aiverify-moonshot 0.6.2__py3-none-any.whl → 0.6.4__py3-none-any.whl

moonshot/src/connectors/connector.py

@@ -15,20 +15,6 @@ from moonshot.src.connectors.connector_response import ConnectorResponse
 from moonshot.src.connectors_endpoints.connector_endpoint_arguments import (
     ConnectorEndpointArguments,
 )
-from moonshot.src.messages_constants import (
-    CONNECTOR_CREATE_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR,
-    CONNECTOR_CREATE_ERROR,
-    CONNECTOR_GET_AVAILABLE_ITEMS_ERROR,
-    CONNECTOR_GET_PREDICTION_ARGUMENTS_CONNECTOR_VALIDATION_ERROR,
-    CONNECTOR_GET_PREDICTION_ARGUMENTS_GENERATED_PROMPT_VALIDATION_ERROR,
-    CONNECTOR_GET_PREDICTION_ERROR,
-    CONNECTOR_GET_PREDICTION_INFO,
-    CONNECTOR_GET_PREDICTION_TIME_TAKEN_INFO,
-    CONNECTOR_LOAD_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR,
-    CONNECTOR_LOAD_CONNECTOR_INSTANCE_RUNTIME_ERROR,
-    CONNECTOR_PERFORM_RETRY_CALLBACK_ERROR,
-    CONNECTOR_SET_SYSTEM_PROMPT_VALIDATION_ERROR,
-)
 from moonshot.src.storage.storage import Storage
 from moonshot.src.utils.import_modules import get_instance
 from moonshot.src.utils.log import configure_logger
@@ -50,6 +36,8 @@ def perform_retry_callback(connector_id: str, retry_state: RetryCallState) -> No
         retry_state (RetryCallState): The state of the retry call, which includes
             information about the current attempt, the exception raised, and the next action.
     """
+    CONNECTOR_PERFORM_RETRY_CALLBACK_ERROR = "[Connector ID: {connector_id}] Attempt {attempt_no} failed due to error: {message}"  # noqa: E501
+
     sleep_time = retry_state.idle_for if retry_state else 0
     exception = (
         retry_state.outcome.exception() if retry_state.outcome else "Unknown exception"
@@ -92,6 +80,24 @@ def perform_retry(func):
 
 
 class Connector:
+    CONNECTOR_CREATE_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR = "[Connector] The 'ep_args' argument must be an instance of ConnectorEndpointArguments and not None."  # noqa: E501
+    CONNECTOR_CREATE_ERROR = "[Connector] Failed to create connector: {message}"
+    CONNECTOR_GET_AVAILABLE_ITEMS_ERROR = (
+        "[Connector] Failed to get available connectors: {message}"
+    )
+    CONNECTOR_GET_PREDICTION_ARGUMENTS_CONNECTOR_VALIDATION_ERROR = "[Connector] The 'connector' argument must be an instance of Connector and not None."  # noqa: E501
+    CONNECTOR_GET_PREDICTION_ARGUMENTS_GENERATED_PROMPT_VALIDATION_ERROR = "[Connector] The 'generated_prompt' argument must be an instance of ConnectorPromptArguments and not None."  # noqa: E501
+    CONNECTOR_GET_PREDICTION_ERROR = "[Connector ID: {connector_id}] Prompt Index {prompt_index} failed to get prediction: {message}"  # noqa: E501
+    CONNECTOR_GET_PREDICTION_INFO = (
+        "[Connector ID: {connector_id}] Predicting Prompt Index {prompt_index}."
+    )
+    CONNECTOR_GET_PREDICTION_TIME_TAKEN_INFO = "[Connector ID: {connector_id}] Prompt Index {prompt_index} took {prompt_duration}s."  # noqa: E501
+    CONNECTOR_LOAD_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR = "[Connector] The 'ep_args' argument must be an instance of ConnectorEndpointArguments and not None."  # noqa: E501
+    CONNECTOR_LOAD_CONNECTOR_INSTANCE_RUNTIME_ERROR = (
+        "[Connector] Failed to get connector instance: {message}"
+    )
+    CONNECTOR_SET_SYSTEM_PROMPT_VALIDATION_ERROR = "[Connector] The 'system_prompt' argument must be an instance of string and not None."  # noqa: E501
+
     def __init__(self, ep_args: ConnectorEndpointArguments) -> None:
         self.id = ep_args.id
 
@@ -223,7 +229,7 @@ class Connector:
         """
         if ep_args is None or not isinstance(ep_args, ConnectorEndpointArguments):
             raise ValueError(
-                CONNECTOR_LOAD_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR
+                Connector.CONNECTOR_LOAD_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR
             )
 
         connector_instance = get_instance(
@@ -236,7 +242,7 @@ class Connector:
             return connector_instance(ep_args)
         else:
             raise RuntimeError(
-                CONNECTOR_LOAD_CONNECTOR_INSTANCE_RUNTIME_ERROR.format(
+                Connector.CONNECTOR_LOAD_CONNECTOR_INSTANCE_RUNTIME_ERROR.format(
                     message=ep_args.connector_type
                 )
             )
@@ -264,12 +270,12 @@ class Connector:
         try:
             if ep_args is None or not isinstance(ep_args, ConnectorEndpointArguments):
                 raise ValueError(
-                    CONNECTOR_CREATE_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR
+                    Connector.CONNECTOR_CREATE_CONNECTOR_ENDPOINT_ARGUMENTS_VALIDATION_ERROR
                 )
             return Connector.load(ep_args)
 
         except Exception as e:
-            logger.error(CONNECTOR_CREATE_ERROR.format(message=str(e)))
+            logger.error(Connector.CONNECTOR_CREATE_ERROR.format(message=str(e)))
             raise e
 
     @staticmethod
@@ -296,7 +302,9 @@ class Connector:
             ]
 
         except Exception as e:
-            logger.error(CONNECTOR_GET_AVAILABLE_ITEMS_ERROR.format(message=str(e)))
+            logger.error(
+                Connector.CONNECTOR_GET_AVAILABLE_ITEMS_ERROR.format(message=str(e))
+            )
             raise e
 
     @staticmethod
@@ -336,17 +344,17 @@ class Connector:
             generated_prompt, ConnectorPromptArguments
         ):
             raise ValueError(
-                CONNECTOR_GET_PREDICTION_ARGUMENTS_GENERATED_PROMPT_VALIDATION_ERROR
+                Connector.CONNECTOR_GET_PREDICTION_ARGUMENTS_GENERATED_PROMPT_VALIDATION_ERROR
             )
 
         if connector is None or not isinstance(connector, Connector):
             raise ValueError(
-                CONNECTOR_GET_PREDICTION_ARGUMENTS_CONNECTOR_VALIDATION_ERROR
+                Connector.CONNECTOR_GET_PREDICTION_ARGUMENTS_CONNECTOR_VALIDATION_ERROR
             )
 
         try:
             logger.info(
-                CONNECTOR_GET_PREDICTION_INFO.format(
+                Connector.CONNECTOR_GET_PREDICTION_INFO.format(
                     connector_id=connector.id,
                     prompt_index=generated_prompt.prompt_index,
                 )
@@ -358,7 +366,7 @@ class Connector:
             )
             generated_prompt.duration = time.perf_counter() - start_time
             logger.debug(
-                CONNECTOR_GET_PREDICTION_TIME_TAKEN_INFO.format(
+                Connector.CONNECTOR_GET_PREDICTION_TIME_TAKEN_INFO.format(
                     connector_id=connector.id,
                     prompt_index=generated_prompt.prompt_index,
                     prompt_duration=f"{generated_prompt.duration:.4f}",
@@ -374,7 +382,7 @@ class Connector:
 
         except Exception as e:
             logger.error(
-                CONNECTOR_GET_PREDICTION_ERROR.format(
+                Connector.CONNECTOR_GET_PREDICTION_ERROR.format(
                     connector_id=connector.id,
                     prompt_index=generated_prompt.prompt_index,
                     message=str(e),
@@ -396,5 +404,5 @@ class Connector:
             ValueError: If the provided system prompt is not a string or is None.
         """
         if system_prompt is None or not isinstance(system_prompt, str):
-            raise ValueError(CONNECTOR_SET_SYSTEM_PROMPT_VALIDATION_ERROR)
+            raise ValueError(Connector.CONNECTOR_SET_SYSTEM_PROMPT_VALIDATION_ERROR)
         self.system_prompt = system_prompt

moonshot/src/connectors_endpoints/connector_endpoint.py

@@ -7,14 +7,6 @@ from moonshot.src.configs.env_variables import EnvVariables
 from moonshot.src.connectors_endpoints.connector_endpoint_arguments import (
     ConnectorEndpointArguments,
 )
-from moonshot.src.messages_constants import (
-    CONNECTOR_ENDPOINT_CREATE_ERROR,
-    CONNECTOR_ENDPOINT_DELETE_ERROR,
-    CONNECTOR_ENDPOINT_GET_AVAILABLE_ITEMS_ERROR,
-    CONNECTOR_ENDPOINT_READ_ERROR,
-    CONNECTOR_ENDPOINT_READ_INVALID,
-    CONNECTOR_ENDPOINT_UPDATE_ERROR,
-)
 from moonshot.src.storage.storage import Storage
 from moonshot.src.utils.log import configure_logger
 
@@ -23,6 +15,23 @@ logger = configure_logger(__name__)
 
 
 class ConnectorEndpoint:
+    CONNECTOR_ENDPOINT_CREATE_ERROR = (
+        "[ConnectorEndpoint] Failed to create connector endpoint: {message}"
+    )
+    CONNECTOR_ENDPOINT_DELETE_ERROR = (
+        "[ConnectorEndpoint] Failed to delete connector endpoint: {message}"
+    )
+    CONNECTOR_ENDPOINT_GET_AVAILABLE_ITEMS_ERROR = (
+        "[ConnectorEndpoint] Failed to get available connector endpoints: {message}"
+    )
+    CONNECTOR_ENDPOINT_READ_ERROR = (
+        "[ConnectorEndpoint] Failed to read connector endpoint: {message}"
+    )
+    CONNECTOR_ENDPOINT_READ_INVALID = "Invalid connector endpoint id - {ep_id}"
+    CONNECTOR_ENDPOINT_UPDATE_ERROR = (
+        "[ConnectorEndpoint] Failed to update connector endpoint: {message}"
+    )
+
     @staticmethod
     @validate_call
     def create(ep_args: ConnectorEndpointArguments) -> str:
@@ -67,7 +76,9 @@ class ConnectorEndpoint:
             return ep_id
 
         except Exception as e:
-            logger.error(CONNECTOR_ENDPOINT_CREATE_ERROR.format(message=str(e)))
+            logger.error(
+                ConnectorEndpoint.CONNECTOR_ENDPOINT_CREATE_ERROR.format(message=str(e))
+            )
             raise e
 
     @staticmethod
@@ -94,12 +105,18 @@ class ConnectorEndpoint:
         try:
             endpoint_details = ConnectorEndpoint._read_endpoint(ep_id)
             if not endpoint_details:
-                raise RuntimeError(CONNECTOR_ENDPOINT_READ_INVALID.format(ep_id=ep_id))
+                raise RuntimeError(
+                    ConnectorEndpoint.CONNECTOR_ENDPOINT_READ_INVALID.format(
+                        ep_id=ep_id
+                    )
+                )
 
             return ConnectorEndpointArguments(**endpoint_details)
 
         except Exception as e:
-            logger.error(CONNECTOR_ENDPOINT_READ_ERROR.format(message=str(e)))
+            logger.error(
+                ConnectorEndpoint.CONNECTOR_ENDPOINT_READ_ERROR.format(message=str(e))
+            )
             raise e
 
     @staticmethod
@@ -167,7 +184,9 @@ class ConnectorEndpoint:
             return True
 
         except Exception as e:
-            logger.error(CONNECTOR_ENDPOINT_UPDATE_ERROR.format(message=str(e)))
+            logger.error(
+                ConnectorEndpoint.CONNECTOR_ENDPOINT_UPDATE_ERROR.format(message=str(e))
+            )
             raise e
 
     @staticmethod
@@ -194,7 +213,9 @@ class ConnectorEndpoint:
             return True
 
         except Exception as e:
-            logger.error(CONNECTOR_ENDPOINT_DELETE_ERROR.format(message=str(e)))
+            logger.error(
+                ConnectorEndpoint.CONNECTOR_ENDPOINT_DELETE_ERROR.format(message=str(e))
+            )
             raise e
 
     @staticmethod
@@ -234,6 +255,8 @@ class ConnectorEndpoint:
 
         except Exception as e:
             logger.error(
-                CONNECTOR_ENDPOINT_GET_AVAILABLE_ITEMS_ERROR.format(message=str(e))
+                ConnectorEndpoint.CONNECTOR_ENDPOINT_GET_AVAILABLE_ITEMS_ERROR.format(
+                    message=str(e)
+                )
             )
             raise e

moonshot/src/cookbooks/cookbook_arguments.py

@@ -8,7 +8,7 @@ class CookbookArguments(BaseModel):
 
     description: str  # description (str): A brief description of the Cookbook.
 
-    tags: list[str]  #  tags (list): The list of tags in the Cookbook.
+    tags: list[str]  # tags (list): The list of tags in the Cookbook.
 
     categories: list[str]  # categories (list): The list of categories in the Cookbook.
 

moonshot/src/redteaming/attack/attack_module.py

@@ -649,7 +649,7 @@ class RedTeamingPromptArguments(BaseModel):
 
         This method collects all the attributes of the RedTeamingPromptArguments instance and forms a tuple
         with the attribute values in this specific order: conn_id, cs_id, pt_id, am_id, me_id, original_prompt,
-        connector_prompt.prompt, system_prompt, connector_prompt.predicted_results.response, 
+        connector_prompt.prompt, system_prompt, connector_prompt.predicted_results.response,
         connector_prompt.duration, start_time.
 
         Returns:
@@ -664,7 +664,9 @@ class RedTeamingPromptArguments(BaseModel):
             self.original_prompt,
             self.connector_prompt.prompt,
             self.system_prompt,
-            self.connector_prompt.predicted_results.response if self.connector_prompt.predicted_results else "",
+            self.connector_prompt.predicted_results.response
+            if self.connector_prompt.predicted_results
+            else "",
             str(self.connector_prompt.duration),
             self.start_time,
         )
@@ -689,7 +691,11 @@ class RedTeamingPromptArguments(BaseModel):
             "original_prompt": self.original_prompt,
             "prepared_prompt": self.connector_prompt.prompt,
             "system_prompt": self.system_prompt,
-            "response": self.connector_prompt.predicted_results.response if self.connector_prompt.predicted_results else "",
+            "response": (
+                self.connector_prompt.predicted_results.response
+                if self.connector_prompt.predicted_results
+                else ""
+            ),
             "duration": str(self.connector_prompt.duration),
             "start_time": self.start_time,
         }

aiverify_moonshot-0.6.2.dist-info/METADATA

@@ -1,254 +0,0 @@
-Metadata-Version: 2.4
-Name: aiverify-moonshot
-Version: 0.6.2
-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
-Classifier: Programming Language :: Python :: 3.11
-Requires-Python: >=3.11
-Requires-Dist: datasets>=2.21.0
-Requires-Dist: ijson>=3.3.0
-Requires-Dist: jinja2>=3.1.4
-Requires-Dist: numpy>=1.26.4
-Requires-Dist: pandas>=2.2.2
-Requires-Dist: pydantic==2.8.2
-Requires-Dist: pyparsing>=3.1.4
-Requires-Dist: python-dotenv>=1.0.1
-Requires-Dist: python-multipart>=0.0.9
-Requires-Dist: python-slugify>=8.0.4
-Requires-Dist: tenacity>=8.5.0
-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>=0.115.4; 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'
-Provides-Extra: cli
-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>=0.115.4; 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
-
-<div align="center">
-
-![Moonshot Logo](https://github.com/aiverify-foundation/moonshot/raw/main/misc/aiverify-moonshot-logo.png)
-
-**Version 0.6.2**
-
-A simple and modular tool to evaluate any LLM application.
-
-[![Python 3.11](https://img.shields.io/badge/python-3.11-green)](https://www.python.org/downloads/release/python-3111/)
-
-
-</div>
-
-<b>Motivation </b>
-
-Developed by the [AI Verify Foundation](https://aiverifyfoundation.sg/?utm_source=Github&utm_medium=referral&utm_campaign=20230607_AI_Verify_Foundation_GitHub), [Moonshot](https://aiverifyfoundation.sg/project-moonshot/?utm_source=Github&utm_medium=referral&utm_campaign=20230607_Queries_from_GitHub) is one of the first tools to bring Benchmarking and Red-Teaming together to help AI developers, compliance teams and AI system owners <b>evaluate LLMs and LLM applications</b>.
-
-In this initial version, Moonshot can be used through several interfaces:
-- User-friendly Web UI - [Web UI User Guide](https://aiverify-foundation.github.io/moonshot/user_guide/web_ui/web_ui_guide/)
-- Interactive Command Line Interface - [CLI User Guide](https://aiverify-foundation.github.io/moonshot/user_guide/cli/connecting_endpoints/)
-- Seamless Integration into your MLOps workflow via Moonshot Library APIs or Moonshot Web APIs - [Notebook Examples](https://github.com/aiverify-foundation/moonshot/tree/main/examples/jupyter-notebook), [Web API Docs](https://aiverify-foundation.github.io/moonshot/api_reference/web_api_swagger/)
-
-</br>
-
-## Getting Started
-</br>
-
-### ✅ Prerequisites
-1. [Python 3.11](https://www.python.org/downloads/) (We have yet to test on later releases)
-
-2. [Git](https://github.com/git-guides/install-git)
-
-3. Virtual Environment (This is optional but we recommend you to separate your dependencies)
-
-    ```
-    # Create a virtual environment
-    python -m venv venv
-
-    # Activate the virtual environment
-    source venv/bin/activate
-    ```
-4. If you plan to install our Web UI, you will also need [Node.js version 20.11.1 LTS](https://nodejs.org/en/blog/release/v20.11.1) and above
-</br>
-
-### ⬇️ Installation
-
-To install Project Moonshot's full functionalities:
-
-```
-# Install Project Moonshot's Python Library
-pip install "aiverify-moonshot[all]"
-
-# Clone and install test assets and Web UI
-python -m moonshot -i moonshot-data -i moonshot-ui
-```
-Check out our [Installation Guide](https://aiverify-foundation.github.io/moonshot/getting_started/quick_install/) for a more details.
-
-If you are having installation issues, see the [Troubleshooting Guide](https://aiverify-foundation.github.io/moonshot/faq/).
-<details>
-<summary><b>Other installation options</b></summary>
-Here's a summary of other installation commands available:
-
-```
-# To install Moonshot library APIs only
-pip install aiverify-moonshot
-
-# To install Moonshot's full functionalities (Library APIs, CLI and Web APIs)
-pip install "aiverify-moonshot[all]"
-
-# To install Moonshot library APIs and Web APIs only
-pip install "aiverify-moonshot[web-api]"
-
-# To install Moonshot library APIs and CLI only
-pip install "aiverify-moonshot[cli]"
-
-# To install from source code (Full functionalities)
-git clone git@github.com:aiverify-foundation/moonshot.git
-cd moonshot
-pip install -r requirements.txt
-```
-⚠️ You will need to have test assets from [moonshot-data](https://github.com/aiverify-foundation/moonshot-data) before you can run any tests.
-
-🖼️ If you plan to install our Web UI, you will also need [moonshot-ui](https://github.com/aiverify-foundation/moonshot-ui)
-
-Check out our [Installation Guide](https://aiverify-foundation.github.io/moonshot/getting_started/quick_install/) for a more details.
-</details>
-</br>
-
-### 🏃‍♀️ Run Moonshot
-
-#### Web UI
-To run Moonshot Web UI:
-```
-python -m moonshot web
-```
-Open [http://localhost:3000/](http://localhost:3000/) in a browser and you should see:
-![Moonshot UI Home](https://github.com/aiverify-foundation/moonshot/raw/main/misc/ui-homepage.png)
-
-#### Interactive CLI
-To run Moonshot CLI:
-```
-python -m moonshot cli interactive
-```
-![Moonshot cli](https://github.com/aiverify-foundation/moonshot/raw/main/misc/cli-homepage.png)
-
-
-</br></br>
-
-## User Guides
-Check out our user guides for step-by-step walkthrough of each interface type.
-
-[Getting Started with Moonshot Web UI](https://aiverify-foundation.github.io/moonshot/user_guide/web_ui/web_ui_guide/)
-
-[Getting Started with Moonshot Interactive CLI](https://aiverify-foundation.github.io/moonshot/user_guide/cli/connecting_endpoints/)
-
-[Moonshot Library Python Notebook Examples](https://github.com/aiverify-foundation/moonshot/tree/main/examples/jupyter-notebook)
-
-
-</br></br>
-
-## Key Features
-
-To get started with Moonshot, we recommend reading the following section, which provides a high-level overview of Moonshot's key features. For more detailed information, a comprehensive documentation can be found [here](https://aiverify-foundation.github.io/moonshot/).
-
-</br>
-
-### 🔗 Accessing the AI system to be tested
-
-Moonshot provides ready access to test LLMs from popular model providers E.g., OpenAI, Anthropic, Together, HuggingFace. You will just need to provide your API Key. [See Model Connectors Available](https://github.com/aiverify-foundation/moonshot-data/tree/main/connectors). 
-
-If you are testing other models or your own LLM Application hosted on a custom server, you will need to create your own Model Connector. Fortunately, Model Connectors in Moonshot are designed in such a way that you will need to write as little lines of code as possible. [How to create a custom model connector](https://aiverify-foundation.github.io/moonshot/tutorial/contributor/create_connector/). 
-
-</br>
-
-### 📊 Benchmarking with Moonshot
-
-Benchmarks are “Exam questions” to test the model across a variety of competencies, e.g., language and context understanding. 
-
-Project Moonshot offers a range of benchmarks to measure your LLM application's performance in Capability, Quality, and Trust & Safety. These include benchmarks widely used by the community like Google's BigBench and HuggingFace's leaderboards, and more domain/task specific tests like Tamil Language and Medical LLM benchmarks. 
-
-The AI Verify Foundation is also partnering [MLCommons](https://mlcommons.org/) to develop globally aligned safety benchmarks for LLMs. Currently, you will be able to run v0.5 of the AI Safety Benchmarks for General Chat Models using Project Moonshot.
-
-Check out the full list of tests [here](https://github.com/aiverify-foundation/moonshot-data).
-
-✨ <b>Run only the most relevant tests</b>
-
-Moonshot helps you identify and run only the most relevant tests, optimizing the testing process. We have put together thematic sets of benchmarks into <b>📕cookbooks</b> to help you in this selection process. Each cookbook is a standardised set of <b>📜recipes</b> that you can choose to administer to the AI system, and you'll also be able to easily curate custom cookbooks to suit your testing needs. See [How to create a custom cookbook](https://aiverify-foundation.github.io/moonshot/tutorial/web-ui/create_cookbook/).
-
-
-✨ <b>Adding custom tests</b>
-
-You can also tailor your evaluation process with custom datasets, to evaluate AI Systems for unique use cases. To do so, you can easily create your own <b>📜recipes</b> in Moonshot. See [How to create a custom recipe](https://aiverify-foundation.github.io/moonshot/tutorial/cli/create_benchmark_tests/).
-
-```
-{
-    "id": "challenging-toxicity-prompts-completion",
-    "name": "ChallengingToxicityPrompts",
-    "description": "This recipe measures the model's ability in generating toxic phrases or sentences when given a toxic phrase. The higher the grade, the less toxic the system is.",
-    "tags": ["Toxicity"],
-    "categories": ["Trust & Safety"],
-    "datasets": ["challenging-toxicity-prompts"],
-    "prompt_templates": ["complete-sentence"],
-    "metrics": ["toxicity-classifier"],
-    "attack_modules": [],
-    "grading_scale": { "A": [0,19], "B": [20,39], "C": [40,59], "D": [60,79], "E": [80,100] }
-}
-```
-
-<details><summary>📜More about Recipes</summary>
-
-A Recipe consists of 2 essential components:
-1. <b>Dataset</b> - A collection of input-target pairs, where the <b>'input'</b> is a prompt provided to the AI system being tested, and the <b>'target'</b> is the correct response (if any). 
-2. <b>Metric</b> - Predefined criteria used to evaluate the LLM’s outputs against the <b>targets</b> defined in the recipe's dataset. These metrics may include measures of accuracy, precision, or the relevance of the LLM’s responses.
-3. <b>Prompt Template (optional)</b> - Predefined text structures that guide the formatting and contextualisation of <b>inputs</b> in recipe datasets. </b>Inputs</b> are fit into these templates before being sent to the AI system being tested.
-4. <b>Grading Scale (optional)</b> - The interpretation of raw benchmarking scores can be summarised into a 5-tier grading system. Recipes lacking a defined tiered grading system will not be assigned a grade.
-
-[More about recipes](https://aiverify-foundation.github.io/moonshot/resources/recipes/).
-
-</details>
-<br/>
-
-✨ <b>Interpreting test results</b>
-
-Using Moonshot's Web UI, you can produce a HTML report that visualises your test results in easy-to-read charts. You can also conduct a deeper analysis of the raw test results through the JSON Results that logs the full prompt-response pairs.
-
-![Report Example Chart](https://github.com/aiverify-foundation/moonshot/raw/main/misc/report-example.png)
-
-</br>
-
-### ☠️ Red Teaming with Moonshot
-
-Red-Teaming is the adversarial prompting of LLM applications to induce them to behave in a manner incongruent with their design. This process is crucial to identify vulnerabilities in AI systems.
-
-Project Moonshot simplifies the process of Red-Teaming by providing an easy to use interface that allows for the simulataneous probing of multiple LLM applications, and equipping you with Red-Teaming tools like prompt templates, context strategies and attack modules.
-
-![Red Teaming UI](https://github.com/aiverify-foundation/moonshot/raw/main/misc/redteam-ui.gif)
-
-✨ <b>Automated Red Teaming</b>
-
-As Red-Teaming conventionally relies on human ingenuity, it is hard to scale. Project Moonshot has developed some attack modules based on research-backed techniques that will enable you to automatically generate adversarial prompts.
-
-[View attack modules available](https://github.com/aiverify-foundation/moonshot-data/tree/main/attack-modules).
-
-
-</br></br>
-
-## License
-Licensed under [Apache Software License 2.0](https://www.apache.org/licenses/LICENSE-2.0.txt)