> For the complete documentation index, see [llms.txt](https://help.tellius.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.tellius.com/tellius-6.4/kaiya/ask-across-your-documents-unstructured.md).
# Ask across your documents (Unstructured)
Ask questions across unstructured documents in Tellius to extract insights from text, PDFs, and files using AI-powered search, semantic understanding, and contextual answers.
The **Unstructured** tab within the **Data → Connect** module is where you create, manage, and monitor connections to non-tabular data sources. While the **Structured** tab handles traditional database and warehouse connections, the Unstructured tab is purpose-built for file-based and document-based sources. These connections feed documents, PDFs, call transcripts, presentations, and other file-based content into Kaiya's unstructured analysis engine.
Once connected and synced, the files from these sources are indexed and made available to Kaiya for retrieval, search, and reasoning within Workspaces. This enables use cases such as analyzing sales call transcripts alongside CRM data, extracting insights from regulatory filings, or grounding Kaiya's answers in internal documentation and reports.
### How Kaiya uses your documents in Tellius 6.4
In Tellius 6.4, any Kaiya conversation can search your indexed documents. You don't need to start a Deep Insight or switch to a separate document mode. In the same conversation, Kaiya can use your documents together with your Business View data, in whatever order the question needs. For example, it can pull figures from a Business View and then check what a policy or a report says about them.
When a question may need your documents, Kaiya works through these steps:
1. **Checks what is available.** Kaiya looks at which document workspaces exist and whether any of them can answer the question.
2. **Searches the documents.** Kaiya searches the workspace that fits and gets back the passages that best match the question.
3. **Looks again when needed.** If the first results aren't enough, Kaiya can search again with different wording, narrow the search to specific documents, or read a whole document when short passages don't cover the answer.
4. **Writes one answer with citations.** Kaiya brings what it found into a single answer and cites each claim to the passage it came from.
To see these steps on an answer, open **How Kaiya got this**. Document steps are listed as **Checking indexed documents** and **Searching documents**, and each search shows the words Kaiya searched for. If a workspace has no indexed documents yet, Kaiya says so in the answer instead of guessing.
In Tellius 6.4 you don't need @ mentions. Kaiya picks the right workspaces and documents from your question, so name the report, document or topic in the question. If the **@** list appears in the message box, you don't need it.
Your document access is applied to every search. Kaiya uses only the documents you have permission to see, so an answer never draws on a document you don't have access to.
Kaiya can search documents when an administrator has turned on **Enable Kaiya Unstructured**, under **Settings → Intelligence → Kaiya & AI → Kaiya Configuration → Answers & Retrieval**, and your connections have synced documents into a workspace. See [Kaiya Configuration](https://help.tellius.com/settings/kaiya-and-ai/kaiya-configuration).
{% hint style="success" %}
**Ask in one go.** When a question needs both your numbers and what your documents say, ask it as one question. You don't need to split it into a data question and a document question, because Kaiya works out which parts need which source.
{% endhint %}
{% hint style="info" %}
**Help Kaiya pick the right workspace.** Kaiya uses each workspace's use case description and sample questions to decide whether that workspace can answer. Write them in the words your team uses when it asks questions. See [Workspace Configuration](https://help.tellius.com/kaiya/ask-across-your-documents-unstructured/workspace-configuration).
{% endhint %}
{% hint style="warning" %}
**In releases before Tellius 6.4**, document questions ran in a separate unstructured mode, and only a Deep Insight could combine your documents with your Business View data in one analysis.
{% endhint %}
### Managing unstructured files
The search bar in the top-right corner allows you to filter the list of unstructured connections by name.
The sorting control below the search bar lets you sort the connections list by **Creation Date** and **Name** in either newest-first or oldest-first order.
The **User** filter shows the connections that the selected users created. This is particularly useful in multi-user environments where multiple team members are setting up connections, and you need to find connections owned by a particular person. In releases before Tellius 6.4, this filter was named **Author**.
The **Reset** button clears all active sorting and filter selections, returning the connections list to its default view.
**All/Created by Me:** These two sub-tabs filter the connections list by ownership.
* **"All"** shows every unstructured connection in the environment regardless of who created it.
* **"Created by me"** filters the list to show only connections that the currently logged-in user created.
### Connections Table
The main area displays a table listing all configured unstructured data connections. Each row represents a single connection and displays the following columns:
**Name:** The display name assigned to the connection when it was created.
**Type:** The connector type, indicating which external storage service this connection links to. Supported types include
* Google Drive
* Amazon S3
* Gong
* Azure Blob Storage
* Google Cloud Storage
* SharePoint
* File Upload (documents uploaded from your computer, listed under the **dataset\_upload** connection)
In the table, Amazon S3 connections show the type **S3**.
**Schedule:** Displays the configured sync schedule for the connection. If no automatic sync schedule has been set, the connection syncs only when manually triggered. If a schedule is configured, it shows the recurrence pattern (for example, daily or weekly).
**Connection status:** Shows whether Tellius can currently reach the external data source.
* **"Connected"** shows that the credentials are valid and the source is reachable.
* **"Connecting…"** will be displayed when Tellius is trying to connect to the source.
* **"Auth expired"** shows that the saved sign-in or credentials are no longer valid.
* **"Unreachable"** shows that Tellius can't reach the source, for example because of a misconfigured path or revoked permissions.
* **"Paused"** shows that syncing is paused for the connection.
**Data sync status:** Shows the status of the most recent data synchronization: **Pending** (waiting to start), **Syncing** (with the percentage done while it runs), **Synced** (all files from the source have been pulled and indexed) or **Sync failed**. A dash means the connection hasn't synced yet.
**Creation date:** The date and time when the connection was originally created, displayed in your local timezone.
**Created by:** The user who created the connection. On a narrow screen, scroll the table to the right to see it.
### Row Actions (Three-Dot Menu)
Each row in the connections table has a three-dot menu (⋮) on the far right. Clicking this menu reveals four actions that you can perform on that specific connection: **Edit**, **Synchronize**, **Share** and **Delete**.
**Edit:** Opens the connection configuration for editing and update credentials.
**Synchronize:** Triggers an immediate, on-demand synchronization of the connection. When you click **Synchronize**, Tellius reaches out to the external data source, pulls any new or updated files, and indexes them for use in **Kaiya Workspaces**. Use this action when you have recently added new files to the source and want Kaiya to have access to them immediately without waiting for a scheduled sync. The **Data sync status** column will update to reflect the progress and completion of the sync operation.
**Share:** Opens **Share Datasource**. Type a name, username, email or group name in **Share with**, pick the access level and select **Share**. The dialog also lists who already has access, with a dropdown to change each person's access and a trash icon to remove it.
* **Can view:** the Business Views, datasets and datasources that belong to this connection are shared in read-only mode.
* **Can Edit:** the connection itself is shared in edit mode, and its Business Views, datasets and datasources are shared in read-only mode.
{% hint style="info" %}
**Can view or Can Edit?** Pick **Can view** for people who only need what the connection brings in. Pick **Can Edit** for a teammate who will maintain the connection with you.
{% endhint %}
**Delete:** Permanently removes the connection. Deleting a connection removes the link to the external data source and removes the indexed content from Kaiya's knowledge base. This action cannot be undone. Any **Workspaces** that were using files from this connection will no longer have access to that content.
### Re-index data
Re-indexing rebuilds the entire search index for all unstructured data across all connections. Specifically, it re-indexes all unstructured data that has been synced from your connections, regenerates automatic entities that Kaiya has extracted from the documents (such as people, organizations, dates, products, and other named entities), and deletes any manual entities that were previously created by users.
In Tellius 6.4, re-indexing is started from the **Workspaces** page: select **Workspace configuration** on the Unstructured tab, then select **Re-index now**. The re-index starts right away, and **Schedule** next to it opens the automatic re-index settings. See [Workspace Configuration](https://help.tellius.com/kaiya/ask-across-your-documents-unstructured/workspace-configuration#re-index-now-and-schedule).
In releases before Tellius 6.4, the Unstructured tab had a **Re-index data** button. Selecting it opened a confirmation dialog, and **Confirm** started the re-index.
#### When to re-index data?
Use **Re-index** after large-scale changes to your connected data sources, after modifying Workspace configurations, or if the index has become fragmented over time. Re-indexing is also appropriate after resolving connection errors that may have caused partial or failed syncs.
{% hint style="warning" %}
Re-indexing is a resource-intensive operation that processes all unstructured data in your environment. The time required depends on the total volume of documents across all connections. This operation cannot be undone. Any manual entities that your team has created will be permanently deleted and will need to be recreated after the re-index completes.
{% endhint %}
The **"Create new connection"** button in the top-right corner launches the workflow for adding a new unstructured data source. Check out [this](/tellius-6.4/kaiya/ask-across-your-documents-unstructured/how-to-connect-to-unstructured-data.md) page for more details.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://help.tellius.com/tellius-6.4/kaiya/ask-across-your-documents-unstructured.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
