feat: implement File API for file upload and retrieval with new endpoints

apps/knowledge/api/document.py

@@ -19,13 +19,7 @@ class DocumentSplitAPI(APIMixin):
                 location='path',
                 required=True,
             ),
-            OpenApiParameter(
+
-                name="file",
-                description="文件",
-                type=OpenApiTypes.BINARY,
-                location='query',
-                required=False,
-            ),
             OpenApiParameter(
                 name="limit",
                 description="分段长度",
@@ -49,6 +43,20 @@ class DocumentSplitAPI(APIMixin):
             ),
         ]
 
+    @staticmethod
+    def get_request():
+        return {
+            'multipart/form-data': {
+                'type': 'object',
+                'properties': {
+                    'file': {
+                        'type': 'string',
+                        'format': 'binary'  # Tells Swagger it's a file
+                    }
+                }
+            }
+        }
+
 
 class DocumentBatchAPI(APIMixin):
     @staticmethod
@@ -197,15 +205,23 @@ class TableDocumentCreateAPI(APIMixin):
                 location='path',
                 required=True,
             ),
-            OpenApiParameter(
+
-                name="file",
-                description="文件",
-                type=OpenApiTypes.BINARY,
-                location='query',
-                required=False,
-            ),
         ]
 
+    @staticmethod
+    def get_request():
+        return {
+            'multipart/form-data': {
+                'type': 'object',
+                'properties': {
+                    'file': {
+                        'type': 'string',
+                        'format': 'binary'  # Tells Swagger it's a file
+                    }
+                }
+            }
+        }
+
     @staticmethod
     def get_response():
         return DefaultResultSerializer

apps/knowledge/api/file.py

@@ -0,0 +1,44 @@
+from drf_spectacular.types import OpenApiTypes
+from drf_spectacular.utils import OpenApiParameter
+
+from common.mixins.api_mixin import APIMixin
+from common.result import DefaultResultSerializer
+
+
+class FileUploadAPI(APIMixin):
+
+    @staticmethod
+    def get_request():
+        return {
+            'multipart/form-data': {
+                'type': 'object',
+                'properties': {
+                    'file': {
+                        'type': 'string',
+                        'format': 'binary'  # Tells Swagger it's a file
+                    }
+                }
+            }
+        }
+
+    @staticmethod
+    def get_response():
+        return DefaultResultSerializer
+
+
+class FileGetAPI(APIMixin):
+    @staticmethod
+    def get_parameters():
+        return [
+            OpenApiParameter(
+                name="file_id",
+                description="文件id",
+                type=OpenApiTypes.STR,
+                location='path',
+                required=True,
+            ),
+        ]
+
+    @staticmethod
+    def get_response():
+        return DefaultResultSerializer

apps/knowledge/serializers/file.py

@@ -0,0 +1,95 @@
+# coding=utf-8
+
+import uuid_utils.compat as uuid
+from django.db.models import QuerySet
+from django.http import HttpResponse
+from django.utils.translation import gettext_lazy as _
+from rest_framework import serializers
+
+from common.exception.app_exception import NotFound404
+from knowledge.models import File
+from tools.serializers.tool import UploadedFileField
+
+mime_types = {
+    "html": "text/html", "htm": "text/html", "shtml": "text/html", "css": "text/css", "xml": "text/xml",
+    "gif": "image/gif", "jpeg": "image/jpeg", "jpg": "image/jpeg", "js": "application/javascript",
+    "atom": "application/atom+xml", "rss": "application/rss+xml", "mml": "text/mathml", "txt": "text/plain",
+    "jad": "text/vnd.sun.j2me.app-descriptor", "wml": "text/vnd.wap.wml", "htc": "text/x-component",
+    "avif": "image/avif", "png": "image/png", "svg": "image/svg+xml", "svgz": "image/svg+xml",
+    "tif": "image/tiff", "tiff": "image/tiff", "wbmp": "image/vnd.wap.wbmp", "webp": "image/webp",
+    "ico": "image/x-icon", "jng": "image/x-jng", "bmp": "image/x-ms-bmp", "woff": "font/woff",
+    "woff2": "font/woff2", "jar": "application/java-archive", "war": "application/java-archive",
+    "ear": "application/java-archive", "json": "application/json", "hqx": "application/mac-binhex40",
+    "doc": "application/msword", "pdf": "application/pdf", "ps": "application/postscript",
+    "docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    "xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    "pptx": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+    "eps": "application/postscript", "ai": "application/postscript", "rtf": "application/rtf",
+    "m3u8": "application/vnd.apple.mpegurl", "kml": "application/vnd.google-earth.kml+xml",
+    "kmz": "application/vnd.google-earth.kmz", "xls": "application/vnd.ms-excel",
+    "eot": "application/vnd.ms-fontobject", "ppt": "application/vnd.ms-powerpoint",
+    "odg": "application/vnd.oasis.opendocument.graphics",
+    "odp": "application/vnd.oasis.opendocument.presentation",
+    "ods": "application/vnd.oasis.opendocument.spreadsheet", "odt": "application/vnd.oasis.opendocument.text",
+    "wmlc": "application/vnd.wap.wmlc", "wasm": "application/wasm", "7z": "application/x-7z-compressed",
+    "cco": "application/x-cocoa", "jardiff": "application/x-java-archive-diff",
+    "jnlp": "application/x-java-jnlp-file", "run": "application/x-makeself", "pl": "application/x-perl",
+    "pm": "application/x-perl", "prc": "application/x-pilot", "pdb": "application/x-pilot",
+    "rar": "application/x-rar-compressed", "rpm": "application/x-redhat-package-manager",
+    "sea": "application/x-sea", "swf": "application/x-shockwave-flash", "sit": "application/x-stuffit",
+    "tcl": "application/x-tcl", "tk": "application/x-tcl", "der": "application/x-x509-ca-cert",
+    "pem": "application/x-x509-ca-cert", "crt": "application/x-x509-ca-cert",
+    "xpi": "application/x-xpinstall", "xhtml": "application/xhtml+xml", "xspf": "application/xspf+xml",
+    "zip": "application/zip", "bin": "application/octet-stream", "exe": "application/octet-stream",
+    "dll": "application/octet-stream", "deb": "application/octet-stream", "dmg": "application/octet-stream",
+    "iso": "application/octet-stream", "img": "application/octet-stream", "msi": "application/octet-stream",
+    "msp": "application/octet-stream", "msm": "application/octet-stream", "mid": "audio/midi",
+    "midi": "audio/midi", "kar": "audio/midi", "mp3": "audio/mpeg", "ogg": "audio/ogg", "m4a": "audio/x-m4a",
+    "ra": "audio/x-realaudio", "3gpp": "video/3gpp", "3gp": "video/3gpp", "ts": "video/mp2t",
+    "mp4": "video/mp4", "mpeg": "video/mpeg", "mpg": "video/mpeg", "mov": "video/quicktime",
+    "webm": "video/webm", "flv": "video/x-flv", "m4v": "video/x-m4v", "mng": "video/x-mng",
+    "asx": "video/x-ms-asf", "asf": "video/x-ms-asf", "wmv": "video/x-ms-wmv", "avi": "video/x-msvideo"
+}
+
+
+class FileSerializer(serializers.Serializer):
+    file = UploadedFileField(required=True, label=_('file'))
+    meta = serializers.JSONField(required=False, allow_null=True)
+
+    def upload(self, with_valid=True):
+        if with_valid:
+            self.is_valid(raise_exception=True)
+        meta = self.data.get('meta', None)
+        if not meta:
+            meta = {'debug': True}
+        file_id = meta.get('file_id', uuid.uuid7())
+        file = File(id=file_id, file_name=self.data.get('file').name, meta=meta)
+        file.save(self.data.get('file').read())
+        return f'/api/file/{file_id}'
+
+    class Operate(serializers.Serializer):
+        id = serializers.UUIDField(required=True)
+
+        def get(self, with_valid=True):
+            if with_valid:
+                self.is_valid(raise_exception=True)
+            file_id = self.data.get('id')
+            file = QuerySet(File).filter(id=file_id).first()
+            if file is None:
+                raise NotFound404(404, _('File not found'))
+            # 如果是音频文件，直接返回文件流
+            file_type = file.file_name.split(".")[-1]
+            if file_type in ['mp3', 'wav', 'ogg', 'aac']:
+                return HttpResponse(
+                    file.get_bytes(),
+                    status=200,
+                    headers={
+                        'Content-Type': f'audio/{file_type}',
+                        'Content-Disposition': 'attachment; filename="{}"'.format(file.file_name)
+                    }
+                )
+            return HttpResponse(
+                file.get_bytes(),
+                status=200,
+                headers={'Content-Type': mime_types.get(file_type, 'text/plain')}
+            )

apps/knowledge/urls.py

@@ -38,4 +38,7 @@ urlpatterns = [
     path('workspace/<str:workspace_id>/knowledge/<str:knowledge_id>/problem/<int:current_page>/<int:page_size>', views.ProblemView.Page.as_view()),
     path('workspace/<str:workspace_id>/knowledge/<str:knowledge_id>/document/<int:current_page>/<int:page_size>', views.DocumentView.Page.as_view()),
     path('workspace/<str:workspace_id>/knowledge/<int:current_page>/<int:page_size>', views.KnowledgeView.Page.as_view()),
+    path('file', views.FileView.as_view()),
+    path('file/<str:file_id>', views.FileView.Operate.as_view()),
+
 ]

apps/knowledge/views/__init__.py

@@ -2,3 +2,4 @@ from .document import *
 from .knowledge import *
 from .paragraph import *
 from .problem import *
+from .file import *

apps/knowledge/views/file.py

@@ -0,0 +1,42 @@
+# coding=utf-8
+from django.utils.translation import gettext_lazy as _
+from drf_spectacular.utils import extend_schema
+from rest_framework.parsers import MultiPartParser
+from rest_framework.views import APIView
+from rest_framework.views import Request
+
+from common.auth import TokenAuth
+from common.result import result
+from knowledge.api.file import FileUploadAPI, FileGetAPI
+from knowledge.serializers.file import FileSerializer
+
+
+class FileView(APIView):
+    authentication_classes = [TokenAuth]
+    parser_classes = [MultiPartParser]
+
+    @extend_schema(
+        methods=['POST'],
+        summary=_('Upload file'),
+        description=_('Upload file'),
+        operation_id=_('Upload file'),
+        parameters=FileUploadAPI.get_parameters(),
+        request=FileUploadAPI.get_request(),
+        responses=FileUploadAPI.get_response(),
+        tags=[_('file')]
+    )
+    def post(self, request: Request):
+        return result.success(FileSerializer(data={'file': request.FILES.get('file')}).upload())
+
+    class Operate(APIView):
+        @extend_schema(
+            methods=['GET'],
+            summary=_('Get file'),
+            description=_('Get file'),
+            operation_id=_('Get file'),
+            parameters=FileGetAPI.get_parameters(),
+            responses=FileGetAPI.get_response(),
+            tags=[_('file')]
+        )
+        def get(self, request: Request, file_id: str):
+            return FileSerializer.Operate(data={'id': file_id}).get()

apps/tools/api/tool.py

@@ -139,14 +139,23 @@ class ToolImportAPI(APIMixin):
                 location='path',
                 required=True,
             ),
-            OpenApiParameter(
+
-                name='file',
-                type=OpenApiTypes.BINARY,
-                description='工具文件',
-                required=True
-            ),
         ]
 
+    @staticmethod
+    def get_request():
+        return {
+            'multipart/form-data': {
+                'type': 'object',
+                'properties': {
+                    'file': {
+                        'type': 'string',
+                        'format': 'binary'  # Tells Swagger it's a file
+                    }
+                }
+            }
+        }
+
     @staticmethod
     def get_response():
         return DefaultResultSerializer