Files
wehub-resource-sync 5a558eb09e
TypeScript SDK Compatibility V1.x E2E Tests / Select Node version matrix (push) Has been cancelled
TypeScript SDK Compatibility V1.x E2E Tests / TypeScript SDK Compatibility V1.x E2E Tests Node ${{matrix.node_version}} (push) Has been cancelled
TypeScript SDK E2E Tests / TypeScript SDK E2E Tests Node ${{matrix.node_version}} (push) Has been cancelled
Opik Optimizer - E2E Tests / build-opik (push) Has been cancelled
TypeScript SDK Compatibility V1.x E2E Tests / build-opik (push) Has been cancelled
Python SDK E2E Tests / Select Python version matrix (push) Has been cancelled
Python SDK E2E Tests / Python SDK E2E Tests ${{matrix.python_version}} (push) Has been cancelled
Python SDK E2E Tests / build-opik (push) Has been cancelled
Python SDK Compatibility V1.x E2E Tests / Select Python version matrix (push) Has been cancelled
Python SDK Compatibility V1.x E2E Tests / Python SDK Compatibility V1.x E2E Tests ${{matrix.python_version}} (push) Has been cancelled
Python SDK Compatibility V1.x E2E Tests / build-opik (push) Has been cancelled
TypeScript SDK E2E Tests / Select Node version matrix (push) Has been cancelled
TypeScript SDK E2E Tests / build-opik (push) Has been cancelled
Opik Optimizer - E2E Tests / Opik Optimizer E2E Tests Python ${{matrix.python_version}} (push) Has been cancelled
Opik Optimizer - E2E Tests / Opik Optimizer Integration Smoke Tests (push) Has been cancelled
🐙 Code Quality / detect (push) Has been cancelled
🐙 Code Quality / lint (${{ matrix.leg.name }}) (push) Has been cancelled
🐙 Code Quality / summary (push) Has been cancelled
TypeScript SDK Library Integration Tests / Check Secrets (push) Has been cancelled
TypeScript SDK Library Integration Tests / opik-vercel (Vercel AI SDK / eve) (push) Has been cancelled
SDK Library Integration Tests Runner / Check Secrets (push) Has been cancelled
SDK Library Integration Tests Runner / Missed OpenAI API Key Warning (push) Has been cancelled
SDK Library Integration Tests Runner / Build (push) Has been cancelled
SDK Library Integration Tests Runner / openai_tests (push) Has been cancelled
SDK Library Integration Tests Runner / langchain_tests (push) Has been cancelled
SDK Library Integration Tests Runner / langchain_legacy_tests (push) Has been cancelled
SDK Library Integration Tests Runner / llama_index_tests (push) Has been cancelled
SDK Library Integration Tests Runner / anthropic_tests (push) Has been cancelled
SDK Library Integration Tests Runner / mistral_tests (push) Has been cancelled
SDK Library Integration Tests Runner / groq_tests (push) Has been cancelled
SDK Library Integration Tests Runner / aisuite_tests (push) Has been cancelled
SDK Library Integration Tests Runner / haystack_tests (push) Has been cancelled
SDK Library Integration Tests Runner / dspy_tests (push) Has been cancelled
SDK Library Integration Tests Runner / crewai_v0_tests (push) Has been cancelled
SDK Library Integration Tests Runner / crewai_v1_tests (push) Has been cancelled
SDK Library Integration Tests Runner / genai_tests (push) Has been cancelled
SDK Library Integration Tests Runner / adk_tests (push) Has been cancelled
SDK Library Integration Tests Runner / adk_legacy_1_3_0_tests (push) Has been cancelled
SDK Library Integration Tests Runner / evaluation_metrics_tests (push) Has been cancelled
SDK Library Integration Tests Runner / bedrock_tests (push) Has been cancelled
SDK Library Integration Tests Runner / litellm_tests (push) Has been cancelled
SDK Library Integration Tests Runner / harbor_tests (push) Has been cancelled
SDK Library Integration Tests Runner / Slack Notification (push) Has been cancelled
Lint Opik Helm Chart / render-equality (push) Has been cancelled
Opik Optimizer - Unit Tests / Opik Optimizer Unit Tests Python ${{matrix.python_version}} (push) Has been cancelled
Python BE E2E Tests / Python BE E2E (push) Has been cancelled
Python Backend Tests / run-python-backend-tests (push) Has been cancelled
Python SDK Unit Tests / Python SDK Unit Tests ${{matrix.python_version}} (push) Has been cancelled
Release Drafter / update_release_draft (push) Has been cancelled
SDK E2E Libraries Integration Tests / Check Secrets (push) Has been cancelled
SDK E2E Libraries Integration Tests / Missed OpenAI API Key Warning (push) Has been cancelled
SDK E2E Libraries Integration Tests / build-opik (push) Has been cancelled
SDK E2E Libraries Integration Tests / E2E Lib Integration Python ${{matrix.python_version}} (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-gemini) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-langchain) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-openai) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-otel) (push) Has been cancelled
TypeScript SDK Integration Build & Publish / build-and-publish (opik-vercel) (push) Has been cancelled
TypeScript SDK Build & Publish / build-and-publish (push) Has been cancelled
TypeScript SDK Unit Tests / Test on Node ${{ matrix.node-version }} (push) Has been cancelled
Backend Tests / discover-tests (push) Has been cancelled
Backend Tests / ${{ matrix.name }} (push) Has been cancelled
Build and Publish SDK / build-and-publish (push) Has been cancelled
Build Opik Docker Images / set-version (push) Has been cancelled
Build Opik Docker Images / build-backend (push) Has been cancelled
Build Opik Docker Images / build-sandbox-executor-python (push) Has been cancelled
Build Opik Docker Images / build-python-backend (push) Has been cancelled
Build Opik Docker Images / build-frontend (push) Has been cancelled
Build Opik Docker Images / create-git-tag (push) Has been cancelled
ClickHouse Migration Cluster Check / validate-clickhouse-migrations (push) Has been cancelled
Docs - Publish / run (push) Has been cancelled
E2E Tests - Post Merge (v2) / 🧪 E2E v2 Tests (${{ github.event.inputs.tier || 't1' }}) (push) Has been cancelled
E2E Tests - Post Merge (v2) / 📢 Slack Notification (push) Has been cancelled
Frontend Unit Tests / Test on Node 20 (push) Has been cancelled
Guardrails E2E Tests / Select Python version matrix (push) Has been cancelled
Guardrails E2E Tests / Guardrails E2E Tests ${{matrix.python_version}} (push) Has been cancelled
Guardrails E2E Tests / 📢 Slack Notification (push) Has been cancelled
Guardrails Backend Unit Tests / Guardrails Backend Unit Tests (push) Has been cancelled
Guardrails Backend Unit Tests / 📢 Slack Notification (push) Has been cancelled
Lint Opik Helm Chart / lint-helm-chart (Helm v3.21.0) (push) Has been cancelled
Lint Opik Helm Chart / lint-helm-chart (Helm v4.2.0) (push) Has been cancelled
Lint Opik Helm Chart / unittest-helm-chart (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:25:44 +08:00

70 lines
2.9 KiB
Plaintext

---
headline: Pytest integration | Opik Documentation
og:description: Monitor your LLM applications' performance by using Opik's Pytest
integration to track test results and ensure reliability before deployment.
og:site_name: Opik Documentation
og:title: Testing with Pytest - Opik
subtitle: Describes how to use Opik with Pytest to write LLM unit tests
title: Pytest integration
canonical-url: https://www.comet.com/docs/opik/evaluation/overview
---
Ensuring your LLM applications is working as expected is a crucial step before deploying to production. Opik provides a Pytest integration so that you can easily track the overall pass / fail rates of your tests as well as the individual pass / fail rates of each test.
## Using the Pytest Integration
We recommend using the `llm_unit` decorator to wrap your tests. This will ensure that Opik can track the results of your tests and provide you with a detailed report. It also works well when used in conjunction with the `track` decorator used to trace your LLM application.
Pytest hooks activate automatically when Opik `llm_unit` tests are collected. If your suite does not collect any `llm_unit` tests, the plugin remains inert by default. You can force enablement with `--opik` or by setting `opik_pytest_enabled = true` in your pytest configuration.
```python
import pytest
from opik import track, llm_unit
@track
def llm_application(user_question: str) -> str:
# LLM application code here
return "Paris"
@llm_unit()
def test_simple_passing_test():
user_question = "What is the capital of France?"
response = llm_application(user_question)
assert response == "Paris"
```
When you run the tests, Opik will create a new experiment for each run and log each test result. By navigating to the `tests` dataset, you will see a new experiment for each test run.
<Frame>
<img src="/img/testing/test_experiments.png" />
</Frame>
<Tip>
If you are evaluating your LLM application during development, we recommend using the `evaluate` function as it will
provide you with a more detailed report. You can learn more about the `evaluate` function in the [evaluation
documentation](/v1/evaluation/evaluate_your_llm).
</Tip>
### Advanced Usage
The `llm_unit` decorator also works well when used in conjunctions with the `parametrize` Pytest decorator that allows you to run the same test with different inputs:
```python
import pytest
from opik import track, llm_unit
@track
def llm_application(user_question: str) -> str:
# LLM application code here
return "Paris"
@llm_unit(expected_output_key="expected_output")
@pytest.mark.parametrize("user_question, expected_output", [
("What is the capital of France?", "Paris"),
("What is the capital of Germany?", "Berlin")
])
def test_simple_passing_test(user_question, expected_output):
response = llm_application(user_question)
assert response == expected_output
```