chore: import upstream snapshot with attribution
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled

This commit is contained in:
wehub-resource-sync
2026-07-13 13:24:08 +08:00
commit 0d3cb498a3
5438 changed files with 1316560 additions and 0 deletions
+8
View File
@@ -0,0 +1,8 @@
# provider-cloudflare (Cloudflare)
Examples for using promptfoo with Cloudflare AI services.
## Examples
- [ai](./ai/) - Cloudflare Workers AI native models (Llama, GPT-OSS, etc.)
- [gateway](./gateway/) - Cloudflare AI Gateway proxy for OpenAI, Anthropic, Groq, etc.
+94
View File
@@ -0,0 +1,94 @@
# provider-cloudflare/ai (Cloudflare Workers AI)
Cloudflare Workers AI evaluation with OpenAI-compatible endpoints.
## Quick Start
You can run this example with:
```bash
npx promptfoo@latest init --example provider-cloudflare/ai
cd provider-cloudflare/ai
```
## Environment Variables
This example requires the following environment variables:
- `CLOUDFLARE_ACCOUNT_ID` - Your Cloudflare account ID (found in your Cloudflare dashboard)
- `CLOUDFLARE_API_KEY` - Your Cloudflare API key with Workers AI permissions
Set these in your environment:
```bash
export CLOUDFLARE_ACCOUNT_ID=your_account_id_here
export CLOUDFLARE_API_KEY=your_api_key_here
```
## Example Configurations
### Basic Usage (`chat_config.yaml`)
Compares the latest flagship chat models:
- `cloudflare-ai:chat:@cf/openai/gpt-oss-120b` - OpenAI's production, general purpose, high reasoning model
- `cloudflare-ai:chat:@cf/meta/llama-4-scout-17b-16e-instruct` - Meta's Llama 4 Scout with native multimodal capabilities
### Advanced Configuration (`chat_advanced_configuration.yaml`)
Demonstrates OpenAI-compatible parameters with Cloudflare AI:
- Uses `@cf/mistralai/mistral-small-3.1-24b-instruct` (enhanced vision understanding and 128K context)
- Custom `max_tokens`, `temperature`, `seed` parameters
- Environment variable configuration patterns
### Embedding Configuration (`embedding_configuration.yaml`)
Shows embedding generation and similarity testing:
- Chat: `@cf/meta/llama-3.3-70b-instruct-fp8-fast` (optimized 70B model with fp8 quantization)
- Embedding: `@cf/google/embeddinggemma-300m` (state-of-the-art embedding model trained on 100+ languages)
- Similarity assertion testing with configurable thresholds
## Provider Types
Cloudflare AI supports three provider types:
1. **Chat**: `cloudflare-ai:chat:model-name` - Conversational AI and instruction following
2. **Completion**: `cloudflare-ai:completion:model-name` - Text completion and generation
3. **Embedding**: `cloudflare-ai:embedding:model-name` - Text embeddings for similarity and search
## Featured Models (2025)
This example showcases the latest flagship models:
- **OpenAI GPT-OSS-120B** (`@cf/openai/gpt-oss-120b`) - Production-ready, high reasoning capabilities
- **Meta Llama 4 Scout** (`@cf/meta/llama-4-scout-17b-16e-instruct`) - Multimodal with mixture-of-experts
- **Meta Llama 3.3 70B Fast** (`@cf/meta/llama-3.3-70b-instruct-fp8-fast`) - Speed-optimized 70B model
- **Mistral Small 3.1** (`@cf/mistralai/mistral-small-3.1-24b-instruct`) - Enhanced vision and 128K context
- **EmbeddingGemma-300M** (`@cf/google/embeddinggemma-300m`) - Multilingual embeddings (100+ languages)
## OpenAI Compatibility
All examples use Cloudflare's OpenAI-compatible endpoints, supporting standard parameters:
- `temperature` - Response randomness control
- `max_tokens` - Output length limits
- `top_p` - Nucleus sampling
- `frequency_penalty` - Repetition reduction
- `presence_penalty` - Topic diversity
## Local Development
For local testing with your development version:
```bash
npm run local -- eval -c examples/provider-cloudflare/ai/chat_config.yaml
```
## References
- [Cloudflare Workers AI Models](https://developers.cloudflare.com/workers-ai/models/) - Complete model catalog
- [Cloudflare Workers AI Documentation](https://developers.cloudflare.com/workers-ai/) - Platform overview
- [OpenAI Compatibility](https://developers.cloudflare.com/workers-ai/configuration/open-ai-compatibility/) - API details
- [promptfoo Cloudflare AI Provider](../../../site/docs/providers/cloudflare-ai.md) - Provider documentation
@@ -0,0 +1,25 @@
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
prompts:
- Tell me a funny joke about {{topic}}
providers:
- id: cloudflare-ai:chat:@cf/mistralai/mistral-small-3.1-24b-instruct
config:
accountId: your_account_id_here
# ===============
# API key is loaded from CLOUDFLARE_API_KEY environment variable
# Alternatively, use custom environment variable names:
# apiKeyEnvar: CUSTOM_CLOUDFLARE_KEY
# accountIdEnvar: CUSTOM_CLOUDFLARE_ACCOUNT
# ===============
# OpenAI-compatible model parameters
max_tokens: 800
temperature: 0.7
seed: 1
tests:
- vars:
topic: programming
assert:
- type: icontains
value: '{{topic}}'
@@ -0,0 +1,19 @@
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
prompts:
- What is the capital of the {{country}}?
providers:
- cloudflare-ai:chat:@cf/openai/gpt-oss-120b
- cloudflare-ai:chat:@cf/meta/llama-4-scout-17b-16e-instruct
tests:
- vars:
country: United States
assert:
- type: icontains
value: Washington, D.C.
- vars:
country: England
assert:
- type: icontains
value: London
@@ -0,0 +1,31 @@
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
prompts:
- This prompt will be evaluated for embedding similarity
defaultTest:
options:
provider:
embedding:
id: cloudflare-ai:embedding:@cf/google/embeddinggemma-300m
config:
accountId: your_account_id_here
providers:
- id: cloudflare-ai:chat:@cf/meta/llama-3.3-70b-instruct-fp8-fast
config:
accountId: your_account_id_here
# ===============
# API key is loaded from CLOUDFLARE_API_KEY environment variable
# Alternatively, use custom environment variable names:
# apiKeyEnvar: CUSTOM_CLOUDFLARE_KEY
# accountIdEnvar: CUSTOM_CLOUDFLARE_ACCOUNT
# ===============
# OpenAI-compatible model parameters
max_tokens: 800
temperature: 0.6
tests:
- assert:
- type: similar
value: embedding similarity
threshold: 0.6
@@ -0,0 +1,55 @@
# provider-cloudflare/gateway (Cloudflare AI Gateway)
You can run this example with:
```bash
npx promptfoo@latest init --example provider-cloudflare/gateway
cd provider-cloudflare/gateway
```
This example demonstrates how to route AI requests through [Cloudflare AI Gateway](https://developers.cloudflare.com/ai-gateway/) for caching, rate limiting, and analytics.
## Prerequisites
1. A Cloudflare account with AI Gateway enabled
2. An AI Gateway created in your Cloudflare dashboard
3. API keys for the providers you want to use (OpenAI, Anthropic, Groq, etc.)
## Setup
Set the required environment variables:
```bash
export CLOUDFLARE_ACCOUNT_ID=your_account_id
export CLOUDFLARE_GATEWAY_ID=your_gateway_id
export OPENAI_API_KEY=your_openai_key
export ANTHROPIC_API_KEY=your_anthropic_key
export GROQ_API_KEY=your_groq_key
```
## Running the Example
```bash
npx promptfoo eval -c examples/provider-cloudflare/gateway/promptfooconfig.yaml
```
## What This Example Does
The configuration compares responses from three different providers, all routed through Cloudflare AI Gateway:
- **OpenAI** (gpt-4o-mini)
- **Anthropic** (claude-haiku-4-5-20251001)
- **Groq** (llama-3.1-8b-instant)
Each provider answers questions about technical topics, and the assertions verify that responses contain relevant keywords.
## Benefits of Using AI Gateway
- **Caching**: Identical requests are cached, reducing costs during development
- **Analytics**: View usage across all providers in your Cloudflare dashboard
- **Rate Limiting**: Protect against quota issues with request queuing
- **Logging**: All requests and responses are logged for debugging
## Documentation
See the [Cloudflare AI Gateway provider documentation](https://www.promptfoo.dev/docs/providers/cloudflare-gateway) for more details.
@@ -0,0 +1,89 @@
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
# Cloudflare AI Gateway Example
#
# This example demonstrates routing AI requests through Cloudflare AI Gateway
# for caching, rate limiting, and analytics.
#
# Required environment variables:
# CLOUDFLARE_ACCOUNT_ID - Your Cloudflare account ID
# CLOUDFLARE_GATEWAY_ID - Your AI Gateway ID
#
# Optional environment variables:
# CF_AIG_TOKEN - Required if your gateway has "Authenticated Gateway" enabled
#
# Provider API keys (choose based on which providers you use):
# OPENAI_API_KEY - OpenAI API key
# ANTHROPIC_API_KEY - Anthropic API key
# GROQ_API_KEY - Groq API key
#
# Note: If you've configured BYOK (Bring Your Own Keys) in Cloudflare dashboard,
# you can omit the provider API keys - Cloudflare will use the stored keys.
#
# Run with:
# npx promptfoo eval -c examples/provider-cloudflare/gateway/promptfooconfig.yaml
description: Cloudflare AI Gateway comparison
prompts:
- 'Explain {{topic}} in simple terms, in about 2-3 sentences.'
providers:
# Route OpenAI requests through Cloudflare AI Gateway
- id: cloudflare-gateway:openai:gpt-4o-mini
config:
accountId: '{{env.CLOUDFLARE_ACCOUNT_ID}}'
gatewayId: '{{env.CLOUDFLARE_GATEWAY_ID}}'
# Uncomment if using authenticated gateway:
# cfAigToken: '{{env.CF_AIG_TOKEN}}'
temperature: 0.7
max_tokens: 200
# Route Anthropic requests through Cloudflare AI Gateway
- id: cloudflare-gateway:anthropic:claude-haiku-4-5-20251001
config:
accountId: '{{env.CLOUDFLARE_ACCOUNT_ID}}'
gatewayId: '{{env.CLOUDFLARE_GATEWAY_ID}}'
# Uncomment if using authenticated gateway:
# cfAigToken: '{{env.CF_AIG_TOKEN}}'
max_tokens: 200
# Route Groq requests through Cloudflare AI Gateway
- id: cloudflare-gateway:groq:llama-3.1-8b-instant
config:
accountId: '{{env.CLOUDFLARE_ACCOUNT_ID}}'
gatewayId: '{{env.CLOUDFLARE_GATEWAY_ID}}'
# Uncomment if using authenticated gateway:
# cfAigToken: '{{env.CF_AIG_TOKEN}}'
temperature: 0.7
max_tokens: 200
tests:
- vars:
topic: machine learning
assert:
- type: contains-any
value:
- algorithm
- data
- learn
- pattern
- vars:
topic: quantum computing
assert:
- type: contains-any
value:
- qubit
- quantum
- superposition
- computer
- vars:
topic: blockchain
assert:
- type: contains-any
value:
- block
- chain
- ledger
- decentralized