Feat/dataset notion import (#392)

Co-authored-by: StyleZhang <jasonapring2015@outlook.com>
Co-authored-by: JzoNg <jzongcode@gmail.com>

api/controllers/console/datasets/data_source.py

@@ -0,0 +1,303 @@
+import datetime
+import json
+
+from cachetools import TTLCache
+from flask import request, current_app
+from flask_login import login_required, current_user
+from flask_restful import Resource, marshal_with, fields, reqparse, marshal
+from werkzeug.exceptions import NotFound
+
+from controllers.console import api
+from controllers.console.setup import setup_required
+from controllers.console.wraps import account_initialization_required
+from core.data_source.notion import NotionPageReader
+from core.indexing_runner import IndexingRunner
+from extensions.ext_database import db
+from libs.helper import TimestampField
+from libs.oauth_data_source import NotionOAuth
+from models.dataset import Document
+from models.source import DataSourceBinding
+from services.dataset_service import DatasetService, DocumentService
+from tasks.document_indexing_sync_task import document_indexing_sync_task
+
+cache = TTLCache(maxsize=None, ttl=30)
+
+FILE_SIZE_LIMIT = 15 * 1024 * 1024  # 15MB
+ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm']
+PREVIEW_WORDS_LIMIT = 3000
+
+
+class DataSourceApi(Resource):
+    integrate_icon_fields = {
+        'type': fields.String,
+        'url': fields.String,
+        'emoji': fields.String
+    }
+    integrate_page_fields = {
+        'page_name': fields.String,
+        'page_id': fields.String,
+        'page_icon': fields.Nested(integrate_icon_fields, allow_null=True),
+        'parent_id': fields.String,
+        'type': fields.String
+    }
+    integrate_workspace_fields = {
+        'workspace_name': fields.String,
+        'workspace_id': fields.String,
+        'workspace_icon': fields.String,
+        'pages': fields.List(fields.Nested(integrate_page_fields)),
+        'total': fields.Integer
+    }
+    integrate_fields = {
+        'id': fields.String,
+        'provider': fields.String,
+        'created_at': TimestampField,
+        'is_bound': fields.Boolean,
+        'disabled': fields.Boolean,
+        'link': fields.String,
+        'source_info': fields.Nested(integrate_workspace_fields)
+    }
+    integrate_list_fields = {
+        'data': fields.List(fields.Nested(integrate_fields)),
+    }
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(integrate_list_fields)
+    def get(self):
+        # get workspace data source integrates
+        data_source_integrates = db.session.query(DataSourceBinding).filter(
+            DataSourceBinding.tenant_id == current_user.current_tenant_id,
+            DataSourceBinding.disabled == False
+        ).all()
+
+        base_url = request.url_root.rstrip('/')
+        data_source_oauth_base_path = "/console/api/oauth/data-source"
+        providers = ["notion"]
+
+        integrate_data = []
+        for provider in providers:
+            # existing_integrate = next((ai for ai in data_source_integrates if ai.provider == provider), None)
+            existing_integrates = filter(lambda item: item.provider == provider, data_source_integrates)
+            if existing_integrates:
+                for existing_integrate in list(existing_integrates):
+                    integrate_data.append({
+                        'id': existing_integrate.id,
+                        'provider': provider,
+                        'created_at': existing_integrate.created_at,
+                        'is_bound': True,
+                        'disabled': existing_integrate.disabled,
+                        'source_info': existing_integrate.source_info,
+                        'link': f'{base_url}{data_source_oauth_base_path}/{provider}'
+                })
+            else:
+                integrate_data.append({
+                    'id': None,
+                    'provider': provider,
+                    'created_at': None,
+                    'source_info': None,
+                    'is_bound': False,
+                    'disabled': None,
+                    'link': f'{base_url}{data_source_oauth_base_path}/{provider}'
+                })
+        return {'data': integrate_data}, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def patch(self, binding_id, action):
+        binding_id = str(binding_id)
+        action = str(action)
+        data_source_binding = DataSourceBinding.query.filter_by(
+            id=binding_id
+        ).first()
+        if data_source_binding is None:
+            raise NotFound('Data source binding not found.')
+        # enable binding
+        if action == 'enable':
+            if data_source_binding.disabled:
+                data_source_binding.disabled = False
+                data_source_binding.updated_at = datetime.datetime.utcnow()
+                db.session.add(data_source_binding)
+                db.session.commit()
+            else:
+                raise ValueError('Data source is not disabled.')
+        # disable binding
+        if action == 'disable':
+            if not data_source_binding.disabled:
+                data_source_binding.disabled = True
+                data_source_binding.updated_at = datetime.datetime.utcnow()
+                db.session.add(data_source_binding)
+                db.session.commit()
+            else:
+                raise ValueError('Data source is disabled.')
+        return {'result': 'success'}, 200
+
+
+class DataSourceNotionListApi(Resource):
+    integrate_icon_fields = {
+        'type': fields.String,
+        'url': fields.String,
+        'emoji': fields.String
+    }
+    integrate_page_fields = {
+        'page_name': fields.String,
+        'page_id': fields.String,
+        'page_icon': fields.Nested(integrate_icon_fields, allow_null=True),
+        'is_bound': fields.Boolean,
+        'parent_id': fields.String,
+        'type': fields.String
+    }
+    integrate_workspace_fields = {
+        'workspace_name': fields.String,
+        'workspace_id': fields.String,
+        'workspace_icon': fields.String,
+        'pages': fields.List(fields.Nested(integrate_page_fields))
+    }
+    integrate_notion_info_list_fields = {
+        'notion_info': fields.List(fields.Nested(integrate_workspace_fields)),
+    }
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    @marshal_with(integrate_notion_info_list_fields)
+    def get(self):
+        dataset_id = request.args.get('dataset_id', default=None, type=str)
+        exist_page_ids = []
+        # import notion in the exist dataset
+        if dataset_id:
+            dataset = DatasetService.get_dataset(dataset_id)
+            if not dataset:
+                raise NotFound('Dataset not found.')
+            if dataset.data_source_type != 'notion_import':
+                raise ValueError('Dataset is not notion type.')
+            documents = Document.query.filter_by(
+                dataset_id=dataset_id,
+                tenant_id=current_user.current_tenant_id,
+                data_source_type='notion_import',
+                enabled=True
+            ).all()
+            if documents:
+                for document in documents:
+                    data_source_info = json.loads(document.data_source_info)
+                    exist_page_ids.append(data_source_info['notion_page_id'])
+        # get all authorized pages
+        data_source_bindings = DataSourceBinding.query.filter_by(
+            tenant_id=current_user.current_tenant_id,
+            provider='notion',
+            disabled=False
+        ).all()
+        if not data_source_bindings:
+            return {
+                'notion_info': []
+            }, 200
+        pre_import_info_list = []
+        for data_source_binding in data_source_bindings:
+            source_info = data_source_binding.source_info
+            pages = source_info['pages']
+            # Filter out already bound pages
+            for page in pages:
+                if page['page_id'] in exist_page_ids:
+                    page['is_bound'] = True
+                else:
+                    page['is_bound'] = False
+            pre_import_info = {
+                'workspace_name': source_info['workspace_name'],
+                'workspace_icon': source_info['workspace_icon'],
+                'workspace_id': source_info['workspace_id'],
+                'pages': pages,
+            }
+            pre_import_info_list.append(pre_import_info)
+        return {
+            'notion_info': pre_import_info_list
+        }, 200
+
+
+class DataSourceNotionApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, workspace_id, page_id, page_type):
+        workspace_id = str(workspace_id)
+        page_id = str(page_id)
+        data_source_binding = DataSourceBinding.query.filter(
+            db.and_(
+                DataSourceBinding.tenant_id == current_user.current_tenant_id,
+                DataSourceBinding.provider == 'notion',
+                DataSourceBinding.disabled == False,
+                DataSourceBinding.source_info['workspace_id'] == f'"{workspace_id}"'
+            )
+        ).first()
+        if not data_source_binding:
+            raise NotFound('Data source binding not found.')
+        reader = NotionPageReader(integration_token=data_source_binding.access_token)
+        if page_type == 'page':
+            page_content = reader.read_page(page_id)
+        elif page_type == 'database':
+            page_content = reader.query_database_data(page_id)
+        else:
+            page_content = ""
+        return {
+            'content': page_content
+        }, 200
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument('notion_info_list', type=list, required=True, nullable=True, location='json')
+        parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
+        args = parser.parse_args()
+        # validate args
+        DocumentService.estimate_args_validate(args)
+        indexing_runner = IndexingRunner()
+        response = indexing_runner.notion_indexing_estimate(args['notion_info_list'], args['process_rule'])
+        return response, 200
+
+
+class DataSourceNotionDatasetSyncApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id_str = str(dataset_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        documents = DocumentService.get_document_by_dataset_id(dataset_id_str)
+        for document in documents:
+            document_indexing_sync_task.delay(dataset_id_str, document.id)
+        return 200
+
+
+class DataSourceNotionDocumentSyncApi(Resource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, document_id):
+        dataset_id_str = str(dataset_id)
+        document_id_str = str(document_id)
+        dataset = DatasetService.get_dataset(dataset_id_str)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+
+        document = DocumentService.get_document(dataset_id_str, document_id_str)
+        if document is None:
+            raise NotFound("Document not found.")
+        document_indexing_sync_task.delay(dataset_id_str, document_id_str)
+        return 200
+
+
+api.add_resource(DataSourceApi, '/data-source/integrates', '/data-source/integrates/<uuid:binding_id>/<string:action>')
+api.add_resource(DataSourceNotionListApi, '/notion/pre-import/pages')
+api.add_resource(DataSourceNotionApi,
+                 '/notion/workspaces/<uuid:workspace_id>/pages/<uuid:page_id>/<string:page_type>/preview',
+                 '/datasets/notion-indexing-estimate')
+api.add_resource(DataSourceNotionDatasetSyncApi, '/datasets/<uuid:dataset_id>/notion/sync')
+api.add_resource(DataSourceNotionDocumentSyncApi, '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/notion/sync')

api/controllers/console/datasets/datasets.py

@@ -12,8 +12,9 @@ from controllers.console.wraps import account_initialization_required
 from core.indexing_runner import IndexingRunner
 from libs.helper import TimestampField
 from extensions.ext_database import db
+from models.dataset import DocumentSegment, Document
 from models.model import UploadFile
-from services.dataset_service import DatasetService
+from services.dataset_service import DatasetService, DocumentService
 
 dataset_detail_fields = {
     'id': fields.String,
@@ -217,17 +218,31 @@ class DatasetIndexingEstimateApi(Resource):
     @login_required
     @account_initialization_required
     def post(self):
-        segment_rule = request.get_json()
-        file_detail = db.session.query(UploadFile).filter(
-            UploadFile.tenant_id == current_user.current_tenant_id,
-            UploadFile.id == segment_rule["file_id"]
-        ).first()
+        parser = reqparse.RequestParser()
+        parser.add_argument('info_list', type=dict, required=True, nullable=True, location='json')
+        parser.add_argument('process_rule', type=dict, required=True, nullable=True, location='json')
+        args = parser.parse_args()
+        # validate args
+        DocumentService.estimate_args_validate(args)
+        if args['info_list']['data_source_type'] == 'upload_file':
+            file_ids = args['info_list']['file_info_list']['file_ids']
+            file_details = db.session.query(UploadFile).filter(
+                UploadFile.tenant_id == current_user.current_tenant_id,
+                UploadFile.id.in_(file_ids)
+            ).all()
 
-        if file_detail is None:
-            raise NotFound("File not found.")
+            if file_details is None:
+                raise NotFound("File not found.")
 
-        indexing_runner = IndexingRunner()
-        response = indexing_runner.indexing_estimate(file_detail, segment_rule['process_rule'])
+            indexing_runner = IndexingRunner()
+            response = indexing_runner.file_indexing_estimate(file_details, args['process_rule'])
+        elif args['info_list']['data_source_type'] == 'notion_import':
+
+            indexing_runner = IndexingRunner()
+            response = indexing_runner.notion_indexing_estimate(args['info_list']['notion_info_list'],
+                                                                args['process_rule'])
+        else:
+            raise ValueError('Data source type not support')
         return response, 200
 
 
@@ -274,8 +289,54 @@ class DatasetRelatedAppListApi(Resource):
         }, 200
 
 
+class DatasetIndexingStatusApi(Resource):
+    document_status_fields = {
+        'id': fields.String,
+        'indexing_status': fields.String,
+        'processing_started_at': TimestampField,
+        'parsing_completed_at': TimestampField,
+        'cleaning_completed_at': TimestampField,
+        'splitting_completed_at': TimestampField,
+        'completed_at': TimestampField,
+        'paused_at': TimestampField,
+        'error': fields.String,
+        'stopped_at': TimestampField,
+        'completed_segments': fields.Integer,
+        'total_segments': fields.Integer,
+    }
+
+    document_status_fields_list = {
+        'data': fields.List(fields.Nested(document_status_fields))
+    }
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id):
+        dataset_id = str(dataset_id)
+        documents = db.session.query(Document).filter(
+            Document.dataset_id == dataset_id,
+            Document.tenant_id == current_user.current_tenant_id
+        ).all()
+        documents_status = []
+        for document in documents:
+            completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                              DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+            total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                          DocumentSegment.status != 're_segment').count()
+            document.completed_segments = completed_segments
+            document.total_segments = total_segments
+            documents_status.append(marshal(document, self.document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
 api.add_resource(DatasetListApi, '/datasets')
 api.add_resource(DatasetApi, '/datasets/<uuid:dataset_id>')
 api.add_resource(DatasetQueryApi, '/datasets/<uuid:dataset_id>/queries')
-api.add_resource(DatasetIndexingEstimateApi, '/datasets/file-indexing-estimate')
+api.add_resource(DatasetIndexingEstimateApi, '/datasets/indexing-estimate')
 api.add_resource(DatasetRelatedAppListApi, '/datasets/<uuid:dataset_id>/related-apps')
+api.add_resource(DatasetIndexingStatusApi, '/datasets/<uuid:dataset_id>/indexing-status')

api/controllers/console/datasets/datasets_document.py

@@ -1,6 +1,7 @@
 # -*- coding:utf-8 -*-
 import random
 from datetime import datetime
+from typing import List
 
 from flask import request
 from flask_login import login_required, current_user
@@ -61,6 +62,29 @@ document_fields = {
     'hit_count': fields.Integer,
 }
 
+document_with_segments_fields = {
+    'id': fields.String,
+    'position': fields.Integer,
+    'data_source_type': fields.String,
+    'data_source_info': fields.Raw(attribute='data_source_info_dict'),
+    'dataset_process_rule_id': fields.String,
+    'name': fields.String,
+    'created_from': fields.String,
+    'created_by': fields.String,
+    'created_at': TimestampField,
+    'tokens': fields.Integer,
+    'indexing_status': fields.String,
+    'error': fields.String,
+    'enabled': fields.Boolean,
+    'disabled_at': TimestampField,
+    'disabled_by': fields.String,
+    'archived': fields.Boolean,
+    'display_status': fields.String,
+    'word_count': fields.Integer,
+    'hit_count': fields.Integer,
+    'completed_segments': fields.Integer,
+    'total_segments': fields.Integer
+}
 
 class DocumentResource(Resource):
     def get_document(self, dataset_id: str, document_id: str) -> Document:
@@ -83,6 +107,23 @@ class DocumentResource(Resource):
 
         return document
 
+    def get_batch_documents(self, dataset_id: str, batch: str) -> List[Document]:
+        dataset = DatasetService.get_dataset(dataset_id)
+        if not dataset:
+            raise NotFound('Dataset not found.')
+
+        try:
+            DatasetService.check_dataset_permission(dataset, current_user)
+        except services.errors.account.NoPermissionError as e:
+            raise Forbidden(str(e))
+
+        documents = DocumentService.get_batch_documents(dataset_id, batch)
+
+        if not documents:
+            raise NotFound('Documents not found.')
+
+        return documents
+
 
 class GetProcessRuleApi(Resource):
     @setup_required
@@ -132,9 +173,9 @@ class DatasetDocumentListApi(Resource):
         dataset_id = str(dataset_id)
         page = request.args.get('page', default=1, type=int)
         limit = request.args.get('limit', default=20, type=int)
-        search = request.args.get('search', default=None, type=str)
+        search = request.args.get('keyword', default=None, type=str)
         sort = request.args.get('sort', default='-created_at', type=str)
-
+        fetch = request.args.get('fetch', default=False, type=bool)
         dataset = DatasetService.get_dataset(dataset_id)
         if not dataset:
             raise NotFound('Dataset not found.')
@@ -173,9 +214,20 @@ class DatasetDocumentListApi(Resource):
         paginated_documents = query.paginate(
             page=page, per_page=limit, max_per_page=100, error_out=False)
         documents = paginated_documents.items
-
+        if fetch:
+            for document in documents:
+                completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                                  DocumentSegment.document_id == str(document.id),
+                                                                  DocumentSegment.status != 're_segment').count()
+                total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+                document.completed_segments = completed_segments
+                document.total_segments = total_segments
+            data = marshal(documents, document_with_segments_fields)
+        else:
+            data = marshal(documents, document_fields)
         response = {
-            'data': marshal(documents, document_fields),
+            'data': data,
             'has_more': len(documents) == limit,
             'limit': limit,
             'total': paginated_documents.total,
@@ -184,10 +236,15 @@ class DatasetDocumentListApi(Resource):
 
         return response
 
+    documents_and_batch_fields = {
+        'documents': fields.List(fields.Nested(document_fields)),
+        'batch': fields.String
+    }
+
     @setup_required
     @login_required
     @account_initialization_required
-    @marshal_with(document_fields)
+    @marshal_with(documents_and_batch_fields)
     def post(self, dataset_id):
         dataset_id = str(dataset_id)
 
@@ -221,7 +278,7 @@ class DatasetDocumentListApi(Resource):
         DocumentService.document_create_args_validate(args)
 
         try:
-            document = DocumentService.save_document_with_dataset_id(dataset, args, current_user)
+            documents, batch = DocumentService.save_document_with_dataset_id(dataset, args, current_user)
         except ProviderTokenNotInitError:
             raise ProviderNotInitializeError()
         except QuotaExceededError:
@@ -229,13 +286,17 @@ class DatasetDocumentListApi(Resource):
         except ModelCurrentlyNotSupportError:
             raise ProviderModelCurrentlyNotSupportError()
 
-        return document
+        return {
+            'documents': documents,
+            'batch': batch
+        }
 
 
 class DatasetInitApi(Resource):
     dataset_and_document_fields = {
         'dataset': fields.Nested(dataset_fields),
-        'document': fields.Nested(document_fields)
+        'documents': fields.List(fields.Nested(document_fields)),
+        'batch': fields.String
     }
 
     @setup_required
@@ -258,7 +319,7 @@ class DatasetInitApi(Resource):
         DocumentService.document_create_args_validate(args)
 
         try:
-            dataset, document = DocumentService.save_document_without_dataset_id(
+            dataset, documents, batch = DocumentService.save_document_without_dataset_id(
                 tenant_id=current_user.current_tenant_id,
                 document_data=args,
                 account=current_user
@@ -272,7 +333,8 @@ class DatasetInitApi(Resource):
 
         response = {
             'dataset': dataset,
-            'document': document
+            'documents': documents,
+            'batch': batch
         }
 
         return response
@@ -317,11 +379,122 @@ class DocumentIndexingEstimateApi(DocumentResource):
                     raise NotFound('File not found.')
 
                 indexing_runner = IndexingRunner()
-                response = indexing_runner.indexing_estimate(file, data_process_rule_dict)
+
+                response = indexing_runner.file_indexing_estimate([file], data_process_rule_dict)
 
         return response
 
 
+class DocumentBatchIndexingEstimateApi(DocumentResource):
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, batch):
+        dataset_id = str(dataset_id)
+        batch = str(batch)
+        dataset = DatasetService.get_dataset(dataset_id)
+        if dataset is None:
+            raise NotFound("Dataset not found.")
+        documents = self.get_batch_documents(dataset_id, batch)
+        response = {
+            "tokens": 0,
+            "total_price": 0,
+            "currency": "USD",
+            "total_segments": 0,
+            "preview": []
+        }
+        if not documents:
+            return response
+        data_process_rule = documents[0].dataset_process_rule
+        data_process_rule_dict = data_process_rule.to_dict()
+        info_list = []
+        for document in documents:
+            if document.indexing_status in ['completed', 'error']:
+                raise DocumentAlreadyFinishedError()
+            data_source_info = document.data_source_info_dict
+            # format document files info
+            if data_source_info and 'upload_file_id' in data_source_info:
+                file_id = data_source_info['upload_file_id']
+                info_list.append(file_id)
+            # format document notion info
+            elif data_source_info and 'notion_workspace_id' in data_source_info and 'notion_page_id' in data_source_info:
+                pages = []
+                page = {
+                    'page_id': data_source_info['notion_page_id'],
+                    'type': data_source_info['type']
+                }
+                pages.append(page)
+                notion_info = {
+                    'workspace_id': data_source_info['notion_workspace_id'],
+                    'pages': pages
+                }
+                info_list.append(notion_info)
+
+        if dataset.data_source_type == 'upload_file':
+            file_details = db.session.query(UploadFile).filter(
+                UploadFile.tenant_id == current_user.current_tenant_id,
+                UploadFile.id in info_list
+            ).all()
+
+            if file_details is None:
+                raise NotFound("File not found.")
+
+            indexing_runner = IndexingRunner()
+            response = indexing_runner.file_indexing_estimate(file_details, data_process_rule_dict)
+        elif dataset.data_source_type:
+
+            indexing_runner = IndexingRunner()
+            response = indexing_runner.notion_indexing_estimate(info_list,
+                                                                data_process_rule_dict)
+        else:
+            raise ValueError('Data source type not support')
+        return response
+
+
+class DocumentBatchIndexingStatusApi(DocumentResource):
+    document_status_fields = {
+        'id': fields.String,
+        'indexing_status': fields.String,
+        'processing_started_at': TimestampField,
+        'parsing_completed_at': TimestampField,
+        'cleaning_completed_at': TimestampField,
+        'splitting_completed_at': TimestampField,
+        'completed_at': TimestampField,
+        'paused_at': TimestampField,
+        'error': fields.String,
+        'stopped_at': TimestampField,
+        'completed_segments': fields.Integer,
+        'total_segments': fields.Integer,
+    }
+
+    document_status_fields_list = {
+        'data': fields.List(fields.Nested(document_status_fields))
+    }
+
+    @setup_required
+    @login_required
+    @account_initialization_required
+    def get(self, dataset_id, batch):
+        dataset_id = str(dataset_id)
+        batch = str(batch)
+        documents = self.get_batch_documents(dataset_id, batch)
+        documents_status = []
+        for document in documents:
+            completed_segments = DocumentSegment.query.filter(DocumentSegment.completed_at.isnot(None),
+                                                              DocumentSegment.document_id == str(document.id),
+                                                              DocumentSegment.status != 're_segment').count()
+            total_segments = DocumentSegment.query.filter(DocumentSegment.document_id == str(document.id),
+                                                          DocumentSegment.status != 're_segment').count()
+            document.completed_segments = completed_segments
+            document.total_segments = total_segments
+            documents_status.append(marshal(document, self.document_status_fields))
+        data = {
+            'data': documents_status
+        }
+        return data
+
+
 class DocumentIndexingStatusApi(DocumentResource):
     document_status_fields = {
         'id': fields.String,
@@ -408,7 +581,7 @@ class DocumentDetailApi(DocumentResource):
                 'disabled_by': document.disabled_by,
                 'archived': document.archived,
                 'segment_count': document.segment_count,
-                'average_segment_length':   document.average_segment_length,
+                'average_segment_length': document.average_segment_length,
                 'hit_count': document.hit_count,
                 'display_status': document.display_status
             }
@@ -428,7 +601,7 @@ class DocumentDetailApi(DocumentResource):
                 'created_at': document.created_at.timestamp(),
                 'tokens': document.tokens,
                 'indexing_status': document.indexing_status,
-                'completed_at': int(document.completed_at.timestamp())if document.completed_at else None,
+                'completed_at': int(document.completed_at.timestamp()) if document.completed_at else None,
                 'updated_at': int(document.updated_at.timestamp()) if document.updated_at else None,
                 'indexing_latency': document.indexing_latency,
                 'error': document.error,
@@ -579,6 +752,8 @@ class DocumentStatusApi(DocumentResource):
             return {'result': 'success'}, 200
 
         elif action == "disable":
+            if not document.completed_at or document.indexing_status != 'completed':
+                raise InvalidActionError('Document is not completed.')
             if not document.enabled:
                 raise InvalidActionError('Document already disabled.')
 
@@ -678,6 +853,10 @@ api.add_resource(DatasetInitApi,
                  '/datasets/init')
 api.add_resource(DocumentIndexingEstimateApi,
                  '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-estimate')
+api.add_resource(DocumentBatchIndexingEstimateApi,
+                 '/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-estimate')
+api.add_resource(DocumentBatchIndexingStatusApi,
+                 '/datasets/<uuid:dataset_id>/batch/<string:batch>/indexing-status')
 api.add_resource(DocumentIndexingStatusApi,
                  '/datasets/<uuid:dataset_id>/documents/<uuid:document_id>/indexing-status')
 api.add_resource(DocumentDetailApi,