intellif-aihub 0.1.12__py3-none-any.whl → 0.1.14__py3-none-any.whl

aihub/__init__.py

@@ -1 +1 @@
-__version__ = "0.1.12"
+__version__ = "0.1.14"

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")

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):

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.dist-info → intellif_aihub-0.1.14.dist-info}/METADATA

@@ -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.dist-info → intellif_aihub-0.1.14.dist-info}/RECORD

@@ -1,11 +1,11 @@
-aihub/__init__.py,sha256=LcIlFjHZFfiF9Rd4UHoakmombOFkxIYk00I181frGBM,23
+aihub/__init__.py,sha256=PIBqEOI-nqKFL9oJAWQQwlHuujG9Cd7EmdxDrThNQto,23
 aihub/client.py,sha256=nVELjkyVOG6DKJjurYn59fCoT5JsSayUweiH7bvKcAo,5547
 aihub/exceptions.py,sha256=l2cMAvipTqQOio3o11fXsCCSCevbuK4PTsxofkobFjk,500
 aihub/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aihub/models/artifact.py,sha256=4xIWV3xfZuZWcCdmZGEZ5k_rvV4oc5C_3gapw5O-2vQ,4586
 aihub/models/common.py,sha256=qmabc2LkAdQJXIcpT1P35zxd0Lc8yDYdD4ame1iF4Bs,241
 aihub/models/data_warehouse.py,sha256=zXvWwg7ySoFJMdqQ_1UMTNEKDMhu1hDHlWdBAXdizBk,3905
-aihub/models/dataset_management.py,sha256=HmmOW0bA2byQNVavrDG0K5L6pAeGrTFv-ap9pvBWgds,6511
+aihub/models/dataset_management.py,sha256=etvMOwKO3Oc8h-pJ-adoGCOLWIe2YYzx2smZZ7eCdWw,10327
 aihub/models/document_center.py,sha256=od9bzx6krAS6ktIA-ChxeqGcch0v2wsS1flY2vuHXBc,1340
 aihub/models/eval.py,sha256=4Gon4Sg4dOkyCx3KH2mO5ip3AhrBwrPC0UZA447HeoQ,910
 aihub/models/labelfree.py,sha256=nljprYO6ECuctTVbHqriQ73N5EEyYURhBrnU28Ngfvc,1589
@@ -19,7 +19,7 @@ aihub/models/workflow_center.py,sha256=4xtI1WZ38ceXJ8gwDBj-QNjOiRlLO_8kGiQybdudJ
 aihub/services/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aihub/services/artifact.py,sha256=PtCGhYFpFK_hppQr7A0bdXvceXzmYSwEpRj-PE2rIcQ,11473
 aihub/services/data_warehouse.py,sha256=awvlJdggo8ph6sXweXXVp4GLRuUSD46LoD0QQksXRts,2964
-aihub/services/dataset_management.py,sha256=KB-NZpcQwixOpEkQ1xI0gKzvWA3A6ay6aQzFQoUfXXU,12847
+aihub/services/dataset_management.py,sha256=i9Q_Mt8XZeFQR3_5JqIeXu3Y01ay-fPXbykkrfs0OmQ,15961
 aihub/services/document_center.py,sha256=dG67Ji-DOnzL2t-4x4gVfMt9fbSj_IjVHCLw5R-VTkQ,1813
 aihub/services/eval.py,sha256=V1nBISIyYWg9JJO24xzy4-kit9NsaCYp1EWIX_fgJkQ,2128
 aihub/services/labelfree.py,sha256=xua62UWhVXTxJjHRyy86waaormnJjmpQwepcARBy_h0,1450
@@ -33,10 +33,10 @@ aihub/services/user_system.py,sha256=IqWL4bnsKyyzuGT5l6adnw0qNXlH9PSo1-C_pFyOSzA
 aihub/services/workflow_center.py,sha256=caKxOlba0J1s1RUK6RUm1ndJSwAcZXEakRanu3sGKPU,17468
 aihub/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 aihub/utils/download.py,sha256=yC3SoL5uE68pMB-IsNz233wj-gFrHB7D7ALzQA5JkFM,2155
-aihub/utils/http.py,sha256=rSNh4uNP7E3YGm3H1indRHctxC5Wu5xNBPvDrb9UHt4,421
+aihub/utils/http.py,sha256=SvEWB4BxvwaHYqMVE4B0Go3OWGAD4xyQnUXDZ16yOSo,410
 aihub/utils/s3.py,sha256=ISIBP-XdBPkURpXnN56ZnIWokOOg2SRUh_qvxJk-G1Q,2187
-intellif_aihub-0.1.12.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
-intellif_aihub-0.1.12.dist-info/METADATA,sha256=LPpYwvlgxhqRiSk6-PD7BEY0F8pVjw-kOZH_oU4Vwug,2917
-intellif_aihub-0.1.12.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-intellif_aihub-0.1.12.dist-info/top_level.txt,sha256=vIvTtSIN73xv46BpYM-ctVGnyOiUQ9EWP_6ngvdIlvw,6
-intellif_aihub-0.1.12.dist-info/RECORD,,
+intellif_aihub-0.1.14.dist-info/licenses/LICENSE,sha256=QwcOLU5TJoTeUhuIXzhdCEEDDvorGiC6-3YTOl4TecE,11356
+intellif_aihub-0.1.14.dist-info/METADATA,sha256=f1WbrM_51scvCQQZsNdhgYpweM3tVtdMftIif8zq7yU,2949
+intellif_aihub-0.1.14.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+intellif_aihub-0.1.14.dist-info/top_level.txt,sha256=vIvTtSIN73xv46BpYM-ctVGnyOiUQ9EWP_6ngvdIlvw,6
+intellif_aihub-0.1.14.dist-info/RECORD,,