### Set Up Virtual Environment and Install Dependencies

Source: https://github.com/llmquant/quant-wiki/blob/master/README.md

Create a virtual environment using venv, activate it, and install project dependencies from requirements.txt.

```bash
python -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
```

--------------------------------

### Clone Repository and Navigate

Source: https://github.com/llmquant/quant-wiki/blob/master/README.md

Clone the quant-wiki repository and navigate into the project directory to begin local setup.

```bash
git clone https://github.com/LLMQuant/quant-wiki.git
cd quant-wiki
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/SITE_CONFIGURATION.md

Install all project dependencies listed in the requirements.txt file using pip. This ensures the project has all necessary libraries to run.

```bash
pip install -r requirements.txt
```

--------------------------------

### Install Python Dependencies

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/DeepSeek-R1-tesla.md

Installs necessary Python libraries for fetching news, parsing HTML, and interacting with LLMs.

```bash
pip install yfinance pandas markitdown requests langchain langchain-ollama
```

--------------------------------

### Setup Python Virtual Environment

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/SITE_CONFIGURATION.md

Create and activate a Python virtual environment to isolate project dependencies. This is a standard practice for Python development.

```bash
python -m venv .venv
source .venv/bin/activate  # Linux/Mac
# or
.venv\Scripts\activate  # Windows
```

--------------------------------

### Example Call to Get Tesla News

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/DeepSeek-R1-tesla.md

Demonstrates how to call the `get_news` function for 'TSLA' and print the number of articles found and the details of the first article.

```python
news_list = get_news("TSLA")
print(len(news_list))  # 查看获取到的新闻数量
print(news_list[0])    # 输出其中一篇新闻的信息
```

--------------------------------

### Knowledge Checklist Example

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/LEARNING_PATHS.md

A checklist to track mastery of key financial concepts, probability, and trading principles. Useful for self-assessment and progress tracking.

```plaintext
Financial Concepts:
☐ Primary/secondary markets
☐ Stocks, bonds, derivatives
☐ Options Greeks
☐ Margin and leverage
☐ Short selling

Probability:
☐ Normal distribution
☐ Conditional probability
☐ Bayes' theorem
☐ Hypothesis testing
☐ Monte Carlo simulation

Trading:
☐ CAPM
☐ Fama-French
☐ Alpha/beta
☐ Momentum/mean reversion
☐ Backtesting methodology
```

--------------------------------

### Check for Outdated Packages

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/SITE_CONFIGURATION.md

List all installed Python packages that have newer versions available.

```bash
pip list --outdated
```

--------------------------------

### Agents with PythonREPLTool for Code Execution

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/aiquant/ChatGPT-langchain.md

Illustrates using an Agent with the PythonREPLTool to execute Python code directly within a LangChain flow for data processing, analysis, or computation. Note: This example uses langchain-core < 0.2.

```python
from langchain.agents import AgentType, initialize_agent
from langchain_experimental.tools import PythonREPLTool
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0)

tools = [
    PythonREPLTool()
]

agent = initialize_agent(
    tools, 
    llm, 
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True
)

agent.run("What is 3 + 3?")
```

--------------------------------

### Install Pydantic

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/aiquant/ChatGPT-langchain.md

Installs a specific version of the Pydantic library, which is often a dependency for LangChain components.

```shell
!pip install pydantic==<相应版本>
```

--------------------------------

### Serve MkDocs Locally

Source: https://github.com/llmquant/quant-wiki/blob/master/README.md

Run this command to serve the MkDocs documentation locally for previewing.

```bash
mkdocs serve
```

--------------------------------

### Build Static Site for Production

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/SITE_CONFIGURATION.md

Generate the static HTML, CSS, and JS files for the website in the 'site/' directory. This command optimizes assets for deployment.

```bash
mkdocs build
```

--------------------------------

### Initialize DeepSeek-R1 with OllamaLLM

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/DeepSeek-R1-tesla.md

Sets up the DeepSeek-R1 language model using LangChain's OllamaLLM integration, preparing it for sentiment analysis tasks.

```python
from langchain_ollama.llms import OllamaLLM
from langchain_core.prompts import ChatPromptTemplate
from pprint import pprint

# 初始化DeepSeek-R1
llm = OllamaLLM(model="deepseek-r1:1.5b")
```

--------------------------------

### Clone Repository

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/SITE_CONFIGURATION.md

Clone the quant-wiki repository to your local machine to begin contributing. Navigate into the cloned directory.

```bash
git clone https://github.com/YOUR_USERNAME/quant-wiki.git
cd quant-wiki
```

--------------------------------

### Ratio Signal Formula

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/chat-paper.md

Example of a ratio-based signal formula used in financial research, derived from accounting variables.

```latex
\text{Signal}_{i,t} = \frac{\text{AccountingVar1}_{i,t}}{\text{AccountingVar2}_{i,t}}
```

--------------------------------

### Project Directory Structure

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/README.md

This snippet shows the directory structure of the quant-wiki project, outlining the purpose of each main file.

```bash
output/
├── README.md                      # This file (overview and index)
├── PROJECT_OVERVIEW.md            # Project structure and architecture
├── CONTENT_CATALOG.md             # Complete content index (422 docs)
├── CONCEPTS_REFERENCE.md          # 192 core concepts encyclopedia
├── AI_TRADING_FRAMEWORKS.md       # AI/ML frameworks reference
├── SITE_CONFIGURATION.md          # Build system and deployment
└── LEARNING_PATHS.md              # 5 structured learning journeys
```

--------------------------------

### Difference Signal Formula

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/chat-paper.md

Example of a difference-based signal formula, calculating the change in an accounting variable over time relative to another variable.

```latex
\text{Signal}_{i,t} = \frac{\text{AccountingVar1}_{i,t} - \text{AccountingVar1}_{i,t-1}}{\text{AccountingVar2}_{i,t-1}}
```

--------------------------------

### Concept Map Example

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/LEARNING_PATHS.md

Illustrates a hierarchical structure for organizing knowledge about a concept like 'Volatility'. Useful for studying and interview preparation.

```plaintext
Volatility
├── Measurement (standard deviation)
├── Drivers (price movement)
├── Prediction (volatility forecasting)
├── Application (option pricing)
└── Trading (volatility arbitrage)
```

--------------------------------

### Deploy to GitHub Pages

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/SITE_CONFIGURATION.md

Build the site and deploy it to GitHub Pages. This command automates the process of building and pushing to the gh-pages branch.

```bash
mkdocs gh-deploy
```

--------------------------------

### Using LLMs with Prompting in LangChain

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/aiquant/ChatGPT-langchain.md

Demonstrates integrating LLMs with Prompting for generating targeted responses. The 'temperature' parameter controls output randomness; setting it to 0 ensures deterministic output.

```python
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(model="gpt-4")

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant."),
    ("user", "{input}")
])

chain = prompt | llm

response = chain.invoke({"input": "Translate the following English text to French: 'hello world'"})

print(response.content)
```

--------------------------------

### Get Tesla News with yfinance

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/DeepSeek-R1-tesla.md

Fetches news articles related to a given stock symbol using the yfinance library. It filters for 'STORY' content types and extracts title, summary, URL, and publication date.

```python
import yfinance as yf
import pandas as pd

def get_news(stock: str) -> list:
    """
    获取与指定股票相关的新闻列表，返回包含标题、摘要、链接、发布日期的字典列表。
    """
    try:
        # 获取股票对象及其新闻
        ticker = yf.Ticker(stock)
        news = ticker.news

        # 如果没有新闻，则返回空列表
        if not news:
            print(f"No news found for {stock}.")
            return []

        # 只保留contentType='STORY'的新闻
        relevant_news = [
            item for item in news if item.get('content', {}).get('contentType') == 'STORY'
        ]

        all_news = []
        for i, item in enumerate(relevant_news):
            try:
                content = item.get('content', {})
                current_news = {
                    'title': content.get('title'),
                    'summary': content.get('summary'),
                    'url': content.get('canonicalUrl', {}).get('url'),
                    'pubdate': content.get('pubDate', '').split('T')[0],
                }
                all_news.append(current_news)
            except Exception as e:
                print(f"Error processing news {i}: {e}")
                continue

        return all_news

    except Exception as e:
        print(f"An error occurred while fetching news for {stock}: {e}")
        return []
```

--------------------------------

### Prompt Templates for Structured Prompts

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/aiquant/ChatGPT-langchain.md

Illustrates the use of Prompt Templates to create predefined structures for prompts, enabling consistent and context-aware queries to language models. Placeholders can be used for dynamic data insertion.

```python
from langchain_core.prompts import PromptTemplate

prompt = PromptTemplate(
    input_variables=["product", "model"],
    template="Tell me more about the {product} in the {model} model.",
)

formatted_prompt = prompt.format(product="iPhone", model="15 Pro")
print(formatted_prompt)
```

--------------------------------

### Chains for Sequential Operations

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/aiquant/ChatGPT-langchain.md

Shows how to create a chain by connecting a prompt and an LLM ('prompt | llm') to perform sequential operations and generate responses. This structure is fundamental for building complex NLP tasks.

```python
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(model="gpt-4")

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant."),
    ("user", "{input}")
])

chain = prompt | llm

response = chain.invoke({"input": "What is the capital of France?"})
print(response.content)
```

--------------------------------

### Batch Processing with Chains

Source: https://github.com/llmquant/quant-wiki/blob/master/docs/ai/aiquant/ChatGPT-langchain.md

Demonstrates batch processing by inputting multiple data points into a chain simultaneously for parallel processing, which enhances efficiency.

```python
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(model="gpt-4")

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a helpful assistant."),
    ("user", "{input}")
])

chain = prompt | llm

responses = chain.batch([{"input": "Translate 'hello' to French"}, {"input": "Translate 'goodbye' to French"}])

for response in responses:
    print(response.content)
```

--------------------------------

### LangChain + ChatGPT Integration Pattern

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/AI_TRADING_FRAMEWORKS.md

Illustrates the flow for building AI-powered financial analysis agents using LangChain and OpenAI's GPT-4. This pattern is suitable for automated report generation and market analysis agents.

```text
LLM (GPT-4) → LangChain Agent → Financial Tools/APIs → Analysis Output
```

--------------------------------

### Include Custom CSS

Source: https://github.com/llmquant/quant-wiki/blob/master/_autodocs/SITE_CONFIGURATION.md

To use custom CSS, place your file in the 'docs/stylesheets/' directory and reference it in mkdocs.yml under 'extra_css'.

```yaml
extra_css:
  - stylesheets/custom.css
```