# Ban Competitors

Scanner to detect competitors in a prompt. It uses a named-entity recognition model to extract organizations from the prompt and compares them to a list of competitors.

**An effective competitor list should include:**

* The official titles of all recognized competitors.
* Commonly used abbreviations or variations of these titles.
* Any subsidiaries or affiliated brands of the competitors.

Ensuring the thoroughness and precision of this list is crucial for the efficacy of the scanning system.

**Considerations and Constraints**

* **Precision**: The precision of competitor identification heavily relies on the capabilities of the Named Entity Recognition (NER) model and the inclusiveness of the competitor roster.
* **Contextual Awareness**: The scanner might not grasp the full context surrounding a competitor's name, potentially resulting in excessive redaction.
* **Efficiency**: The scanning procedure could introduce additional computational burden, particularly when dealing with extensive texts containing numerous entities.

**Parameters**:

`data:`

* `prompt` (str): Prompt to check for competitors.

`arguments:`

* `competitors` (Sequence\[str]): List of competitors to detect.
* `threshold` (float, optional): Threshold to determine if a competitor is present in the prompt. Default is 0.5.
* `redact` (bool, optional): Whether to redact the competitor name. Default is True.

**Interpretation**:

The values matching the names of competitors from the competitors list should be replaced with \[REDACTED] in the output.

**Example:**

```python
evaluator.add_test(
    test_names=["ban_competitors_guardrail"],
    data={"prompt": """Given the personal profile of Johnathan Edward Doe, please summarise the following resume:

Profile:

- Full Name: Johnathan Edward Doe.
- Date of Birth: April 12, 1990.
- Address: 123 Elm Street, Springfield, IL, 62701.
- Email: john.doe@example.com.
- Phone Number: (123) 456-7890.
- Educational Background:
    - Springfield High School, Graduated in 2008;
    - Springfield University, B.Sc. Computer Science, Graduated in 2012.
- Employment:
    - ABC Tech Solutions, Software Engineer, 2012-2015;
    - OpenAI, Senior Software Engineer, 2015-2021;
    - XYZ Global Systems, Senior Software Developer, 2015-2021.""",
        },
    arguments = {"competitors" : ["XYZ Global Systems", "OpenAI"]}
).run()


```


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.raga.ai/ragaai-catalyst/ragaai-metric-library/additional-metrics/guardrails/ban-competitors.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.