> For the complete documentation index, see [llms.txt](https://docs.sigrex.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.sigrex.io/startegies/llm-session/chart-setup.md).

# Chart Setup

This page explains how to configure chart input for AI-powered analysis.

Chart input is **optional**, but when enabled it allows the AI to analyze a **visual price chart with indicators**. This requires selecting an **image-capable AI model**.

***

### 🧠 When to Use Chart Input

Enable chart input if you want the AI to:

* Visually analyze **price structure**
* Identify **trends, ranges, and breakouts**
* Interpret **indicator behavior** directly from the chart
* Combine **visual context** with your custom prompt

If you only need **text-based reasoning** or strategy logic, chart input is not required.

***

### ⚠️ Model Compatibility

Chart input requires an AI model that supports **image (vision) input**.

* ✅ **Chart input enabled** → **Vision-capable model required**
* ✅ **Chart input disabled** → Any supported text-based model can be used

If a non-vision model is selected while chart input is enabled, the session will not run.

***

### ⚙️ Chart Configuration Options

#### Chart Image Input

Toggle this option to enable or disable chart screenshots.

* **Enabled**
  * A chart image is captured on each session run
  * Indicators are rendered on the chart
  * The image is sent to the AI for analysis
* **Disabled**
  * No chart image is sent
  * Indicator and timeframe settings are ignored

***

#### Symbol

The trading pair or market to display on the chart.

Uses **TradingView-compatible symbols**.

**Examples:**

* `BINANCE:BTCUSDT`
* `BINANCE:ETHUSDT`
* `BTCUSDT`

***

#### Candlestick Interval

Defines the timeframe of each candle on the chart.

**Common values:**

* `1m` – Scalping
* `5m`, `15m` – Intraday
* `1h`, `4h` – Swing trading
* `1d` – Higher timeframe analysis

***

#### Indicators

You can enable **up to two indicators** to be displayed on the chart.

Supported indicators include:

* RSI
* MACD
* EMA
* VWAP
* ATR
* Bollinger Bands

> Indicators are rendered directly onto the chart image and interpreted visually by the AI.

***

### 🖼️ What the AI Receives

When chart input is enabled, the AI receives:

* A **chart screenshot**
* The selected **symbol**
* The **candlestick interval**
* Enabled **indicators**
* Your **custom prompt**
* Any additional system context (e.g. last action)

***

### ✍️ Prompt Writing Tips for Chart Analysis

When using chart input, your prompt should reference **visual elements**.

**Good examples:**

* “Analyze the trend and momentum shown on the chart.”
* “Identify key support and resistance zones.”
* “Check if RSI divergence is forming.”
* “Is the price consolidating or breaking out?”

Avoid prompts that rely only on **numerical data**, since the AI is analyzing an image, not raw OHLC values.

***

### ❌ Common Misconfigurations

* Enabling chart input while using a **text-only AI model**
* Expecting indicator analysis when **chart input is disabled**
* Using very short analysis intervals with **high timeframes** (e.g. 1m period on 1d candles)

***

### 🔗 Related Pages

* [**LLM Session**](/startegies/llm-session.md) – Schedule AI-based analysis
* [**Chart Analysis with Signal Generation**](/startegies/llm-session/signal-generation.md) – Generate actionable trading signals


---

# 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 dynamically by asking a question.

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

```
GET https://docs.sigrex.io/startegies/llm-session/chart-setup.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.