From b1b93088c58018e831d19eb806065a12fc09e980 Mon Sep 17 00:00:00 2001 From: Sai Soundararaj Date: Tue, 1 Jul 2025 16:36:35 -0700 Subject: [PATCH] a --- api_update_plan.md | 4 ++-- docs/_static/llama-stack-spec.html | 31 ++++++++++++++++----------- docs/_static/llama-stack-spec.yaml | 19 +++++++++++++--- llama_stack/apis/datasets/datasets.py | 16 ++++++++++++++ llama_stack/apis/files/files.py | 3 +++ 5 files changed, 56 insertions(+), 17 deletions(-) diff --git a/api_update_plan.md b/api_update_plan.md index 91ad92bca..b59745fbc 100644 --- a/api_update_plan.md +++ b/api_update_plan.md @@ -227,8 +227,8 @@ Before finalizing documentation, verify: [x] 6. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/tools/rag_tool.py` - RAG tool runtime [x] 7. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/vector_io/vector_io.py` - Vector database operations [x] 8. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/vector_dbs/vector_dbs.py` - Vector database management -9. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/files/files.py` - File management -10. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/datasets/datasets.py` - Dataset management +[x] 9. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/files/files.py` - File management +[x] 10. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/datasets/datasets.py` - Dataset management 11. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/datasetio/datasetio.py` - Dataset I/O operations 12. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/post_training/post_training.py` - Training and fine-tuning 13. `/Users/saip/Documents/GitHub/llama-stack/llama_stack/apis/eval/eval.py` - Evaluation framework diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html index 67c9a695e..4cebaec61 100644 --- a/docs/_static/llama-stack-spec.html +++ b/docs/_static/llama-stack-spec.html @@ -10366,9 +10366,9 @@ "tool", "tool_group" ], - "title": "ResourceType", "const": "dataset", - "default": "dataset" + "default": "dataset", + "description": "Type of resource, always 'dataset' for datasets" }, "purpose": { "type": "string", @@ -10377,11 +10377,11 @@ "eval/question-answer", "eval/messages-answer" ], - "title": "DatasetPurpose", - "description": "Purpose of the dataset. Each purpose has a required input data schema." + "description": "Purpose of the dataset indicating its intended use" }, "source": { - "$ref": "#/components/schemas/DataSource" + "$ref": "#/components/schemas/DataSource", + "description": "Data source configuration for the dataset" }, "metadata": { "type": "object", @@ -10406,7 +10406,8 @@ "type": "object" } ] - } + }, + "description": "Additional metadata for the dataset" } }, "additionalProperties": false, @@ -10418,7 +10419,8 @@ "source", "metadata" ], - "title": "Dataset" + "title": "Dataset", + "description": "Dataset resource for storing and accessing training or evaluation data." }, "RowsDataSource": { "type": "object", @@ -12007,14 +12009,16 @@ "type": "array", "items": { "$ref": "#/components/schemas/Dataset" - } + }, + "description": "List of datasets" } }, "additionalProperties": false, "required": [ "data" ], - "title": "ListDatasetsResponse" + "title": "ListDatasetsResponse", + "description": "Response from listing datasets." }, "ListModelsResponse": { "type": "object", @@ -14091,13 +14095,16 @@ "description": "List of file objects" }, "has_more": { - "type": "boolean" + "type": "boolean", + "description": "Whether there are more files available beyond this page" }, "first_id": { - "type": "string" + "type": "string", + "description": "ID of the first file in the list for pagination" }, "last_id": { - "type": "string" + "type": "string", + "description": "ID of the last file in the list for pagination" }, "object": { "type": "string", diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml index 7fd65d1fd..d154c6d76 100644 --- a/docs/_static/llama-stack-spec.yaml +++ b/docs/_static/llama-stack-spec.yaml @@ -7459,20 +7459,22 @@ components: - benchmark - tool - tool_group - title: ResourceType const: dataset default: dataset + description: >- + Type of resource, always 'dataset' for datasets purpose: type: string enum: - post-training/messages - eval/question-answer - eval/messages-answer - title: DatasetPurpose description: >- - Purpose of the dataset. Each purpose has a required input data schema. + Purpose of the dataset indicating its intended use source: $ref: '#/components/schemas/DataSource' + description: >- + Data source configuration for the dataset metadata: type: object additionalProperties: @@ -7483,6 +7485,7 @@ components: - type: string - type: array - type: object + description: Additional metadata for the dataset additionalProperties: false required: - identifier @@ -7492,6 +7495,8 @@ components: - source - metadata title: Dataset + description: >- + Dataset resource for storing and accessing training or evaluation data. RowsDataSource: type: object properties: @@ -8606,10 +8611,12 @@ components: type: array items: $ref: '#/components/schemas/Dataset' + description: List of datasets additionalProperties: false required: - data title: ListDatasetsResponse + description: Response from listing datasets. ListModelsResponse: type: object properties: @@ -10081,10 +10088,16 @@ components: description: List of file objects has_more: type: boolean + description: >- + Whether there are more files available beyond this page first_id: type: string + description: >- + ID of the first file in the list for pagination last_id: type: string + description: >- + ID of the last file in the list for pagination object: type: string const: list diff --git a/llama_stack/apis/datasets/datasets.py b/llama_stack/apis/datasets/datasets.py index 8bf7a48d0..76f8dbe8f 100644 --- a/llama_stack/apis/datasets/datasets.py +++ b/llama_stack/apis/datasets/datasets.py @@ -94,6 +94,10 @@ register_schema(DataSource, name="DataSource") class CommonDatasetFields(BaseModel): """ Common fields for a dataset. + + :param purpose: Purpose of the dataset indicating its intended use + :param source: Data source configuration for the dataset + :param metadata: Additional metadata for the dataset """ purpose: DatasetPurpose @@ -106,6 +110,10 @@ class CommonDatasetFields(BaseModel): @json_schema_type class Dataset(CommonDatasetFields, Resource): + """Dataset resource for storing and accessing training or evaluation data. + + :param type: Type of resource, always 'dataset' for datasets + """ type: Literal[ResourceType.dataset] = ResourceType.dataset @property @@ -118,10 +126,18 @@ class Dataset(CommonDatasetFields, Resource): class DatasetInput(CommonDatasetFields, BaseModel): + """Input parameters for dataset operations. + + :param dataset_id: Unique identifier for the dataset + """ dataset_id: str class ListDatasetsResponse(BaseModel): + """Response from listing datasets. + + :param data: List of datasets + """ data: list[Dataset] diff --git a/llama_stack/apis/files/files.py b/llama_stack/apis/files/files.py index a72dcd8d4..ba8701e23 100644 --- a/llama_stack/apis/files/files.py +++ b/llama_stack/apis/files/files.py @@ -54,6 +54,9 @@ class ListOpenAIFileResponse(BaseModel): Response for listing files in OpenAI Files API. :param data: List of file objects + :param has_more: Whether there are more files available beyond this page + :param first_id: ID of the first file in the list for pagination + :param last_id: ID of the last file in the list for pagination :param object: The object type, which is always "list" """