Themeisle Docs

Appearance

Hyve - Settings Reference ​

Hyve is an AI-powered chatbot that turns your WordPress content into interactive conversations with your site visitors. You can find all Hyve settings by navigating to the Hyve menu item in your WordPress admin sidebar.

Dashboard ​

The Dashboard is the first screen you see when you open Hyve. It shows usage statistics and provides quick access to other areas of the plugin.

Enable Chat on all the pages ​

When enabled, the chatbot widget appears on every page of your site. When disabled, the chatbot does not appear anywhere unless you place the Hyve Gutenberg Block on specific pages. You would disable this if you only want the chatbot on certain pages rather than site-wide. The chatbot will not appear on the frontend unless you have also entered an OpenAI API key and added at least one piece of content to the Knowledge Base.

Knowledge Base ​

The Knowledge Base is where you manage the content that powers the chatbot's responses. Content is broken into chunks and stored as embeddings so the chatbot can search for relevant answers. Without Qdrant connected, the Knowledge Base has a limit of 500 chunks.

Knowledge Base ​

This is the main view where you can browse, add, and remove content from the chatbot's data source. You can add WordPress posts and pages individually or in bulk. Each piece of content goes through OpenAI's moderation check before being added.

Requires Update ​

Lists any posts or pages in the Knowledge Base whose content has changed since they were last processed. You should re-process these items so the chatbot has up-to-date information.

Failed Moderation ​

Shows content that was flagged by OpenAI's moderation system during processing. If you believe the flag is a false positive, you can review the content and override the moderation decision to add it to the Knowledge Base anyway.

FAQ ​

Tracks questions that users ask the chatbot which it was unable to answer. This helps you identify gaps in your Knowledge Base so you can add content to cover those topics. This feature is available with Hyve Pro.

Data Sources ​

You can add content to the Knowledge Base from several sources. WordPress posts and pages are available in the free version. The following additional sources are available with Hyve Pro:

  • Custom Data lets you manually write and add information that does not exist as a WordPress post or page, such as FAQs or policy details.
  • Website URL lets you enter a URL and crawl its content to add to the Knowledge Base, useful for importing content from external sites or pages not managed by WordPress.
  • Sitemap lets you provide a sitemap URL to crawl and import multiple pages at once, making it easy to add large amounts of content in a single operation.

Options ​

Cosine Similarity Threshold ​

Controls how closely a user's question must match your Knowledge Base content for the chatbot to consider it a relevant answer. The value ranges from -1 to 1, with a default of 0.4. A higher value means the chatbot only returns answers that are very closely related to the question, which reduces irrelevant responses but may cause it to miss valid answers. A lower value broadens the search, returning more results but potentially including less precise matches. Adjust this if users report that the chatbot is not finding answers it should know, or if it is returning unrelated content.

Messages ​

Displays a history of all conversations between the chatbot and your site visitors. You can browse conversation threads, view individual messages, and delete threads you no longer need.

In the free version, you can view the most recent conversations but loading additional message history and exporting messages require Hyve Pro.

Integrations ​

Qdrant ​

Qdrant is an external vector database service that removes the 500-chunk Knowledge Base limit and can improve search performance for large datasets.

API Key ​

The API key from your Qdrant Cloud account. You need this along with the API Endpoint to connect Hyve to your Qdrant instance. You can obtain this from the Qdrant Cloud dashboard.

API Endpoint ​

The URL of your Qdrant instance. Enter the full endpoint URL provided by Qdrant Cloud. Once both the API Key and API Endpoint are saved, Hyve attempts to connect and begins migrating your existing Knowledge Base data to Qdrant. If you later disconnect Qdrant, all data stored in Qdrant for this site is deleted and any Knowledge Base entries exceeding the 500-chunk limit are removed.

Hyve Connect ​

This tab is available with Hyve Pro.

Hyve Connect lets external services search your Knowledge Base through a secure REST API endpoint using semantic search powered by Retrieval-Augmented Generation and OpenAI embeddings. You can integrate automation tools like Zapier or n8n to perform intelligent content searches from outside your WordPress site.

Access Tokens ​

Manage the API tokens that authorize external services to search your Knowledge Base. You can generate new tokens, reveal or hide token values, copy tokens to the clipboard, and delete tokens you no longer need. Each token grants bearer-style access to the search endpoint. Deleting a token immediately revokes access for any application using it. This feature is available with Hyve Pro.

Settings ​

General ​

Enable "Add to Hyve" Post Action ​

When enabled, an "Add to Hyve" button appears in the row actions beneath each post and page in your WordPress posts and pages lists. This gives you a quick way to add individual pieces of content to the Knowledge Base without navigating to the Hyve settings. Disable this if you find the extra action clutters your posts list or if you prefer to manage the Knowledge Base exclusively from within the Hyve interface.

Welcome Message ​

The greeting message displayed to visitors when they first open the chatbot. Use this to set the tone for the conversation and let visitors know what the chatbot can help with. If left empty, the chatbot displays a default greeting.

Default Message ​

The fallback message the chatbot returns when it cannot find a relevant answer in the Knowledge Base. Use this to guide visitors toward other support channels or suggest they rephrase their question. If left empty, the chatbot uses a built-in default response.

Suggested Questions ​

Up to three pre-written questions displayed in the chat window to help visitors start a conversation. These appear as clickable prompts, making it easier for visitors to engage with the chatbot without having to think of a question. This is useful for highlighting your most common topics or drawing attention to specific content. This feature is available with Hyve Pro.

Appearance ​

This tab is available with Hyve Pro. In the free version, the tab is visible but all controls are inactive.

Chat Icons ​

Choose the icon style for the chatbot's floating button. Six bubble-style icons are available: Chat Bubble Left Ellipsis (default), Chat Bubble Oval Left, Chat Bubble Bottom Center Text, Chat Bubble Bottom Center, Chat Bubble Left, and Chat Bubble Left Right. Pick the style that best fits your site's design.

Chat Background ​

Sets the background color of the chat window where conversations are displayed. The default is white (#ffffff).

Assistant Background ​

Sets the background color of the chatbot's message bubbles. The default is a light blue (#ecf1fb). Choose a color that contrasts well with the chat background so messages are easy to read.

User Background ​

Sets the background color of the visitor's message bubbles. The default is blue (#1155cc). This should contrast with the chat background and be visually distinct from the assistant's message color.

Icon Background ​

Sets the background color of the floating chat icon button that visitors click to open the chatbot. The default is blue (#1155cc). Choose a color that stands out against your site's design so visitors can easily find the chat.

Assistant ​

This tab is accessible once an OpenAI API key has been saved.

Model ​

Choose the AI model that powers the chatbot's responses. More capable models produce higher-quality answers but cost more per request on your OpenAI account. The available options are:

  • GPT-4.1 is the most accurate and capable model, ideal for complex questions that require nuanced understanding.
  • GPT-4.1 mini is faster and cheaper than GPT-4.1 while still delivering strong response quality, a good balance of cost and capability.
  • GPT-4.1 nano is ultra-fast and the lowest cost option, best for lightweight conversations or high-traffic sites where speed and budget matter most.
  • GPT-4o is fast, smart, and cost-effective, suitable for most use cases.
  • GPT-4o mini is optimized for real-time conversations with faster response times and lower cost than GPT-4o. This is the default model.
  • GPT-3.5 Turbo 0125 is a legacy model suitable for basic tasks. Consider using a newer model for better results.

Temperature ​

Controls how creative or predictable the chatbot's responses are, on a scale from 0.1 to 2. The default is 1. Lower values like 0.2 make responses more focused and consistent, which is useful for factual or support-oriented chatbots. Higher values like 1.5 make responses more varied and creative. OpenAI recommends adjusting either Temperature or Top P, but not both at the same time, as changing both can produce unpredictable results.

Top P ​

An alternative to Temperature for controlling response variety, using a technique called nucleus sampling. The value ranges from 0.1 to 1, with a default of 1. A value of 0.1 means the model only considers the top 10% most likely words when generating a response, producing very focused output. A value of 1 considers all possibilities. OpenAI recommends adjusting either this or Temperature, but not both at the same time.

Moderation ​

This tab is accessible once an OpenAI API key has been saved.

Moderation settings control the sensitivity of content filtering applied to Knowledge Base content during processing. Each category has a threshold slider ranging from 0 to 1. A lower threshold means stricter filtering, where content is flagged more easily. A higher threshold means more lenient filtering, allowing more content through. OpenAI's moderation system can occasionally produce false positives, so you may need to adjust these thresholds if legitimate content is being incorrectly flagged.

Hate Speech ​

Filters content that expresses, incites, or promotes hate based on race, gender, ethnicity, religion, nationality, sexual orientation, disability status, or caste. The default threshold is 0.7.

Hate Speech/Threatening ​

Filters hateful content that also includes violence or serious harm towards a targeted group based on protected characteristics. The default threshold is 0.6, which is stricter than the general Hate Speech setting because the combination of hate and threats is considered more severe.

Harassment ​

Filters content that expresses, incites, or promotes harassing language towards any target. The default threshold is 0.7.

Harassment/Threatening ​

Filters harassment content that also includes violence or serious harm towards any target. The default threshold is 0.6.

Self-Harm ​

Filters content that promotes, encourages, or depicts acts of self-harm, such as suicide, cutting, and eating disorders. The default threshold is 0.5.

Self-Harm with Intent ​

Filters content where the speaker expresses that they are engaging or intend to engage in acts of self-harm. The default threshold is 0.5.

Self-Harm Instructions ​

Filters content that encourages performing acts of self-harm or gives instructions on how to do so. The default threshold is 0.5.

Sexual Content ​

Filters content meant to arouse sexual excitement or that promotes sexual services, excluding sex education and wellness content. The default threshold is 0.8, which is more lenient than most other categories to reduce false positives on educational or health-related content.

Sexual Content Involving Minors ​

Filters sexual content that includes an individual who is under 18 years old. The default threshold is 0.5, which is stricter than the general Sexual Content threshold given the severity of this category.

Violence ​

Filters content that depicts death, violence, or physical injury. The default threshold is 0.7.

Graphic Violence ​

Filters content that depicts death, violence, or physical injury in graphic detail. The default threshold is 0.8.

Advanced ​

OpenAI API Key ​

Your OpenAI API key, required for the plugin to function. Without this key, the chatbot cannot generate responses, process content for the Knowledge Base, or perform moderation checks. You can get an API key from OpenAI's platform. Once saved, the rest of the plugin's features become accessible. Usage of the chatbot and content processing counts against your OpenAI account's API usage and billing.

License ​

This section appears in Hyve Pro only.

Enter your license key from your ThemeIsle purchase history to receive plugin updates for Hyve Pro. Once activated, the license status and expiration date are displayed. If the license expires, you can renew it to continue receiving updates and support. You can also deactivate the license if you want to transfer it to a different site.