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
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:
@@ -0,0 +1,32 @@
|
||||
# openai-function-call (OpenAI Function Call Example)
|
||||
|
||||
You can run this example with:
|
||||
|
||||
```bash
|
||||
npx promptfoo@latest init --example openai-function-call
|
||||
cd openai-function-call
|
||||
```
|
||||
|
||||
This example demonstrates how to use promptfoo to evaluate OpenAI function calls. It showcases two different methods of defining functions: in an external YAML file and directly in the configuration file.
|
||||
|
||||
## Setup
|
||||
|
||||
1. Set your OPENAI_API_KEY environment variable:
|
||||
|
||||
```bash
|
||||
export OPENAI_API_KEY=your_api_key_here
|
||||
```
|
||||
|
||||
2. This example is pre-configured in `promptfooconfig.yaml`. You can review and modify it if needed.
|
||||
|
||||
3. Run the evaluation:
|
||||
|
||||
```bash
|
||||
promptfoo eval
|
||||
```
|
||||
|
||||
4. View the results:
|
||||
|
||||
```bash
|
||||
promptfoo view
|
||||
```
|
||||
@@ -0,0 +1,15 @@
|
||||
- name: get_current_weather
|
||||
description: Get the current weather in a given location
|
||||
parameters:
|
||||
type: object
|
||||
properties:
|
||||
location:
|
||||
type: string
|
||||
description: The city and state, e.g. San Francisco, CA
|
||||
unit:
|
||||
type: string
|
||||
enum:
|
||||
- celsius
|
||||
- fahrenheit
|
||||
required:
|
||||
- location
|
||||
@@ -0,0 +1,66 @@
|
||||
# yaml-language-server: $schema=https://promptfoo.dev/config-schema.json
|
||||
description: OpenAI function calling with weather API integration
|
||||
|
||||
prompts:
|
||||
- 'What is the weather like in {{city}}?'
|
||||
|
||||
providers:
|
||||
- id: 'openai:chat:gpt-4.1-mini'
|
||||
label: 'functions-defined-in-external-file'
|
||||
config:
|
||||
functions: file://get_current_weather.yaml
|
||||
- id: 'openai:chat:gpt-4.1-mini'
|
||||
label: 'functions-defined-in-config'
|
||||
config:
|
||||
functions:
|
||||
[
|
||||
{
|
||||
'name': 'get_current_weather',
|
||||
'description': 'Get the current weather in a given location',
|
||||
'parameters':
|
||||
{
|
||||
'type': 'object',
|
||||
'properties':
|
||||
{
|
||||
'location':
|
||||
{
|
||||
'type': 'string',
|
||||
'description': 'The city and state, e.g. San Francisco, CA',
|
||||
},
|
||||
'unit': { 'type': 'string', 'enum': ['celsius', 'fahrenheit'] },
|
||||
},
|
||||
'required': ['location'],
|
||||
},
|
||||
},
|
||||
]
|
||||
|
||||
tests:
|
||||
- vars:
|
||||
city: Boston
|
||||
assert:
|
||||
- type: is-json
|
||||
- type: is-valid-openai-function-call
|
||||
- type: javascript
|
||||
value: output.name === 'get_current_weather'
|
||||
- type: javascript
|
||||
value: JSON.parse(output.arguments).location === 'Boston, MA'
|
||||
|
||||
- vars:
|
||||
city: New York
|
||||
assert:
|
||||
- type: equals
|
||||
value: get_current_weather
|
||||
# Transform is a cleaner way to pick out specific properties.
|
||||
# This transform returns only the 'name' property
|
||||
transform: output.name
|
||||
- type: similar
|
||||
value: NYC
|
||||
threshold: 0.5
|
||||
# This transform returns only the parsed location argument.
|
||||
transform: JSON.parse(output.arguments).location
|
||||
|
||||
- vars:
|
||||
city: Paris
|
||||
|
||||
- vars:
|
||||
city: Mars
|
||||
Reference in New Issue
Block a user