[Evals API][2/n] datasets / datasetio meta-reference implementation (#288)

* skeleton dataset / datasetio

* dataset datasetio

* config

* address comments

* delete dataset_utils

* address comments

* naming fix

tests/examples/evals-tgi-run.yaml

@@ -0,0 +1,52 @@
+version: '2'
+built_at: '2024-10-08T17:40:45.325529'
+image_name: local
+docker_image: null
+conda_env: local
+apis:
+- shields
+- safety
+- agents
+- models
+- memory
+- memory_banks
+- inference
+- datasets
+- datasetio
+providers:
+  datasetio:
+  - provider_id: meta0
+    provider_type: meta-reference
+    config: {}
+  inference:
+  - provider_id: tgi0
+    provider_type: remote::tgi
+    config:
+      url: http://127.0.0.1:5009
+  memory:
+  - provider_id: meta-reference
+    provider_type: meta-reference
+    config: {}
+  agents:
+  - provider_id: meta-reference
+    provider_type: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: ~/.llama/runtime/kvstore.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: meta-reference
+    config: {}
+  safety:
+  - provider_id: meta-reference
+    provider_type: meta-reference
+    config:
+      llama_guard_shield:
+        model: Llama-Guard-3-1B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M