Prompt Optimizer

This example demonstrates how to use the prompt optimization features of the gollm package for individual prompt optimization.

Key Components

1. LLM Setup: Initializes an LLM client using the Groq provider.

2. PromptExamples: Defines prompts to be optimized with associated metrics and thresholds.

3. Optimization Process: Iterates through examples, optimizing each prompt.

4. Response Generation: Generates content using optimized prompts.

5. Result Display: Shows original prompts, optimized versions, and generated content.

Code Structure

func main() {
    // LLM setup
    // Define PromptExamples
    // For each example:
    //     Create and configure optimizer
    //     Optimize prompt
    //     Generate response
    //     Store result
    // Display results
}

Key Code Snippets

LLM Setup

llm, err := gollm.NewLLM(
    gollm.SetProvider("groq"),
    gollm.SetModel("llama-3.1-70b-versatile"),
    gollm.SetAPIKey(os.Getenv("GROQ_API_KEY")),
    gollm.SetMaxTokens(1024),
    gollm.SetDebugLevel(gollm.LogLevelWarn),
)

Defining a PromptExample

{
    Name:        "Creative Writing",
    Prompt:      "Write the opening paragraph of a mystery novel set in a small coastal town.",
    Description: "Create an engaging and atmospheric opening that hooks the reader",
    Threshold:   0.9,
    Metrics: []gollm.Metric{
        {Name: "Atmosphere", Description: "How well the writing evokes the setting"},
        {Name: "Intrigue", Description: "How effectively it sets up the mystery"},
        {Name: "Character Introduction", Description: "How well it introduces key characters"},
    },
}

Optimization Process

optimizer := gollm.NewPromptOptimizer(llm, ex.Prompt, ex.Description,
    gollm.WithCustomMetrics(ex.Metrics...),
    gollm.WithRatingSystem("numerical"),
    gollm.WithThreshold(ex.Threshold),
    gollm.WithMaxRetries(3),
    gollm.WithRetryDelay(time.Second * 2),
    gollm.WithVerbose(),
)

optimizedPrompt, err := optimizer.OptimizePrompt(ctx)

Usage

1. Install and configure the gollm package.

2. Set the GROQ_API_KEY environment variable.

3. Run: go run prompt_optimizer_example.go

Customization

• Modify PromptExample structs in the examples slice.

• Adjust optimization parameters (threshold, metrics, rating system).

• Change LLM configuration (provider, model).