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

## Overview Violet Chat allows you to query your data, summarize changes, and generate reports and charts in natural language. Ask Violet to: * List parts with a certain release status, mass or owner * Calculate the total unpaid amount across your open invoices * Summarize recent changes to a BOM, requirement or test ### Setup First, head to **Integrations** to connect to an LLM provider. We support: * Amazon Bedrock * Azure AI Foundry * Claude * Gemini via Vertex AI * Google Gemini * Groq * OpenAI (ChatGPT) To connect, you'll need an API key generated from your selected provider.

Next, navigate to **Chat** and select your provider and desired model.

### Queries Use natural language queries to summarize data, count relevant results, identify outliers and perform calculations.

### Explorations To dive deeper into your data, open the query results in **Data Explorer** or save the results as an **Exploration**.

### Charts To visualize your data in a chart, click **Show Chart**.

Click **Expanded View** to see a preview, or click download to export the chart as a .png file.

Configure your chart by selecting the properties to measure, the type of chart, and the orientation.

--- # 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.violetlabs.com/ai/chat.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.