DOCSEARCHbyAlgolia
Submit Docs

AI Puffer Documentation

website·Indexed 35 days ago

https://docs.aipower.org

A WordPress plugin that integrates AI tools for content generation, chatbots, and image creation. Features include a Knowledge Base with vector store support (OpenAI, Pinecone, Qdrant, Chroma), AI-powered forms, automated content rewriting via CSV or RSS, and REST API endpoints for external application integration.

Tokens
37.7K
Snippets
72
Records
261
Agent score
72%

What's inside AI Puffer

  1. Overview of AI Puffer for WordPress

    AI Puffer is a WordPress plugin that integrates AI tools into the website and admin area. It allows users to connect their own AI provider keys and assign specific models to different features. AI tools are accessible via WordPress pages, shortcodes, blocks, products, and scheduled tasks. Supported providers include OpenAI, Google, Azure, OpenRouter, xAI, DeepSeek, Ollama, Anthropic, ElevenLabs, Replicate, Pinecone, Qdrant, and Chroma.

  2. Overview of AI Puffer Provider Model

    AI Puffer operates on a 'bring-your-own-key' model. Users must provide their own API credentials and manage billing directly with the chosen AI provider (e.g., OpenAI, Google, Anthropic). AI Puffer Pro provides additional plugin features, but does not include API credits.

  3. Overview of AI Puffer Automations

    AI Puffer Automations allow users to create content, rewrite published WordPress content, maintain a knowledge base, or reply to comments in the background. Automations are managed in the WordPress admin under AI Puffer > Automations. Before creating an automation, ensure that the required AI provider, image provider, vector store, or source connections are configured. If the menu is missing, verify access in AI Puffer > Settings > Modules.

  4. Overview of AI Puffer Usage and Credits

    The Usage section in the WordPress admin (AI Puffer > Usage) allows administrators to review AI activity and manage internal credits.

    Key Concepts:

    • Credit: An internal AI Puffer unit stored on a logged-in user's account.
    • Balance: The user's available prepaid credits.
    • Quota: A periodic usage limit for guests, users, or roles.
    • Pricing rule: A rule that converts model usage (tokens, images, etc.) into credits.
    • Ledger: A record of purchases, admin balance changes, and usage.

    Important Note: AI Puffer credits are internal to the plugin. They do not replace the billing of external providers (e.g., OpenAI, Google, Anthropic, xAI, Replicate); those providers still bill your connected API account separately.

  5. Overview of AI Puffer Knowledge Base

    The Knowledge Base stores source content that AI Puffer searches to provide context before generating answers or content. It is used for support answers, product details, documentation, policies, and uploaded documents. It supports multiple vector store providers and embedding models to enable semantic search.

  6. Overview of AI Puffer Image and Video Generation

    AI Puffer adds a frontend generator to WordPress pages, allowing visitors to enter prompts and receive generated media. It supports image generation, image editing, Google video generation, and maintains a history for logged-in users. Management is handled via the AI Puffer > Images menu in the WordPress admin, with a dedicated Image Generator tab for publishing and a Settings tab for limits, UI text, and CSS.

  7. Consume Chatbot Event Data

    When processing chatbot.session_started or chatbot.user_message_submitted events, the data object contains details about the bot, the conversation, and the user.

    Chatbot Data Fields

    • data.bot.id: Chatbot ID
    • data.bot.name: Chatbot name
    • data.conversation.id: Conversation UUID
    • data.conversation.message_count: Total messages in conversation
    • data.actor.type: Either user or guest
    • data.actor.user_id: WordPress user ID (if available)
    • data.message.text: The text of the user's message
    • data.ai.provider: AI provider used
    • data.ai.model: AI model used

    Note: chatbot.response_generated provides data.response.text, and chatbot.fb_submitted provides data.feedback.

  8. Understand Smart SEO rules for All in One SEO (AIOSEO)

    When using the All in One SEO profile, Smart SEO evaluates content based on the following criteria:

    • Focus Keyword: Must be present in the content, introduction (first paragraph), meta description, image alt text, and in 30%-75% of H2/H3 subheadings. Length should be 1-4 words.
    • Meta Description: Target length is 121-160 characters.
    • Content: Must be over 300 words; should include internal and external links.
    • SEO Title: Focus keyword should be near the beginning; target length is 41-60 characters.
    • Readability: Aims for a 70+ headline score, Flesch reading ease of 63+, passive voice $\le$ 10%, and at least 30% transition words. Avoid 4+ consecutive sentences starting with the same word.
    • Structure: Long sections must be separated by subheadings; content should include rich media (images/videos).

  9. Enable and configure Image Analysis in chatbots

    Image analysis allows visitors to upload an image (up to 20 MB) and ask the chatbot questions about it. This feature uses the chatbot's primary selected provider and model. If the option is missing, ensure you have selected a vision-capable model and synced your models.

    Provider Support:

    • Supported: OpenAI, Anthropic, xAI (JPG/JPEG, PNG), OpenRouter (model-dependent), Ollama (model-dependent).
    • Not Supported: Google, Azure, DeepSeek.

    Setup Steps:

    1. Go to AI Puffer > Chatbots and select your chatbot.
    2. Select a supported provider and vision-capable model.
    3. Navigate to Chatbot settings > Conversation > Capabilities.
    4. Enable Image analysis and save the chatbot.

  10. AI Puffer REST API Endpoint Overview

    AI Puffer exposes several REST endpoints under the base URL: https://your-site.com/wp-json/aipkit/v1.

    EndpointMethodUse
    /generatePOSTGenerate text with a configured AI provider.
    /images/generatePOSTGenerate images.
    /embeddingsPOSTCreate embeddings from text.
    /chat/{bot_id}/messagePOSTSend a message to a chatbot.
    /logsGETRead saved chat logs.
    /vector-stores/upsertPOSTEmbed text and upsert it into Pinecone, Qdrant, or Chroma.
    /chatbots/{bot_id}/embed-configGETRead embed config and HTML for an external chatbot widget.

  11. Manage user credit balances and reset usage

    Admin can manage logged-in WordPress users' credits via AI Puffer > Usage > Billing > Balances.

    To edit a balance:

    1. Search for the user.
    2. Edit the Credit Balance field.
    3. Press Enter or click outside the field. The difference is recorded as an admin adjustment in the ledger.

    To reset usage:

    1. Click Details for a user.
    2. Click Reset usage for a specific scope, or Reset all for all scopes.
    3. Confirm the reset. Note: Resetting usage does not change the user's credit balance.

  12. Generate content from RSS Feeds

    Use the RSS Feed option to create content based on feed items. You can provide multiple feed URLs (one per line) and use 'Include' or 'Exclude' keywords to filter which titles are processed. AI Puffer checks up to 15 items per feed and maintains a history to prevent duplicate queuing of the same item.