# Conversational CSV Analytics

You can upload CSV documents and generate charts, graphs, and insights using natural language queries. You can iteratively refine outputs through follow-up questions such as filtering, grouping, or changing visualization types.

The Aisera Gen AI Platform automatically interprets column headers so you can convert raw CSV data into presentation-ready visualizations that can be downloaded and reused externally.

This capability is designed to support lightweight data analysis without requiring spreadsheet tools or BI expertise.

## CSV Visualization Mode

To visualize CSV data in AI Copilot

1. In the chat input bar, select the **+** icon on the left.
2. From the menu, select **Visualize CSV data**. This opens the CSV Data Panel on the right.
3. Upload your CSV file by licking **Click to upload** or dragging and dropping it into the upload area.
4. Once uploaded, select the **checkbox** next to the file you wan to visualize.

With your file selected, type your query in the chat to generate a visualization.

While you're in the CSV Visualization Mode:

* Only CSV file uploads are supported.
* You can only upload files with a .csv extension.
* The most recently uploaded CSV file is treated as the active dataset.
* The active file is displayed in the right panel.
* You can generate charts and visualizations.
* Ask follow-up questions such as:
  * Changing graph types (such as: bar charts, line charts, and pie charts)
  * Applying filters or transformations

After you've entered the CSV Visualization Mode, an initial prompt asks you to upload a CSV file before proceeding.

### Follow Up Queries

All follow-up queries operate on the currently active CSV dataset.

When you select a CSV file on the landing page, the default conversation prompts are replaced with data-analysis prompts, such as:

* Show revenue by month
* Bar chart of sales by region
* Top 10 products by revenue
* Average response time by agent
* Compare this month vs. last month
* Show me a summary of the data

### CSV File Requirements:

* **File format:** .csv
* **Max file size:** 10MB
* **Must include a header row**

The file upload supports UTF-8 encoding to support international languages. Missing fields and rows are ignored by the platform. Currently the upload only supports & validates date formats in US English (MM/DD/YYYY) format.

### Supported Chart Types

The supported chart types include:

* Bar chart
* Line chart
* Pie chart
* Area chart
* Scatter plot

### Chart Export

The chart export function returns base64-encoded chart images that can be exported in the following formats:

* PNG
* PDF

The Copilot UI renders the chart with hover-activated PNG and PDF download buttons

The CSV Data Panel shows a locked state: upload zone disabled, "Locked to this conversation" label, warning banner, Clear link hidden

### Sidebar & Conversation Library <a href="#sidebar-and-conversation-library" id="sidebar-and-conversation-library"></a>

* Visualization threads stored in the same conversation library as regular threads (no separate section)
* **No visual indicator**: CSV threads look identical to normal threads in the sidebar. Conversation type is tracked internally only.
* Thread title is set by conversation server (not UI). Can be renamed by user.

## Leaving the CSV Visualization Mode

Clicking **New Conversation** at any time takes you out of the CSV Visualization Mode and opens the original landing page.

Clicking a visualization thread from the **Conversation History** takes you back to the CSV Visualization mode.<br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.aisera.com/aisera-copilot/using-aisera-assistant-copilot/conversational-csv-analytics.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.