change schema -> dataset_schema for register_dataset api (#443)

# What does this PR do?

- API updates: change schema to dataset_schema for register_dataset for
resolving pydantic naming conflict
- Note: this OpenAPI update will be synced with
llama-stack-client-python SDK.

cc @dineshyv 

## Test Plan

```
pytest -v -s -m meta_reference_eval_together_inference_huggingface_datasetio eval/test_eval.py
```

## 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.

docs/resources/llama-stack-spec.html

@@ -21,7 +21,7 @@
     "info": {
         "title": "[DRAFT] Llama Stack Specification",
         "version": "0.0.1",
-        "description": "This is the specification of the llama stack that provides\n                a set of endpoints and their corresponding interfaces that are tailored to\n                best leverage Llama Models. The specification is still in draft and subject to change.\n                Generated at 2024-11-12 15:47:15.607543"
+        "description": "This is the specification of the llama stack that provides\n                a set of endpoints and their corresponding interfaces that are tailored to\n                best leverage Llama Models. The specification is still in draft and subject to change.\n                Generated at 2024-11-13 11:02:50.081698"
     },
     "servers": [
         {
@@ -5170,7 +5170,7 @@
                         "const": "dataset",
                         "default": "dataset"
                     },
-                    "schema": {
+                    "dataset_schema": {
                         "type": "object",
                         "additionalProperties": {
                             "oneOf": [
@@ -5352,7 +5352,7 @@
                     "provider_resource_id",
                     "provider_id",
                     "type",
-                    "schema",
+                    "dataset_schema",
                     "url",
                     "metadata"
                 ]
@@ -6678,7 +6678,7 @@
                     "dataset_id": {
                         "type": "string"
                     },
-                    "schema": {
+                    "dataset_schema": {
                         "type": "object",
                         "additionalProperties": {
                             "oneOf": [
@@ -6863,7 +6863,7 @@
                 "additionalProperties": false,
                 "required": [
                     "dataset_id",
-                    "schema",
+                    "dataset_schema",
                     "url"
                 ]
             },
@@ -7837,58 +7837,58 @@
     ],
     "tags": [
         {
-            "name": "Safety"
+            "name": "Inspect"
-        },
-        {
-            "name": "EvalTasks"
-        },
-        {
-            "name": "Shields"
-        },
-        {
-            "name": "Telemetry"
-        },
-        {
-            "name": "Memory"
-        },
-        {
-            "name": "Scoring"
-        },
-        {
-            "name": "ScoringFunctions"
-        },
-        {
-            "name": "SyntheticDataGeneration"
         },
         {
             "name": "Models"
         },
         {
-            "name": "Agents"
+            "name": "Eval"
         },
         {
-            "name": "MemoryBanks"
+            "name": "EvalTasks"
         },
         {
-            "name": "DatasetIO"
+            "name": "Scoring"
         },
         {
             "name": "Inference"
         },
         {
-            "name": "Datasets"
+            "name": "Memory"
+        },
+        {
+            "name": "Safety"
         },
         {
             "name": "PostTraining"
         },
+        {
+            "name": "ScoringFunctions"
+        },
+        {
+            "name": "Telemetry"
+        },
+        {
+            "name": "Shields"
+        },
         {
             "name": "BatchInference"
         },
         {
-            "name": "Eval"
+            "name": "MemoryBanks"
         },
         {
-            "name": "Inspect"
+            "name": "Datasets"
+        },
+        {
+            "name": "SyntheticDataGeneration"
+        },
+        {
+            "name": "DatasetIO"
+        },
+        {
+            "name": "Agents"
         },
         {
             "name": "BuiltinTool",

docs/resources/llama-stack-spec.yaml

@@ -723,23 +723,7 @@ components:
     Dataset:
       additionalProperties: false
       properties:
-        identifier:
+        dataset_schema:
-          type: string
-        metadata:
-          additionalProperties:
-            oneOf:
-            - type: 'null'
-            - type: boolean
-            - type: number
-            - type: string
-            - type: array
-            - type: object
-          type: object
-        provider_id:
-          type: string
-        provider_resource_id:
-          type: string
-        schema:
           additionalProperties:
             oneOf:
             - additionalProperties: false
@@ -833,6 +817,22 @@ components:
               - type
               type: object
           type: object
+        identifier:
+          type: string
+        metadata:
+          additionalProperties:
+            oneOf:
+            - type: 'null'
+            - type: boolean
+            - type: number
+            - type: string
+            - type: array
+            - type: object
+          type: object
+        provider_id:
+          type: string
+        provider_resource_id:
+          type: string
         type:
           const: dataset
           default: dataset
@@ -844,7 +844,7 @@ components:
       - provider_resource_id
       - provider_id
       - type
-      - schema
+      - dataset_schema
       - url
       - metadata
       type: object
@@ -1910,21 +1910,7 @@ components:
       properties:
         dataset_id:
           type: string
-        metadata:
+        dataset_schema:
-          additionalProperties:
-            oneOf:
-            - type: 'null'
-            - type: boolean
-            - type: number
-            - type: string
-            - type: array
-            - type: object
-          type: object
-        provider_dataset_id:
-          type: string
-        provider_id:
-          type: string
-        schema:
           additionalProperties:
             oneOf:
             - additionalProperties: false
@@ -2018,11 +2004,25 @@ components:
               - type
               type: object
           type: object
+        metadata:
+          additionalProperties:
+            oneOf:
+            - type: 'null'
+            - type: boolean
+            - type: number
+            - type: string
+            - type: array
+            - type: object
+          type: object
+        provider_dataset_id:
+          type: string
+        provider_id:
+          type: string
         url:
           $ref: '#/components/schemas/URL'
       required:
       - dataset_id
-      - schema
+      - dataset_schema
       - url
       type: object
     RegisterEvalTaskRequest:
@@ -3384,7 +3384,7 @@ info:
   description: "This is the specification of the llama stack that provides\n     \
     \           a set of endpoints and their corresponding interfaces that are tailored\
     \ to\n                best leverage Llama Models. The specification is still in\
-    \ draft and subject to change.\n                Generated at 2024-11-12 15:47:15.607543"
+    \ draft and subject to change.\n                Generated at 2024-11-13 11:02:50.081698"
   title: '[DRAFT] Llama Stack Specification'
   version: 0.0.1
 jsonSchemaDialect: https://json-schema.org/draft/2020-12/schema
@@ -4748,24 +4748,24 @@ security:
 servers:
 - url: http://any-hosted-llama-stack.com
 tags:
-- name: Safety
-- name: EvalTasks
-- name: Shields
-- name: Telemetry
-- name: Memory
-- name: Scoring
-- name: ScoringFunctions
-- name: SyntheticDataGeneration
-- name: Models
-- name: Agents
-- name: MemoryBanks
-- name: DatasetIO
-- name: Inference
-- name: Datasets
-- name: PostTraining
-- name: BatchInference
-- name: Eval
 - name: Inspect
+- name: Models
+- name: Eval
+- name: EvalTasks
+- name: Scoring
+- name: Inference
+- name: Memory
+- name: Safety
+- name: PostTraining
+- name: ScoringFunctions
+- name: Telemetry
+- name: Shields
+- name: BatchInference
+- name: MemoryBanks
+- name: Datasets
+- name: SyntheticDataGeneration
+- name: DatasetIO
+- name: Agents
 - description: <SchemaDefinition schemaRef="#/components/schemas/BuiltinTool" />
   name: BuiltinTool
 - description: <SchemaDefinition schemaRef="#/components/schemas/CompletionMessage"

llama_stack/apis/datasets/datasets.py

@@ -49,7 +49,7 @@ class Datasets(Protocol):
     async def register_dataset(
         self,
         dataset_id: str,
-        schema: Dict[str, ParamType],
+        dataset_schema: Dict[str, ParamType],
         url: URL,
         provider_dataset_id: Optional[str] = None,
         provider_id: Optional[str] = None,

llama_stack/distribution/routers/routing_tables.py

@@ -310,7 +310,7 @@ class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):
     async def register_dataset(
         self,
         dataset_id: str,
-        schema: Dict[str, ParamType],
+        dataset_schema: Dict[str, ParamType],
         url: URL,
         provider_dataset_id: Optional[str] = None,
         provider_id: Optional[str] = None,
@@ -332,7 +332,7 @@ class DatasetsRoutingTable(CommonRoutingTableImpl, Datasets):
             identifier=dataset_id,
             provider_resource_id=provider_dataset_id,
             provider_id=provider_id,
-            dataset_schema=schema,
+            dataset_schema=dataset_schema,
             url=url,
             metadata=metadata,
         )

llama_stack/providers/tests/datasetio/test_datasetio.py

@@ -57,7 +57,7 @@ async def register_dataset(
 
     await datasets_impl.register_dataset(
         dataset_id=dataset_id,
-        schema=dataset_schema,
+        dataset_schema=dataset_schema,
         url=URL(uri=test_url),
     )
 

llama_stack/providers/tests/eval/test_eval.py

@@ -163,7 +163,7 @@ class Testeval:
 
         await datasets_impl.register_dataset(
             dataset_id="mmlu",
-            schema={
+            dataset_schema={
                 "input_query": StringType(),
                 "expected_answer": StringType(),
                 "chat_completion_input": ChatCompletionInputType(),