'college_biology', 'split': 'test', "
+        "{'dataset_name': 'cais_mmlu', 'dataset_config': 'college_biology', 'split': 'test', "
         "'input_col': ['questions','choices'], 'target_col': 'answer'}\""
     ),
 )

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/web_api/app.py

@@ -71,7 +71,7 @@ def create_app(cfg: providers.Configuration) -> CustomFastAPI:
     }
 
     app: CustomFastAPI = CustomFastAPI(
-        title="Project Moonshot", version="0.5.0", **app_kwargs
+        title="Project Moonshot", version="0.6.0", **app_kwargs
     )
 
     if cfg.cors.enabled():

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/web_api/schemas/benchmark_runner_dto.py

@@ -1,4 +1,4 @@
-from pydantic import BaseModel, ConfigDict
+from pydantic import BaseModel, ConfigDict, Field
 
 
 class BenchmarkRunnerDTO(BaseModel):
@@ -7,7 +7,7 @@ class BenchmarkRunnerDTO(BaseModel):
     description: str
     endpoints: list[str]
     inputs: list[str]
-    num_of_prompts: int
+    prompt_selection_percentage: int = Field(..., ge=1, le=100)
     random_seed: int
     system_prompt: str
     runner_processing_module: str

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/web_api/schemas/cookbook_create_dto.py

@@ -9,6 +9,8 @@ class CookbookCreateDTO(CookbookPydanticModel):
     id: Optional[str] = None
     name: str = Field(..., min_length=1)
     description: Optional[str] = Field(default="", min_length=1)
+    tags: Optional[list[str]] = []
+    categories: Optional[list[str]] = []
     recipes: list[str] = Field(..., min_length=1)
 
 
@@ -16,4 +18,6 @@ class CookbookUpdateDTO(CookbookPydanticModel):
     id: Optional[str] = None
     name: Optional[str] = Field(default=None, min_length=1)
     description: Optional[str] = Field(default=None, min_length=1)
+    tags: Optional[list[str]] = None
+    categories: Optional[list[str]] = None
     recipes: Optional[list[str]] = Field(default=None, min_length=1)

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/web_api/schemas/cookbook_response_model.py

@@ -8,4 +8,4 @@ from moonshot.src.cookbooks.cookbook_arguments import (
 class CookbookResponseModel(CookbookPydanticModel):
     total_prompt_in_cookbook: Optional[int] = None
     total_dataset_in_cookbook: Optional[int] = None
-    endpoint_required: Optional[list[str]] = None
+    required_config: dict | None = None

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/web_api/schemas/dataset_create_dto.py

@@ -1,7 +1,6 @@
-from typing import Optional
+from typing import Any, Optional
 
 from pydantic import Field
-from pyparsing import Iterator
 
 from moonshot.src.datasets.dataset_arguments import (
     DatasetArguments as DatasetPydanticModel,
@@ -10,7 +9,7 @@ from moonshot.src.datasets.dataset_arguments import (
 
 class CSV_Dataset_DTO(DatasetPydanticModel):
     id: Optional[str] = None  # Not a required from user
-    examples: Optional[Iterator[dict]] = None  # Not a required from user
+    examples: Optional[Any] = None  # Not a required from user
     name: str = Field(..., min_length=1)
     description: str = Field(default="", min_length=1)
     license: Optional[str] = ""
@@ -20,7 +19,7 @@ class CSV_Dataset_DTO(DatasetPydanticModel):
 
 class HF_Dataset_DTO(DatasetPydanticModel):
     id: Optional[str] = None  # Not a required from user
-    examples: Optional[Iterator[dict]] = None  # Not a required from user
+    examples: Optional[Any] = None  # Not a required from user
     name: str = Field(..., min_length=1)
     description: str = Field(default="", min_length=1)
     license: Optional[str] = ""

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/web_api/schemas/recipe_response_model.py

@@ -5,4 +5,4 @@ from moonshot.src.recipes.recipe_arguments import RecipeArguments as RecipePydan
 
 class RecipeResponseModel(RecipePydanticModel):
     total_prompt_in_recipe: Optional[int] = None
-    endpoint_required: Optional[list[str]] = None
+    required_config: dict | None = None

{aiverify_moonshot-0.5.0 → aiverify_moonshot-0.6.0}/moonshot/integrations/web_api/services/benchmark_test_manager.py

@@ -60,14 +60,14 @@ class BenchmarkTestManager(BaseService):
             if benchmark_type == BenchmarkCollectionType.COOKBOOK:
                 async_run = moonshot_runner.run_cookbooks(
                     cookbooks=benchmark_input_data.inputs,
-                    num_of_prompts=benchmark_input_data.num_of_prompts,
+                    prompt_selection_percentage=benchmark_input_data.prompt_selection_percentage,
                     random_seed=benchmark_input_data.random_seed,
                     system_prompt=benchmark_input_data.system_prompt,
                 )
             else:
                 async_run = moonshot_runner.run_recipes(
                     recipes=benchmark_input_data.inputs,
-                    num_of_prompts=benchmark_input_data.num_of_prompts,
+                    prompt_selection_percentage=benchmark_input_data.prompt_selection_percentage,
                     random_seed=benchmark_input_data.random_seed,
                     system_prompt=benchmark_input_data.system_prompt,
                 )