Conversing with documents

Converse allows you to have a conversation with your documents, getting on-demand information from documents of nearly any type or format. A Converse conversation can also act as the starting point for a chatbot, so other users can query the documents in your conversation.

Creating conversations

To create a new conversation, you can:

• From the homepage, click Create on the Chats panel. An empty conversation opens in Converse.

• From Workspaces, click Create > Chat.

• While in Converse, hover over the left side menu to display a list of your conversations. Click + to create a new one.

All conversations are created in your personal workspace.

Adding documents

You can upload a variety of file types to your conversation, in a variety of supported languages, though there are some upload limitations. For example, files can be up to 50 MB or 800 pages in length and you can have up to 100 documents per conversation. Any files you upload are digitized and stored in your default drive. You can also add documents present in a connected drive.

In a new conversation, you can add files by:

• Dragging and dropping files into the center pane.

• Clicking the links present in the Select files or folders, browse drives, or paste a URL text in the center pane to open your local file explorer, the AI Hub file explorer, or the URL upload dialog.

  Documents uploaded from a URL are converted to a PDF upon upload. The content doesn’t automatically refresh.

After your first document is uploaded and processed, the center pane is replaced by a document viewer. To add additional documents to your conversation, click Add files in the file panel.

Digitization and object detection

When you upload files to Converse, they’re digitized—converted to machine-readable text—according to your conversation settings.

By default, page rotation, skew, and warp are corrected, and signatures and barcodes-both numeric and non-numeric formats-are detected.

As you use your conversation, you might need to modify digitization settings if responses aren’t being returned accurately. In your conversation’s digitization settings (Settings > Digitization), you can preview how changes impact machine-readable text with up to three documents from your conversation. Any time you change digitization settings, all files in your project are redigitized.

Choose the digitization settings suitable for your documents and AI Hub subscription. For details about OCR support for various languages, see Supported languages.

• Recognize visual objects > Tables: Provides better results when extracting information from tables. Also enables table highlighting, where all detected tables are highlighted in the document viewer. You can enlarge, copy, or download highlighted tables directly from the document viewer. Table extraction in Converse is a public preview feature and has some limitations.

• Recognize visual objects > Checkboxes: Provides better results when extracting information from checkboxes.

  Table and checkbox recognition change the OCR processor used, which slows digitization slightly and might impact accuracy, particularly with less common languages. We recommend enabling tables and checkboxes only if needed.

• Recognize languages > Non-Latin characters Commercial & Enterprise: Enables support for many common languages that use writing systems other than the Latin alphabet (a, b, c…). Support for non-Latin characters is offered in standard and advanced language sets. For details, see Supported languages.

• Enhancements > Treat files as images Commercial & Enterprise: Digitizes files as they appear, discarding any embedded machine-readable text. This option often provides better results for documents that use non-Latin characters, handwritten text, and visually complex documents.

• Pages Commercial & Enterprise: Limits digitization to specified pages.

Conversing with your documents

With Converse, you can ask any question of your documents, extract data from tables, lists, and checkboxes, and get your results in a variety of formats, including tables, charts, and graphs. Converse can identify information from single or multiple sources and select the relevant information for the response. You can query up to 50 documents at one time to find information or compare data across documents, though queries to multiple documents do have some limitations.

For example, for a single document, you might ask:

• What were the total tax deductions from this paystub?

• What was the highest earning fund in this 401k statement?

Or upload multiple documents and ask:

• Does this invoice rate match what’s stated in the contract?

• What conditions need to be met for this claim to be approved based on the guidelines?

• Do all these documents have the same address for Jane Smith?

Message scope

Message scope is the set of documents that you’re conversing with in each query. While you can upload multiple documents to your conversation, you can choose which of these documents to query with each message you send. The document or documents that comprise your current message scope are displayed under the chat box.

You can edit your message scope between queries:

• Switching documents: In the file panel, select the document to switch to. Or, click the + icon under the chat box to open the Edit message scope dialog. Clear the current scope and select the new document, then click Update.

• Adding documents: Click the + icon under the chat box to open the Edit message scope dialog. Select documents in the list then click Update. Or, in the file panel, hover over the document to add and click the + icon.

• Removing documents: Click the + icon under the chat box to open the Edit message scope dialog. Deselect documents in the list, then click Update. Or, click the x on the document name under the chat box.

• Clearing all documents: Click the + icon under the chat box to open the Edit message scope dialog. Click Clear scope, then click Update.

Models and research mode

Converse automatically chooses the best model for your query based on the number of documents included in your message scope. Queries to single documents use the advanced model. Queries to multiple documents use the multistep model. Regardless of the number of documents in 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.

Result formats

Converse can return responses in plain text or in other formats, including rich graph formats such as tables, lists, charts, and code blocks. These result formats can be copied or converted into other formats and downloaded.

Available formats for Converse responses include:

• Tables, which you can copy in TSV (tab-separated values) format or download as CSV files.

• Code blocks, with more than 25 formats available, including JSON, Python, bash, and JavaScript.

• Charts, including line, bar, column, pie, scatter, and multi-axis. Charts are also downloadable as CSV, PNG, or SVG files.

To get results in a specific format, ask for that format in your query to Converse. For example:

• Identify all beneficiaries in this trust document along with the beneficiary type, and return the results as a table.

• Show the payroll deductions as a pie chart.

• Show the percent increase in net sales from 2019 to 2022 as a bar chart.

To see available copy and download options for a given response, mouse over the corner of the response.

Getting the most out of Converse

Learn how to get the most out of Converse, from keyboard shortcuts to guidance on writing better questions.

User interface tips

• If you want to resend a previous query, click the chat box and press the ↑ (upwards arrow) key to populate your last query in the chat box. You can use your arrow keys to move up and down your conversation history. This is useful when you want to edit a previous message or resend the same message with a different scope.

• You can use keyboard shortcuts to edit your message scope. While writing your message, enter @ to bring up a list of all documents uploaded to your conversation. Documents currently in the message scope are highlighted. Select the document to add or remove it from the scope, or navigate through the list with your arrow keys and press Enter/Return to do the same.

• Each response includes a list of documents at the bottom—these are the documents that were referenced and found relevant when generating the response to your query.

• When using research mode, it’s noted in the response window. You can make use of this to compare how enabling research mode affects responses to the same query.

• You can provide feedback on low-quality responses by hovering over the response and clicking the thumbs down icon. Your feedback is used to improve model quality and might be viewed by Instabase. If you add a feedback message, don’t include any personally identifiable or sensitive information.

• You can show and hide the document viewer and file panel by clicking the x at the top of the document viewer. To bring both panels back, click the floating Open file panel (document) button.

• When object detection is enabled, you can see a summary of all detected objects by clicking the highlight icon

  
  at the top of the document viewer.

• When table object detection is enabled, tables are highlighted in the document viewer. You can enlarge the table, copy the table in TSV format, or download the table in CSV format, directly from the document viewer. Click the grid icon on the highlighted table and select the action.

How to ask great questions

Converse gives better answers when you ask better questions—learn how.

Provide clear instructions

Use verbs like extract, identify, calculate, find, explain, and summarize, depending on your documents and question. If you want the answer in a structured format such as table or in JSON, specify the result format explicitly.

Ask the model to think step-by-step

Especially for complex tasks, ask Converse to think step-by-step by adding “explain step by step” to the end of your query. When the model focuses on each task individually, it improves the accuracy of each response.

Provide additional context

Give Converse more context about your question to help it better understand what information you need.

Querying detected objects

You can use Converse to query detected objects such as tables, checkboxes, signatures, and barcodes.

Tables

To extract information from all tables in a document, begin your query with Extract all tables. To get results from multiple tables in a specific format, specify either Markdown or JSON. For example:

• Extract all tables and return in Markdown

• Extract all tables and return in JSON format

To extract information from a single specific table in a document, include the title or header of the table in your query. For example:

• Extract the transactions table for the month of January 2023

• Extract the monthly transaction summary for the month of January 2023

Converse returns single-table extraction results as a table, which you can copy or download as a CSV file.

You can also filter columns or rows, sort columns, and perform other manipulation of table data. For example:

• Extract transactions and filter for amounts greater than $1,000

• Extract transactions and return results for 01 May through 15 May

• Extract transactions table and sort amounts from smallest to largest

• Extract transactions and add a column Flagged with values set to Yes if the debit is greater than $70

Checkboxes

You can extract information from checkboxes in single or multipage documents.

• For a group of checkboxes with a label, such as the Filing Status field on a tax form, use a query asking about which checkboxes are selected, such as What filing status is claimed?

• For a standalone checkbox, use a query that indicates whether the checkbox is ticked. For example, Is the filer claiming capital gains or losses?

Signatures

You can extract information about signatures, including whether a document is signed, who the signer was, and the signature date. Extraction of signature images is not available.

For example, you can ask Converse:

• Extract all signatures

• Is this document signed?

• Who signed this document?

• Are these documents signed by the same people?

Barcodes

You can extract information about barcodes and their embedded values. Both numeric and non-numeric formats and one-dimensional and two-dimensional formats, such as PDF417 or QR codes, are supported. For example:

• Are there any barcodes in this document? If yes, what are their values?

• How many barcodes are in this document?

• What does the QR code in this document link to?