### Install ashr Python SDK

Source: https://ashr.io/docs.html

Installs the ashr Python SDK using pip. This is the first step to using the SDK in your Python environment.

```bash
pip install ashr-labs

```

--------------------------------

### Advanced Eval Run with ashr Python SDK

Source: https://ashr.io/docs.html

Shows a more controlled approach to running evals using EvalRunner. This example includes fetching a dataset, running the agent against each scenario with custom logging, inspecting aggregate metrics, and then deploying the results.

```python
from ashr_labs import AshrLabsClient, EvalRunner

client = AshrLabsClient(api_key="tp_your_api_key_here")

# Fetch a dataset and run your agent against every scenario
runner = EvalRunner.from_dataset(client, dataset_id=42)
run = runner.run(my_agent, on_scenario=lambda sid, s: print(f"Running: {s['title']}"))

# Inspect metrics before submitting
metrics = run.build()["aggregate_metrics"]
print(f"Passed: {metrics['tests_passed']}/{metrics['total_tests']}")
print(f"Avg similarity: {metrics['average_similarity_score']}")

# Submit
run.deploy(client, dataset_id=42)

```

--------------------------------

### Quick Eval Run with ashr Python SDK

Source: https://ashr.io/docs.html

Demonstrates a quick way to initialize the AshrLabsClient and run an evaluation against a dataset using EvalRunner in just a few lines of code. This method is suitable for straightforward agent testing.

```python
from ashr_labs import AshrLabsClient, EvalRunner

# Initialize the client
client = AshrLabsClient(api_key="tp_your_api_key_here")

# Run your agent against a dataset and submit results — 3 lines
runner = EvalRunner.from_dataset(client, dataset_id=42)
runner.run_and_deploy(my_agent, client, dataset_id=42)

```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.