4,052 tools found
A promptfoo example demonstrating how to configure and evaluate prompts using Groq as the LLM provider, with setup commands and evaluation workflow.
Promptfoo example using LiteLLM's unified proxy to eval 400+ LLMs - GPT-4.1, Claude and Gemini - through one provider syntax with centralized cost tracking.
Promptfoo example testing Google Cloud Model Armor guardrails - direct API and Vertex AI integration, with per-filter assertion checks.
Promptfoo workflow that uses the ModelsLab API for text-to-image generation, demonstrated through an example configuration.
Promptfoo example evaluating Nscale's low-cost text and image models, with zero rate limits and no cold starts.
Test OpenClaw AI assistant gateways with promptfoo using an auto-detecting provider for chat, embeddings, and agent-specific evaluation.
Promptfoo examples for Perplexity's search-augmented models - citations, structured output, date/location filters, and reasoning modes.
Promptfoo example for writing a custom Python provider that calls OpenAI, with config loaded from external files.
Promptfoo example comparing QuiverAI Arrow models on text-to-SVG, image-to-SVG, and a chained GPT-Image-2→vectorize pipeline, LLM-judged.
Minimal promptfoo example testing the Replicate provider on a fast hello-world model - verifies API key and setup in under 5 seconds.
Custom Ruby provider example for promptfoo - wraps the OpenAI API in Ruby and shows Ruby-based custom assertion logic for evals.
Fully local promptfoo eval using Transformers.js - no API keys, running Qwen3-0.6B and a MiniLM embedding model on-device.
