Files
promptfoo--promptfoo/examples/eval-python-assert/README.md
T
wehub-resource-sync 0d3cb498a3
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Waiting to run
Test and Publish Multi-arch Docker Image / test (push) Waiting to run
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Blocked by required conditions
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) Blocked by required conditions
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Blocked by required conditions
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Blocked by required conditions
Validate Renovate Config / Validate Renovate Configuration (push) Waiting to run
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
chore: import upstream snapshot with attribution
2026-07-13 13:24:08 +08:00

112 lines
2.8 KiB
Markdown

# eval-python-assert (Python Assertions)
Example configurations for testing LLM outputs using Python assertions with promptfoo.
You can run this example with:
```bash
npx promptfoo@latest init --example eval-python-assert
cd eval-python-assert
```
## Purpose
This example demonstrates how to use Python assertions for custom output validation with:
- External Python files with assertion functions
- Inline Python code directly in configuration files
- Configuration-based assertions with custom parameters
- Different assertion return formats (boolean, score, detailed results)
## Prerequisites
- Python 3.7+ installed and available in your PATH
- OpenAI API key (or other LLM provider)
## Environment Variables
- `OPENAI_API_KEY` - Your OpenAI API key (required)
## Configurations
This example includes two different approaches:
### External Python Files (`promptfooconfig-external.yaml`)
Uses external Python files for complex assertion logic:
- `promptfooconfig-external.yaml` - Configuration with external Python assertions
- `assert.py` - Basic assertion function with detailed scoring
- `assert_with_config.py` - Configuration-based assertion function
### Inline Python Code (`promptfooconfig-inline.yaml`)
Demonstrates inline Python assertions directly in the configuration:
- `promptfooconfig-inline.yaml` - Configuration with inline Python code
- Shows simple boolean checks and complex scoring logic
## Running the Examples
1. **External Python assertions example:**
```sh
promptfoo eval -c promptfooconfig-external.yaml
```
2. **Inline Python assertions example:**
```sh
promptfoo eval -c promptfooconfig-inline.yaml
```
3. **View results:**
```sh
promptfoo view
```
## Python Assertion Patterns
### Basic Boolean Return
```python
def get_assert(output, context):
return "expected_word" in output.lower()
```
### Score-Based Return
```python
def get_assert(output, context):
if "perfect" in output.lower():
return 1.0
elif "good" in output.lower():
return 0.5
else:
return 0.0
```
### Detailed Result Object
```python
def get_assert(output, context):
return {
"pass": True,
"score": 0.8,
"reason": "Contains expected content",
"namedScores": {"quality": 0.9, "relevance": 0.7}
}
```
## Expected Results
- **External example**: Shows advanced assertion patterns with detailed scoring and configuration support
- **Inline example**: Demonstrates quick assertions and simple validation logic
## Learn More
- [Python Assertions Documentation](https://www.promptfoo.dev/docs/configuration/expected-outputs/python/)
- [promptfoo Configuration Guide](https://www.promptfoo.dev/docs/configuration/guide/)
- [Assertion Types](https://www.promptfoo.dev/docs/configuration/expected-outputs/)