### Verify Backend Installation

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Command to run an example Python script to verify the successful installation of the backend components.

```Bash
python examples/discriminative_task/optimizer_example.py
```

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

### Start Backend Service

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Commands to set up a Python virtual environment, install backend dependencies, and start the FastAPI backend server.

```Bash
cd prompt-optimizer
conda create --name prompt_optimizer python=3.10
conda activate prompt_optimizer
pip install -r requirements.txt
cd api
uvicorn main:app --reload --host 0.0.0.0 --port 8000
```

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

### Start Frontend Service

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Commands to navigate to the frontend directory, install dependencies, and start the development server in a new terminal.

```Bash
cd frontend
npm install
npm run dev
```

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

### Install Frontend Dependencies

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Commands to navigate into the frontend directory and install project dependencies using npm.

```Bash
cd frontend
npm install
```

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

### Install Project Dependencies

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Commands to install all required Python dependencies from `requirements.txt` or specific core dependencies individually.

```Bash
pip install -r requirements.txt

# Or install main dependencies individually
pip install pandas openpyxl requests python-dotenv tqdm
```

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

### Run Frontend Development Server

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Command to start the frontend development server for local testing and development.

```Bash
npm run serve
```

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

### Full Prompt Optimization Example with Python

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

A comprehensive Python example demonstrating how to define an evaluation function, prepare test data, configure LLM models, and initialize the PromptOptimizer for a time parsing task. This snippet showcases the core components and their integration for an end-to-end prompt optimization workflow.

```Python
from datetime import datetime
from optimizer.core.prompt_optimizer import PromptOptimizer
from llm.llm_config import LLM_Config
import pandas as pd

# 1. Define evaluation function
def example_evaluation_func(response: str, test_case: dict) -> float:
    """
    评估函数示例 - 检查模型输出是否符合预期
    """
    expected = str(test_case.get("expected", ""))
    if response == expected:
        return 1.0
    return 0.0

# 2. Prepare test dataset
def read_questions_and_units(file_path: str, sheet_name: str) -> list:
    """
    从Excel文件读取测试数据
    """
    df = pd.read_excel(file_path, sheet_name=sheet_name)
    return df.apply(lambda row: {
        "input": row["用户问题"],
        "expected": row["起始时间"]
    }, axis=1).tolist()

# 3. Configure LLM model
optimize_llm_config = LLM_Config(
    model_name="qwen-plus",
    api_key="your-api-key",
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)

test_llm_config = LLM_Config(
    model_name="qwen2.5-32b-instruct",
    api_key="your-api-key",
    base_url="https://dashscope.aliyuncs.com/compatible-mode/v1"
)

# 4. Create optimizer instance
optimizer = PromptOptimizer(
    optimize_llm_config=optimize_llm_config,
    test_llm_config=test_llm_config
)
```

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

### Build Frontend for Production

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Command to build the frontend project for production deployment.

```Bash
npm run build
```

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

### Clone Project Repository

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Commands to clone the Prompt Optimizer repository using either HTTPS or SSH, and then navigate into the project directory.

```Bash
git https://github.com/songtingze/prompt-optimizer.git

# Or using SSH
git clone git@github.com:songtingze/prompt-optimizer.git

cd prompt-optimizer
```

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

### Optimize Prompt API Endpoint

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Documentation for the `/api/optimize` POST endpoint, detailing request and response structures for prompt optimization.

```APIDOC
Endpoint: /api/optimize
Method: POST

Request Body (JSON):
  initial_prompt: string (Required) - The initial prompt.
  success_experience: string (Optional) - Description of successful experiences.
  optimize_suggestion: string (Optional) - Suggestions for optimization.
  test_accuracy: number (Required) - Initial test accuracy.

Response Body (JSON):
  optimized_prompt: string - The optimized prompt.
  success_experience: string - Optimized successful experience.
  optimize_suggestion: string - Optimized optimization suggestion.
  test_accuracy: number - Optimized test accuracy.
  execution_time: string - Time taken for execution.
  total_tokens: string - Total tokens consumed.
```

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

### Create Python Virtual Environment

Source: https://github.com/songtingze/prompt-optimizer/blob/master/README.md

Commands to create and activate a new Python virtual environment using Conda, recommended for dependency management.

```Bash
conda create --name prompt_optimizer python=3.10

# Activate virtual environment
conda activate prompt_optimizer
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.