> For the complete documentation index, see [llms.txt](https://docs.getdot.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.getdot.ai/integrations/files.md).

# CSV & Excel Files

Drop a CSV or Excel file into Dot and query it like a table.

Not everything worth analyzing lives in a database. Board exports, vendor reports, one-off extracts, the spreadsheet finance mails around — drop them into Dot and ask your questions, without waiting for anyone to load them into the warehouse first.

There are two ways to use files, depending on how long they should live.

## Attach a file to a chat

Attach a CSV or Excel file directly to your question in the web app. Dot reads it, profiles the columns, and analyzes it in place — ideal for one-off questions where the file *is* the dataset.

## Upload as a lasting table

For files the whole team should query repeatedly, an admin can upload them under **Settings → Connections → Upload Files**. The file becomes a table in your Model like any other source: Dot detects column names and types automatically, you can add descriptions and relationships, and everyone can ask questions against it.

Supported formats: `.csv`, `.xlsx`, and `.xls`.

{% hint style="info" %}
Files are a great on-ramp, not a governance strategy. When a spreadsheet becomes a system of record, move it to a governed source — or connect it as a [Google Sheet](/integrations/databases/google-sheets.md) so at least everyone reads the same live version.
{% endhint %}


---

# 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://docs.getdot.ai/integrations/files.md?ask=<question>&goal=<user_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.