intellif-aihub 0.1.12__tar.gz → 0.1.14__tar.gz

{intellif_aihub-0.1.12/src/intellif_aihub.egg-info → intellif_aihub-0.1.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: intellif-aihub
-Version: 0.1.12
+Version: 0.1.14
 Summary: Intellif AI-hub SDK.
 Author-email: Platform Team <aihub@example.com>
 License-Expression: Apache-2.0
@@ -17,6 +17,7 @@ Requires-Dist: pyarrow>=21.0.0
 Requires-Dist: tqdm<5.0,>=4.66
 Requires-Dist: loguru>=0.7.3
 Requires-Dist: minio>=7.2.7
+Requires-Dist: requests>=2.32.4
 Dynamic: license-file
 
 # Intellif AI-Hub SDK

{intellif_aihub-0.1.12 → intellif_aihub-0.1.14}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name            = "intellif-aihub"
-version         = "0.1.12"
+version         = "0.1.14"
 description     = "Intellif AI-hub SDK."
 readme          = {file = "README.md", content-type = "text/markdown"}
 requires-python = ">=3.9"
@@ -19,6 +19,7 @@ dependencies    = [
   "tqdm>=4.66,<5.0",
   "loguru>=0.7.3",
   "minio>=7.2.7",
+  "requests>=2.32.4",
 ]
 
 
@@ -64,4 +65,4 @@ exclude = '''
   | build
   | dist
 )/
-'''
+'''

intellif_aihub-0.1.14/src/aihub/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.14"

{intellif_aihub-0.1.12 → intellif_aihub-0.1.14}/src/aihub/models/dataset_management.py

@@ -135,3 +135,71 @@ class FileUploadData(BaseModel):
     """文件上传数据"""
     path: str = Field(description="路径")
     url: str = Field(description="URL")
+
+
+class ListDatasetReq(BaseModel):
+    """列表查询数据集请求(使用 dataset_management v2)"""
+    page_size: int = Field(20, alias="page_size", description="每页大小，默认20")
+    page_num: int = Field(1, alias="page_num", description="页码，从1开始")
+    name: Optional[str] = Field(None, description="数据集名称筛选")
+    tags: Optional[str] = Field(None, description="标签筛选")
+    create_by: Optional[int] = Field(None, alias="create_by", description="创建人筛选")
+    scope: Optional[str] = Field("all", description="范围筛选：created|shared|all")
+
+
+class ListDatasetItem(BaseModel):
+    """列表数据集项"""
+    id: int = Field(description="数据集ID")
+    name: str = Field(description="数据集名称")
+    description: str = Field(description="数据集描述")
+    cover_img: str = Field(alias="cover_img", description="封面图片")
+    created_at: int = Field(alias="created_at", description="创建时间戳")
+    updated_at: int = Field(alias="update_at", description="更新时间戳")
+    user_id: int = Field(alias="user_id", description="创建人ID")
+    username: str = Field(description="创建人用户名")
+    tags: Optional[List[int]] = Field(None, description="标签列表")
+    access_user_ids: Optional[List[int]] = Field(None, alias="access_user_ids", description="有访问权限的用户ID列表")
+    is_private: bool = Field(alias="is_private", description="是否私有")
+
+
+class ListDatasetResp(BaseModel):
+    """列表查询数据集响应"""
+    total: int = Field(description="总数")
+    page_size: int = Field(alias="page_size", description="每页大小")
+    page_num: int = Field(alias="page_num", description="当前页码")
+    data: List[ListDatasetItem] = Field(description="数据集列表")
+
+
+class ListDatasetVersionReq(BaseModel):
+    """列表查询数据集版本请求(使用 dataset_management v2)"""
+    page_size: int = Field(10000000, alias="page_size", description="每页大小，默认10000000")
+    page_num: int = Field(1, alias="page_num", description="页码，从1开始")
+    dataset_id: Optional[int] = Field(None, alias="dataset_id", description="数据集ID筛选")
+    dataset_version_ids: Optional[str] = Field(None, alias="dataset_version_ids", description="数据集版本ID列表，逗号分隔")
+
+
+class ListDatasetVersionItem(BaseModel):
+    """列表数据集版本项"""
+    id: int = Field(description="版本ID")
+    version: int = Field(description="版本号")
+    dataset_id: int = Field(alias="dataset_id", description="数据集ID")
+    upload_path: str = Field(alias="upload_path", description="上传路径")
+    upload_type: int = Field(alias="upload_type", description="上传类型")
+    parent_version_id: Optional[int] = Field(None, alias="parent_version_id", description="父版本ID")
+    description: Optional[str] = Field(None, description="版本描述")
+    status: int = Field(description="版本状态")
+    message: str = Field(description="状态信息")
+    created_at: int = Field(alias="created_at", description="创建时间戳")
+    user_id: int = Field(alias="user_id", description="创建人ID")
+    data_size: int = Field(alias="data_size", description="数据大小")
+    data_count: int = Field(alias="data_count", description="数据条数")
+    username: str = Field(description="创建人用户名")
+    dataset_name: str = Field(alias="dataset_name", description="数据集名称")
+
+
+class ListDatasetVersionResp(BaseModel):
+    """列表查询数据集版本响应"""
+    total: int = Field(description="总数")
+    page_size: int = Field(alias="page_size", description="每页大小")
+    page_num: int = Field(alias="page_num", description="当前页码")
+    data: List[ListDatasetVersionItem] = Field(description="数据集版本列表")

{intellif_aihub-0.1.12 → intellif_aihub-0.1.14}/src/aihub/services/dataset_management.py

@@ -7,6 +7,8 @@
 - **创建数据集及其版本**（支持本地上传和服务器现有文件两种方式）
 - **上传文件到对象存储**（大文件自动分片）
 - **查询数据集／数据集版本详情**
+- **列表查询和搜索数据集**（支持分页和筛选）
+- **列表查询数据集版本**（支持按数据集ID筛选和分页）
 - **按版本名称或ID下载数据集文件**
 """
 
@@ -34,6 +36,10 @@ from ..models.dataset_management import (
     DatasetVersionDetail,
     UploadDatasetVersionResponse,
     FileUploadData,
+    ListDatasetReq,
+    ListDatasetResp,
+    ListDatasetVersionReq,
+    ListDatasetVersionResp,
 )
 from ..models.dataset_management import DatasetVersionStatus
 from ..utils.download import dataset_download, zip_dir
@@ -270,6 +276,66 @@ class DatasetManagementService:
             raise APIError("parquet_index_path 为空")
         dataset_download(detail.parquet_index_path, local_dir, worker)
 
+    def list_datasets(
+        self,
+        *,
+        page_size: int = 20,
+        page_num: int = 1,
+        name: str | None = None,
+        tags: str | None = None,
+        create_by: int | None = None,
+        scope: str = "all"
+    ) -> ListDatasetResp:
+        """列表查询数据集
+
+        Args:
+            page_size: 每页大小，默认20
+            page_num: 页码，从1开始，默认1
+            name: 数据集名称筛选，可选
+            tags: 标签筛选，可选
+            create_by: 创建人筛选，可选
+            scope: 范围筛选：created|shared|all，默认all
+
+        Returns:
+            ListDatasetResp: 数据集列表响应，包含分页信息和数据集列表
+        """
+        payload = ListDatasetReq(
+            page_size=page_size,
+            page_num=page_num,
+            name=name,
+            tags=tags,
+            create_by=create_by,
+            scope=scope
+        )
+        return self._dataset.list_datasets(payload)
+
+    def list_dataset_versions(
+        self,
+        *,
+        page_size: int = 10000000,
+        page_num: int = 1,
+        dataset_id: int | None = None,
+        dataset_version_ids: str | None = None
+    ) -> ListDatasetVersionResp:
+        """列表查询数据集版本
+
+        Args:
+            page_size: 每页大小，默认10000000
+            page_num: 页码，从1开始，默认1
+            dataset_id: 数据集ID筛选，可选
+            dataset_version_ids: 数据集版本ID列表，逗号分隔，可选
+
+        Returns:
+            ListDatasetVersionResp: 数据集版本列表响应，包含分页信息和数据集版本列表
+        """
+        payload = ListDatasetVersionReq(
+            page_size=page_size,
+            page_num=page_num,
+            dataset_id=dataset_id,
+            dataset_version_ids=dataset_version_ids
+        )
+        return self._dataset_version.list_dataset_versions(payload)
+
 
 class _Dataset:
     def __init__(self, http: httpx.Client):
@@ -292,6 +358,15 @@ class _Dataset:
             raise APIError(f"backend code {wrapper.code}: {wrapper.msg}")
         return wrapper.data
 
+    def list_datasets(self, payload: ListDatasetReq) -> ListDatasetResp:
+        """列表查询数据集"""
+        params = payload.model_dump(by_alias=True, exclude_none=True)
+        resp = self._http.get(f"{_BASE}/datasets", params=params)
+        wrapper = APIWrapper[ListDatasetResp].model_validate(resp.json())
+        if wrapper.code != 0:
+            raise APIError(f"backend code {wrapper.code}: {wrapper.msg}")
+        return wrapper.data
+
 
 class _DatasetVersion:
     def __init__(self, http: httpx.Client):
@@ -333,6 +408,15 @@ class _DatasetVersion:
             raise APIError(f"backend code {wrapper.code}: {wrapper.msg}")
         return wrapper.data
 
+    def list_dataset_versions(self, payload: ListDatasetVersionReq) -> ListDatasetVersionResp:
+        """列表查询数据集版本"""
+        params = payload.model_dump(by_alias=True, exclude_none=True)
+        resp = self._http.get(f"{_BASE}/dataset-versions", params=params)
+        wrapper = APIWrapper[ListDatasetVersionResp].model_validate(resp.json())
+        if wrapper.code != 0:
+            raise APIError(f"backend code {wrapper.code}: {wrapper.msg}")
+        return wrapper.data
+
 
 class _Upload:
     def __init__(self, http: httpx.Client):

{intellif_aihub-0.1.12 → intellif_aihub-0.1.14}/src/aihub/utils/http.py

@@ -1,13 +1,14 @@
 from __future__ import annotations
 
-import httpx
 import os
 
+import requests
+
 
 def http_download_file(url: str, dst_path: str, chunk: int = 1 << 16) -> None:
     os.makedirs(os.path.dirname(dst_path), exist_ok=True)
-    with httpx.stream("GET", url, follow_redirects=True, timeout=None) as r:
+    with requests.get(url, timeout=None, stream=True) as r:
         r.raise_for_status()
         with open(dst_path, "wb") as f:
-            for block in r.iter_bytes(chunk):
+            for block in r.iter_content(chunk):
                 f.write(block)

{intellif_aihub-0.1.12 → intellif_aihub-0.1.14/src/intellif_aihub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: intellif-aihub
-Version: 0.1.12
+Version: 0.1.14
 Summary: Intellif AI-hub SDK.
 Author-email: Platform Team <aihub@example.com>
 License-Expression: Apache-2.0
@@ -17,6 +17,7 @@ Requires-Dist: pyarrow>=21.0.0
 Requires-Dist: tqdm<5.0,>=4.66
 Requires-Dist: loguru>=0.7.3
 Requires-Dist: minio>=7.2.7
+Requires-Dist: requests>=2.32.4
 Dynamic: license-file
 
 # Intellif AI-Hub SDK

{intellif_aihub-0.1.12 → intellif_aihub-0.1.14}/src/intellif_aihub.egg-info/requires.txt

@@ -5,3 +5,4 @@ pyarrow>=21.0.0
 tqdm<5.0,>=4.66
 loguru>=0.7.3
 minio>=7.2.7
+requests>=2.32.4

intellif_aihub-0.1.14/tests/test_dataset_management.py

@@ -0,0 +1,124 @@
+from __future__ import annotations
+
+import unittest
+import uuid
+
+from src.aihub.client import Client
+
+BASE_URL = "http://192.168.13.160:30021"
+TOKEN = "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ5MDY2ODUwODAsImlhdCI6MTc1MzA4NTA4MCwidWlkIjoxMH0.89bQ66BJDGoCzwxuxugRRt9acPFKEVmgqXMZX7ApnhM"
+
+
+class TestDatasetManagement(unittest.TestCase):
+    def test_create_dataset_and_version(self):
+        client = Client(base_url=BASE_URL, token=TOKEN)
+        dataset_name = f"sdk_dataset_{uuid.uuid4().hex[:6]}"
+        dataset_id, dataset_version_id, version_tag = (
+            client.dataset_management.create_dataset_and_version(
+                dataset_name=dataset_name,
+                dataset_description="xxxxx",
+                is_local_upload=True,
+                local_file_path=r"C:\Users\admin\Desktop\hbase\images.zip",
+                server_file_path="",
+                version_description="yyyyy",
+            )
+        )
+        print("dataset_id:", dataset_id)
+        print("dataset_version_id:", dataset_version_id)
+        print("version_tag:", version_tag)
+
+    def test_run_download(self):
+        client = Client(base_url=BASE_URL, token=TOKEN)
+        client.dataset_management.run_download(
+            dataset_version_name="re/V12",
+            local_dir=r"C:\Users\admin\Downloads\ljn",
+            worker=4,
+        )
+        print("Done!")
+
+    def test_upload_dir(self):
+        client = Client(base_url=BASE_URL, token=TOKEN)
+        dataset_name = f"sdk_dataset_{uuid.uuid4().hex[:6]}"
+        dataset_id, dataset_version_id, version_tag = (
+            client.dataset_management.create_dataset_and_version(
+                dataset_name=dataset_name,
+                dataset_description="xxxxx",
+                is_local_upload=True,
+                local_file_path="./data",
+                server_file_path="",
+                version_description="yyyyy",
+            )
+        )
+        print("dataset_id:", dataset_id)
+        print("dataset_version_id:", dataset_version_id)
+        print("version_tag:", version_tag)
+
+    def test_list_datasets(self):
+        client = Client(base_url=BASE_URL, token=TOKEN)
+        
+        # Test basic list with default parameters
+        datasets_resp = client.dataset_management.list_datasets()
+        
+        print(f"Total datasets: {datasets_resp.total}")
+        print(f"Page size: {datasets_resp.page_size}")
+        print(f"Page number: {datasets_resp.page_num}")
+        print(f"Number of datasets in current page: {len(datasets_resp.data)}")
+        
+        # Print first few datasets if any
+        for i, dataset in enumerate(datasets_resp.data[:3]):
+            print(f"Dataset {i+1}: ID={dataset.id}, Name={dataset.name}, Description={dataset.description}")
+        
+        # Test with custom page size
+        datasets_resp_custom = client.dataset_management.list_datasets(page_size=5, page_num=1)
+        print(f"Custom page size test - Total: {datasets_resp_custom.total}, Page size: {datasets_resp_custom.page_size}")
+        
+        # Test with name filter
+        if datasets_resp.data:
+            first_dataset_name = datasets_resp.data[0].name
+            datasets_resp_filtered = client.dataset_management.list_datasets(name=first_dataset_name)
+            print(f"Filtered by name '{first_dataset_name}': {len(datasets_resp_filtered.data)} results")
+
+    def test_list_dataset_versions(self):
+        client = Client(base_url=BASE_URL, token=TOKEN)
+        
+        # First get list of datasets to find a valid dataset_id
+        datasets_resp = client.dataset_management.list_datasets(page_size=5)
+        
+        if not datasets_resp.data:
+            print("No datasets found, creating one for testing...")
+            # Create a dataset for testing
+            dataset_name = f"test_list_versions_{uuid.uuid4().hex[:6]}"
+            dataset_id, _, _ = client.dataset_management.create_dataset_and_version(
+                dataset_name=dataset_name,
+                dataset_description="Test dataset for list versions",
+                is_local_upload=True,
+                local_file_path="./data",
+                version_description="Test version",
+            )
+        else:
+            dataset_id = datasets_resp.data[0].id
+            print(f"Using existing dataset ID: {dataset_id}")
+        
+        # Test basic list without dataset_id filter (all versions)
+        versions_resp = client.dataset_management.list_dataset_versions()
+        
+        print(f"Total dataset versions: {versions_resp.total}")
+        print(f"Page size: {versions_resp.page_size}")
+        print(f"Page number: {versions_resp.page_num}")
+        print(f"Number of versions in current page: {len(versions_resp.data)}")
+        
+        # Print first few versions if any
+        for i, version in enumerate(versions_resp.data[:3]):
+            print(f"Version {i+1}: ID={version.id}, Dataset={version.dataset_name}, Version={version.version}, Status={version.status}")
+        
+        # Test with dataset_id filter
+        versions_resp_filtered = client.dataset_management.list_dataset_versions(dataset_id=dataset_id)
+        print(f"Versions for dataset {dataset_id}: {len(versions_resp_filtered.data)} results")
+        
+        if versions_resp_filtered.data:
+            for version in versions_resp_filtered.data:
+                print(f"  Version: ID={version.id}, Version={version.version}, Status={version.status}")
+        
+        # Test with custom page size
+        versions_resp_custom = client.dataset_management.list_dataset_versions(page_size=10, page_num=1)
+        print(f"Custom page size test - Total: {versions_resp_custom.total}, Page size: {versions_resp_custom.page_size}")

intellif_aihub-0.1.12/src/aihub/__init__.py

@@ -1 +0,0 @@
-__version__ = "0.1.12"

intellif_aihub-0.1.12/tests/test_dataset_management.py

@@ -1,54 +0,0 @@
-from __future__ import annotations
-
-import unittest
-import uuid
-
-from src.aihub.client import Client
-
-BASE_URL = "http://192.168.13.160:30021"
-TOKEN = "eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJleHAiOjQ5MDY2ODUwODAsImlhdCI6MTc1MzA4NTA4MCwidWlkIjoxMH0.89bQ66BJDGoCzwxuxugRRt9acPFKEVmgqXMZX7ApnhM"
-
-
-class TestDatasetManagement(unittest.TestCase):
-    def test_create_dataset_and_version(self):
-        client = Client(base_url=BASE_URL, token=TOKEN)
-        dataset_name = f"sdk_dataset_{uuid.uuid4().hex[:6]}"
-        dataset_id, dataset_version_id, version_tag = (
-            client.dataset_management.create_dataset_and_version(
-                dataset_name=dataset_name,
-                dataset_description="xxxxx",
-                is_local_upload=True,
-                local_file_path=r"C:\Users\admin\Desktop\hbase\images.zip",
-                server_file_path="",
-                version_description="yyyyy",
-            )
-        )
-        print("dataset_id:", dataset_id)
-        print("dataset_version_id:", dataset_version_id)
-        print("version_tag:", version_tag)
-
-    def test_run_download(self):
-        client = Client(base_url=BASE_URL, token=TOKEN)
-        client.dataset_management.run_download(
-            dataset_version_name="re/V12",
-            local_dir=r"C:\Users\admin\Downloads\ljn",
-            worker=4,
-        )
-        print("Done!")
-
-    def test_upload_dir(self):
-        client = Client(base_url=BASE_URL, token=TOKEN)
-        dataset_name = f"sdk_dataset_{uuid.uuid4().hex[:6]}"
-        dataset_id, dataset_version_id, version_tag = (
-            client.dataset_management.create_dataset_and_version(
-                dataset_name=dataset_name,
-                dataset_description="xxxxx",
-                is_local_upload=True,
-                local_file_path="./data",
-                server_file_path="",
-                version_description="yyyyy",
-            )
-        )
-        print("dataset_id:", dataset_id)
-        print("dataset_version_id:", dataset_version_id)
-        print("version_tag:", version_tag)