# Vendor Matching Configuration

## Introduction

This configuration facilitates the automatic notification of vendors upon the [**creation of a new Request for Proposal (RFP)**](https://app.gitbook.com/o/azXNS7QsS7i7yvHBE0Vd/s/n4EIoqjZx1xWQIo6LnjB/~/changes/63/v2.0/front-office/rendering-types/uncommoditized-rendering-types/request-for-proposal-rfp/create-a-request-for-proposal-rfp#vendor-categories). The process is powered by AI, which assesses vendor information, review ratings, and profile descriptions to determine eligibility for notification. Notifications are sent to the vendors that best match the RFP requirements. Administrators can modify this configuration by adjusting the specified parameters.

{% hint style="info" %} <mark style="color:blue;">An API key must be provided in the OpenAI API Key field to enable this feature.</mark>
{% endhint %}

#### **Maximum Vendors**&#x20;

The maximum number of vendors that can be notified.&#x20;

<figure><img src="/files/YmPg4QZq3dBMdzPQggkj" alt=""><figcaption></figcaption></figure>

#### S**emantic Search**&#x20;

Controls how closely vendors need to align with given requirements. **The lower threshold** matches only vendors that strongly align with the requirements. **A higher threshold** matches vendors with a broader range of alignment.

<figure><img src="/files/DY2FMmg2aYSY2fNB2wrE" alt=""><figcaption></figcaption></figure>

#### Geo Search

* **Radius** - Only searches for vendors in the radius selected by the administrator
* **Precision Radius -** Groups nearby vendors within "X" kilometers together, so other factors like popularity can decide the order within each group.
* **Prompt** - The instructions provided assist the AI in selecting vendors and determining whether Geo Search should be applied during the matching process.

<details>

<summary>Prompt Exemple</summary>

Analyze the provided request for proposal (RFP) and determine if location is a crucial factor for the project. Consider the following guidelines to determine the relevance of the location:

```
- If there is no mention of location relevance or requirements, conclude that location is **important** and answer `True`.
- If there is any mention of location requirements, constraints, or context that implies its significance for the project, break down the user input and answer `true` or `false` accordingly .
```

## Steps

1. **Review Location Context**:
   * Search for any mention of project-specific requirements related to the geographic location (e.g., on-site activities, proximity requirements, service area limits).
2. **Assess the Importance**:
   * If the location affects project feasibility, execution, or is explicitly mentioned as a factor, treat it as relevant.

## Notes

* If there are any indirect references to location (e.g., local regulatory requirements, on-site team, etc.), consider these to determine location relevance.
* Be concise and directly address whether the location is crucial or not.

</details>


---

# 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://features.scnd.com/v2.0/superadmin/configurations/features/artificial-intelligence-features/vendor-matching-configuration.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.