Using chatbots

Use a chatbot to query and analyze a knowledge base of documents with the help of large language models.

Using the chatbot interface

Understanding the chatbot interface can help you efficiently analyze and compare documents against the chatbot’s knowledge base.

When you first open a chatbot, the interface shows a single panel, the chat panel. To open additional panels, click the Open file panel icon floating in the top right of the chat panel. Three main panels are visible:

• The document list on the left displays all documents included in the chatbot knowledge base. When you submit a query, the model references all documents in the knowledge base to create an answer. If you upload comparison files, those are also displayed in the list under Your files.

• The document view in the center displays the file selected in the document list. The view pane includes a toolbar, auto-hidden by default, with controls for viewing the selected document, including image or text-only views, keyword search, and page selection.

• The chat panel on the right contains the chat box and displays sample prompts, which are suggested queries from the chatbot author. You can click a sample prompt to send the query, or write your own in the chat box. After submitting a query, the sample prompts are replaced with your chat history. Chat history is retained between visits but visible only to you.

  You can clear your chat history by clicking Clear chat.

Querying chatbots

Chatbots are created from conversations and share similar features and functionality. Much of the information about conversing with documents in conversations applies when using a chatbot.

Some key differences between conversations and chatbots include:

• You can’t define message scope in a chatbot. A chatbot query is always made to the entire chatbot knowledge base. This difference affects how automatic model selection works for chatbots.

  While you can’t limit your queries to specific documents, you can direct the chatbot to prioritize referencing a specific document by including @file-name in your message.

• Chatbots don’t support querying information retrieved using object detection, such as tables and checkboxes. If a chatbot’s origin conversation has object detection enabled, the same query can yield different responses in the chatbot.

• Any feedback you provide is visible to the chatbot’s creator.

Models and research mode

Chatbots automatically choose the best model for your query based on the number of documents included in your message scope. Understanding this automatic selection helps you not only be aware of how many consumption units a query consumes but also understand the selected model’s capabilities.

• If the query is directed to a single document, the advanced model is automatically used. Chatbot queries are automatically directed to the entire knowledge base, so this situation applies only when the knowledge base contains one article and you haven’t added your own documents to the query.

• If the query is directed to multiple documents, the multistep model is automatically used.

Regardless of your message scope, you can enable research mode for any query by turning on the Research mode toggle in the chat box. Research mode uses a more powerful variant of the multistep model and is suited for complex reasoning queries, but can result in longer execution times.

Comparison queries

Comparison queries are a way to compare your own documents against the chatbot’s knowledge base. You can upload a file to your chatbot session and then reference it in your queries. Your uploaded files aren’t added to the chatbot’s knowledge base or made visible to the chatbot owner, but the model can still reference them when answering. Examples of when you might create a comparison query include:

• Verifying if a loan application meets all requirements outlined in the chatbot’s knowledge base.

• Comparing an insurance claim against a knowledge base of policies to see which policy the claim is covered under.

• Seeing if a resume meets the criteria outlined in a knowledge base of job listings.

To create a comparison query, start by uploading a comparison file. You can upload up to five files of any supported type and size.

1. Under the chat window, click the Upload query document icon .

2. Drag and drop a file into the upload pane or click the links present in the Select files or folders text to select from your file explorer.

Your files are uploaded and processed. During this time, you can’t send any queries, so expect a delay if uploading large files.

After uploading is complete, your files are added to the document list under Your files. Uploaded files are also automatically added to the current message scope, as indicated by their presence in the chat box. In subsequent queries, you need to explicitly tell the model to reference your uploaded file in one of the following ways:

• Explicitly include the file’s name (@file-name) in the query, such as Which job listings does the resume @jane-doe-resume.pdf meet the criteria for?

  Entering @ in the chat box brings up a list of all files in the knowledge base as well as your uploaded files. You can scroll through and select files from the list rather than typing out the file name yourself.

• Click the Upload query document icon , then click Select from previously uploaded files in the upload pane. You can then select files and click Add to query to add them to the message scope.

Your uploaded files are retained across visits to the same chatbot. Even if you clear your chat history, your uploaded files remain in the file panel. While these files aren’t visible to others, including the chatbot owner, you might want to delete them when finished referencing them or to make way for other files. To delete a file, click the delete icon next to the file name in the document list.

Providing response feedback

If you’re dissatisfied with the quality of a chatbot’s response, you can let the chatbot creator know. When a chatbot creator views feedback, they can see your user ID, the query, the response, and any details you choose to provide.

1. In the chat panel, click the thumbs-down icon below the response you’re providing feedback for.

2. In the feedback window, optionally provide more detailed written feedback.

3. Select a reason for your concern.

4. Click Submit feedback.