How the Chat with PDF Intent Works

When a user provides a valid URL to a PDF file, the chatbot processes the document by splitting it into pages and creating vector embeddings for each page. These embeddings allow the chatbot to compare the user’s query with the content of the PDF and retrieve the most relevant information, ensuring accurate answers. If multiple pages are relevant, the chatbot includes the surrounding pages to provide full context.

This feature is ideal for scenarios such as answering questions about product catalogs, user manuals, or detailed reports. By using embeddings, the chatbot can respond to specific inquiries without needing to process the entire document repeatedly.

Example Key Phrases for Chat with PDF Intent

Here are some example key phrases that a website owner might configure to trigger the Chat with PDF intent:

process this PDF, analyze this PDF, read this document, process the file, check this PDF link

These phrases can be configured in the chatbot’s intent settings. When users provide queries similar to these, the chatbot will detect their intent to process a PDF and guide them accordingly.

Example of Asking Questions About the PDF

Once the PDF is processed, users can ask questions about its content. For instance:

What does page 5 of the document cover?
Who is mentioned in the acknowledgments section?

The chatbot will search the content of the PDF and return answers based on the user’s query, using the embeddings to pinpoint the relevant sections.

Important Notes

• The PDF URL must be publicly accessible and use the HTTPS protocol.
• Only text-based PDFs are supported; image-based PDFs without OCR will not provide usable content.
• The chatbot processes one PDF per session. If a new PDF URL is provided, it will replace the previous one.

How to Set Up Email Capture with Loops

Follow these steps to configure the Email Capture intent:

1. Enter your Loops API Key: In the Loops Settings section, paste your Loops API key and click “Save.”
2. Select a Mailing List: After saving your API key, refresh the page, and you’ll see an option to select a mailing list from your Loops account. Choose the list where you’d like to store collected email addresses.
3. Configure Triggered Phrase Response: This is the automatic response the chatbot will give when it detects a trigger phrase. For example, you might set it to: “I’ve got a discount offer for you! Just drop your email, and I’ll send over the code!”
4. Configure Email Capture Response: This is the chatbot’s follow-up message after a user has provided their email address. For instance, it could be: “Thanks! Your discount code is on its way to your inbox. Anything else I can help you with?”

Once these settings are configured, the chatbot will be able to detect specific trigger phrases and respond accordingly, guiding users to submit their email addresses.

Example Key Phrases for Email Capture Intents

Here are some example key phrases that you might set up to trigger the Email Capture intent. These examples show two different use cases: a discount code and a newsletter sign-up.

1. Coupon Code Offer

discount code, get a discount, send me a coupon, I want a coupon, how do I get a discount

In this example, if a user mentions any of these phrases, the chatbot will respond with the Triggered Phrase Response, encouraging them to submit their email to receive a discount code.

2. Newsletter Sign-Up

sign me up for the newsletter, subscribe me, I want to join the mailing list, newsletter subscription, email updates

Here, if a user expresses interest in signing up for a newsletter, the chatbot will prompt them to submit their email and will respond with the Email Capture Response once their email is received.

How the Show Product Card Intent Works

When a user mentions a product by name, the chatbot attempts to identify the product based on their message. If the product is found, the chatbot will display a product card that includes:

• Product Image: A thumbnail image of the product, making it easy for users to recognize.
• Product Name: The name of the product as listed in WooCommerce.
• Product Price: The current price of the product, shown directly on the card.
• Add to Cart Button: A button that allows users to add the product to their cart directly from the chat, creating a seamless shopping experience.

If a user asks follow-up questions about a product they recently inquired about, the chatbot can remember the last discussed product and continue to display its information, providing a smooth, continuous interaction.

Example Key Phrases for Product Inquiries

Below are some example phrases that could trigger the Show Product Card intent. These examples help the chatbot recognize when a user is asking about a specific product:

show me the product, tell me about the product, what is the price of MxChat, what features does MxChat have, product details for MxChat

In these examples, if the chatbot detects a specific product name within the phrase, it will display the product card with the details for that product. This feature enhances user engagement and supports quick shopping actions within the chat.

How the Order History Intent Works

When a user asks about their previous orders, the chatbot checks if they are logged in to retrieve the necessary details. Based on the user’s query, the chatbot can either show the most recent order or provide a summary of all past orders. The order information displayed includes:

• Order Number: A unique identifier for each order.
• Order Date: The date the order was placed.
• Order Status: The current status of the order (e.g., completed, pending).
• Total Amount: The total cost of the order.
• Items Ordered: A list of items in the order.

If the user is not logged in, the chatbot will prompt them to log in to access their order history.

Example Key Phrases for Order History

Below are some example phrases that users can say to view their order history:

order history, last order, recent orders, view my orders, what did I order last time

These phrases trigger the chatbot to fetch and display order details, providing users with a quick and convenient way to check their past orders directly within the chat.

How the Generate Image Intent Works

When a user provides a description, such as “generate an image of a sunset over the ocean,” the chatbot sends this prompt to OpenAI’s DALL-E image generation model. The AI then creates an image that reflects the request, returning it within the chat as a visual response. The image card includes:

• Generated Image: An AI-generated image based on the user’s description.
• Customizable Prompt: The chatbot can understand a variety of descriptive prompts, allowing users to get creative with their requests.

If the AI cannot generate an image based on the request, the chatbot will inform the user with a fallback message.

Example Key Phrases for Image Generation

Here are some example phrases users can use to trigger image generation. These phrases allow the chatbot to recognize when a user is requesting an image:

generate an image of a sunset, create a picture of a forest, draw a city skyline, show me an image of a mountain, make an image of a futuristic city

In these examples, the chatbot interprets the user’s description and generates a unique image that aligns with the requested theme or scene.

Brave Search API Key Requirement

To enable this feature, you’ll need an API key from Brave. You can sign up for an API key at the Brave Search API page. Once you have your key, enter it in the Brave Search Settings in the MxChat plugin configuration to allow the chatbot to retrieve search results.

How the Brave Web Search Intent Works

When a user requests information, the chatbot identifies key terms in the message, such as “search the web for” or “news about,” to detect that a web search is needed. Based on the user’s request, the chatbot can perform:

• General Web Search: The chatbot retrieves general web results that are relevant to the user’s query, displaying titles, URLs, descriptions, and source information.
• News Search: If the query includes terms like “news,” the chatbot specifically searches for recent news articles, providing a summary with article titles, publication dates, descriptions, and sources.

If no query is provided, or if the chatbot cannot find relevant information, it will prompt the user to refine their search or notify them that results are unavailable.

Example Key Phrases for Brave Web Search

Here are some example phrases that users might use to trigger a Brave Web Search:

search the web for AI advancements, show me the latest news about technology, what’s the news in New York, news about climate change, find articles on health tips

These phrases prompt the chatbot to fetch and display relevant information from Brave’s search engine, helping users quickly access web or news content directly within the chat.

How the Brave Image Search Intent Works

When a user requests an image, the chatbot first processes the user’s message through a predefined model from OpenAI. This model helps interpret the user’s query by identifying the essential keywords needed for the image search, removing any unnecessary words or phrases. For example, if a user asks, “Could you find me an image of a beach at sunset?”, the model simplifies the request to focus on the key terms, such as “beach sunset.”

The refined search query is then sent to Brave’s image search API, which returns a set of images matching the request. The chatbot displays these images in a gallery format within the chat, including:

• Image Thumbnail: A clickable thumbnail that opens the full image in a new tab.
• Image Title: A short description or title of the image, if available.

If the chatbot cannot find relevant images, it prompts the user to provide a more specific query or notifies them that no results were found.

Example Key Phrases for Brave Image Search

Here are some example phrases that users might use to trigger an image search:

find an image of a mountain, show me a picture of a forest, search for images of modern architecture, I want to see photos of the ocean, look up images of cute animals

These phrases prompt the chatbot to interpret the key terms and retrieve relevant images, allowing users to easily view visual content based on their interests.

How the Add to Cart Intent Works

When a user expresses interest in adding a product to their cart, the chatbot will check if there is a “last discussed product” in the conversation. This feature remembers the last product that was mentioned, so users can add it to their cart simply by saying something like “add to cart” without repeating the product name.

If the product is successfully added to the cart, the chatbot will confirm with a message, such as “The product has been added to your cart.” The chatbot will also prompt the user to proceed to checkout if desired. If no recent product is identified, the chatbot will prompt the user to specify the product they’d like to add.

Example Key Phrases for Adding to Cart

Here are some example phrases users might say to add a product to their cart:

add to cart, put this in my cart, I want to buy this, add this product to my cart, include this in my cart

In these examples, the chatbot will detect the intent to add a product and confirm once it has been added to the cart, making the shopping process quick and convenient.

How the Proceed to Checkout Intent Works

Once a user has added items to their cart, they can ask the chatbot to proceed to checkout. If there is an active checkout prompt and items in the cart, the chatbot will provide a link to the checkout page, allowing the user to complete their purchase immediately. If no items are in the cart, the chatbot will prompt the user to add items first.

This intent is useful for creating a smooth, end-to-end shopping experience by guiding users from product selection to checkout within the chat interface.

Example Key Phrases for Proceeding to Checkout

Here are some example phrases that users might say to go to the checkout page:

proceed to checkout, checkout now, I’m ready to checkout, go to checkout, let’s finish my order

Using these phrases, the chatbot will recognize the intent to proceed to checkout and provide a link, making it easy for users to complete their order.