# AI Investment Advisor

### Overview

An AI-powered investment advisor combining Claude's analytical capabilities with Infoway real-time financial data. Supports natural language queries, pre-built analysis templates, and a web visualization interface.

| Item         | Details                                                                             |
| ------------ | ----------------------------------------------------------------------------------- |
| Python       | 3.10+                                                                               |
| Dependencies | `infoway-sdk`, `anthropic`, `streamlit`                                             |
| GitHub       | [infoway-api/infoway-ai-advisor](https://github.com/infoway-api/infoway-ai-advisor) |

### Features

* **Natural language interaction**: Ask questions in everyday language to get professional financial analysis
* **10 built-in data tools**: Automatically calls Infoway API for real-time data
* **3 pre-built analysis templates**: Daily market briefing, stock diagnosis, sector rotation
* **Streamlit Web UI**: Visual interactive interface
* **CLI**: Suitable for automation and scripting

### Installation

```bash
git clone https://github.com/infoway-api/infoway-ai-advisor.git
cd infoway-ai-advisor
pip install -r requirements.txt
```

#### Environment Variables

```bash
export ANTHROPIC_API_KEY="your_anthropic_api_key"
export INFOWAY_API_KEY="your_infoway_api_key"
```

### Web UI

```bash
streamlit run web/app.py
```

Once launched, open in browser to:

* Configure API keys in the sidebar
* Use preset buttons for one-click analysis reports
* Enter free-form questions for conversation

### CLI Examples

#### Daily Market Briefing

```bash
python examples/daily_briefing.py
```

Generates a daily market overview for HK and US markets, including market temperature, leading industries, index performance, etc.

#### Stock Diagnosis

```bash
python examples/stock_diagnosis.py AAPL.US
```

Deep analysis of a single stock, including valuation assessment, institutional ratings, key driver factors, etc.

#### Sector Rotation Analysis

```bash
python examples/sector_rotation.py HK
```

Analyzes sector rotation patterns for a given market, identifying capital flows and trending concepts.

### Built-in Data Tools

| Tool               | Description                                       |
| ------------------ | ------------------------------------------------- |
| Real-time Trades   | Get latest price, volume, and change for symbols  |
| K-line Data        | Get historical K-lines for trend analysis         |
| Market Temperature | Get overall market sentiment and valuation levels |
| Market Breadth     | Get advance / decline distribution                |
| Global Indexes     | Get major global index quotes                     |
| Leading Industries | Get top-performing industry sectors               |
| Industry List      | Get full industry sector list                     |
| Sector Members     | Get constituent stocks of a sector                |
| Company Overview   | Get company profile                               |
| Valuation Data     | Get valuation metrics (PE/PB, etc.)               |

### Project Structure

```
ai-advisor/
├── advisor/
│   ├── agent.py       # Claude tool-use loop (max 15 rounds)
│   ├── tools.py       # 10 tool definitions + dispatcher
│   ├── analysis.py    # Pre-built analysis templates
│   └── report.py      # Markdown report formatter
├── web/
│   └── app.py         # Streamlit Web UI
└── examples/
    ├── daily_briefing.py      # Daily briefing
    ├── stock_diagnosis.py     # Stock diagnosis
    └── sector_rotation.py     # Sector rotation
```

***


---

# 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.infoway.io/en-docs/sdk-and-tools/ai-advisor.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.