[rag evals][2/n] add more braintrust scoring fns for RAG eval (#666)

# What does this PR do?

- add more braintrust scoring functions for RAG eval
- add tests for evaluating against context

## Test Plan

```
pytest -v -s -m braintrust_scoring_together_inference scoring/test_scoring.py
```
<img width="850" alt="image"
src="https://github.com/user-attachments/assets/2f8f0693-ea13-422c-a183-f798faf86433"
/>


**Example Output**
- https://gist.github.com/yanxi0830/2acf3b8b3e8132fda2a48b1f0a49711b

<img width="827" alt="image"
src="https://github.com/user-attachments/assets/9014b957-107c-4c23-bbc0-812cbd0b16da"
/>

<img width="436" alt="image"
src="https://github.com/user-attachments/assets/21e9da17-f426-49b2-9113-855cab7b3d40"
/>




## Sources

Please link relevant resources if necessary.


## Before submitting

- [ ] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [ ] Ran pre-commit to handle lint / formatting issues.
- [ ] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
      Pull Request section?
- [ ] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

llama_stack/providers/tests/scoring/test_scoring.py

@@ -60,7 +60,7 @@ class TestScoring:
                 f"{provider_id} provider does not support scoring without params"
             )
 
-        await register_dataset(datasets_impl)
+        await register_dataset(datasets_impl, for_rag=True)
         response = await datasets_impl.list_datasets()
         assert len(response) == 1
 
@@ -112,7 +112,7 @@ class TestScoring:
             scoring_stack[Api.datasets],
             scoring_stack[Api.models],
         )
-        await register_dataset(datasets_impl)
+        await register_dataset(datasets_impl, for_rag=True)
         response = await datasets_impl.list_datasets()
         assert len(response) == 1
 
@@ -173,7 +173,7 @@ class TestScoring:
             scoring_stack[Api.datasets],
             scoring_stack[Api.models],
         )
-        await register_dataset(datasets_impl)
+        await register_dataset(datasets_impl, for_rag=True)
         rows = await datasetio_impl.get_rows_paginated(
             dataset_id="test_dataset",
             rows_in_page=3,