llama-stack/tests/client-sdk/README.md
Hardik Shah 632e60439a
Fix report generation for url endpoints (#876)
Earlier, we would have some unknown magic to identify the path for
remote endpoints when testing client_sdk/tests.
Removed that and now you have to explicitly pass a path
2025-01-24 13:15:44 -08:00

34 lines
1.3 KiB
Markdown

# Llama Stack Integration Tests
You can run llama stack integration tests on either a Llama Stack Library or a Llama Stack endpoint.
To test on a Llama Stack library with certain configuration, run
```bash
LLAMA_STACK_CONFIG=./llama_stack/templates/cerebras/run.yaml
pytest -s -v tests/client-sdk/inference/test_inference.py
```
or just the template name
```bash
LLAMA_STACK_CONFIG=together
pytest -s -v tests/client-sdk/inference/test_inference.py
```
To test on a Llama Stack endpoint, run
```bash
LLAMA_STACK_BASE_URL=http//localhost:8089
pytest -s -v tests/client-sdk/inference/test_inference.py
```
## Report Generation
To generate a report, run with `--report` option
```bash
LLAMA_STACK_CONFIG=together pytest -s -v report.md tests/client-sdk/ --report
```
## Common options
Depending on the API, there are custom options enabled
- For tests in `inference/` and `agents/, we support `--inference-model` (to be used in text inference tests) and `--vision-inference-model` (only used in image inference tests) overrides
- For tests in `vector_io/`, we support `--embedding-model` override
- For tests in `safety/`, we support `--safety-shield` override
- The param can be `--report` or `--report <path>`
If path is not provided, we do a best effort to infer based on the config / template name. For url endpoints, path is required.