Register
Login
Resources
Docs Blog Datasets Glossary Case Studies Tutorials & Webinars
Product
Data Engine LLMs Platform Enterprise
Pricing Explore
Connect to our Discord channel
Michael 8fe1cc593c
chore(providers): add support for Vertex llama + update documentation (#3107)
5 months ago
..
8fe1cc593c
chore(providers): add support for Vertex llama + update documentation (#3107)
5 months ago
8fe1cc593c
chore(providers): add support for Vertex llama + update documentation (#3107)
5 months ago
8fe1cc593c
chore(providers): add support for Vertex llama + update documentation (#3107)
5 months ago
8fe1cc593c
chore(providers): add support for Vertex llama + update documentation (#3107)
5 months ago
ab0c382085
fix(gemini): support gemini thinking model (#2526)
7 months ago

README.md

You have to be logged in to leave a comment. Sign In

Google Vertex AI Examples

This directory contains example configurations for testing different Google Vertex AI models using promptfoo. The examples demonstrate various features and capabilities of Vertex AI models.

Configuration Files

  • promptfooconfig.gemini.yaml: Examples using Gemini 2.0 models

    • Function calling and tools
    • System instructions
    • Safety settings
    • Context and examples
  • promptfooconfig.claude.yaml: Examples using Claude models

    • Code analysis tools
    • Documentation search
    • Technical writing tests
    • Context customization
  • promptfooconfig.llama.yaml: Examples using Llama models

    • Vision capabilities
    • Safety with Llama Guard
    • Complex reasoning tasks
    • Text generation

Prerequisites

  1. Install the Google Auth Library:

    npm install google-auth-library
    
  2. Enable the Vertex AI API in your Google Cloud project:

  3. Configure authentication:

    # Option 1: User Account (recommended for development)
    gcloud auth application-default login
    
    # Option 2: Service Account
    export GOOGLE_APPLICATION_CREDENTIALS=/path/to/credentials.json
    

Running the Examples

  1. Set your Google Cloud project:

    gcloud config set project YOUR_PROJECT_ID
    
  2. Run specific model tests:

    # Test Gemini models
    promptfoo eval -c promptfooconfig.gemini.yaml
    
    # Test Claude models
    promptfoo eval -c promptfooconfig.claude.yaml
    
    # Test Llama models
    promptfoo eval -c promptfooconfig.llama.yaml
    
  3. View results:

    promptfoo view
    

Features Demonstrated

  • Model-specific configurations
  • Function calling and tools
  • System instructions
  • Safety settings
  • Context and examples
  • Vision capabilities
  • Complex reasoning tasks
  • Technical writing
  • Code analysis

Learn More

Tip!

Press p or to see the previous file or, n or to see the next file

Comments

Loading...