MINOR: First approach for document chunking. (#950)

Bimdata-io · Bimdata-io · commit 553264a6c6f5 · 2026-03-24T16:31:39.000Z
* WIP first approach for document chunking.

* More rag

* Rework vith content type framework

* Improve rag view with new contenttype framework

* multiples fixes &amp; tests

* Remove metadata &amp; add page_numbers.

* Fix how the AI app is loaded.

* Remove code that was wrongfuly commit on this branch

* Start moving exisint ai feature inside ai app.

* Add document content &amp; fixes

* Improve migration to not break cloud during deployment.
diff --git a/bimdata_api_client/api/collaboration_api.py b/bimdata_api_client/api/collaboration_api.py
@@ -9333,7 +9333,7 @@ def create_document(
     ):
         """Create a document  # noqa: E501
 
-        Create a document. If the document is one of {'POINT_CLOUD', 'IFC', 'OBJ', 'DXF', 'DWG', 'GLTF', 'PHOTOSPHERE'}, a model will be created and attached to this document  Required scopes: document:write  # noqa: E501
+        Create a document. If the document is one of {'IFC', 'POINT_CLOUD', 'OBJ', 'GLTF', 'PHOTOSPHERE', 'DXF', 'DWG'}, a model will be created and attached to this document  Required scopes: document:write  # noqa: E501
         This method makes a synchronous HTTP request by default. To make an
         asynchronous HTTP request, please pass async_req=True
 
diff --git a/bimdata_api_client/model/document_text.py b/bimdata_api_client/model/document_text.py
@@ -58,11 +58,11 @@ class DocumentText(ModelNormal):
     allowed_values = {
         ('language',): {
             'None': None,
-            'SPANISH': "spanish",
             'GERMAN': "german",
             'ENGLISH': "english",
-            'FRENCH': "french",
             'ITALIAN': "italian",
+            'FRENCH': "french",
+            'SPANISH': "spanish",
             'NULL': "null",
         },
     }
@@ -153,7 +153,7 @@ def _from_openapi_data(cls, id, *args, **kwargs):  # noqa: E501
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
             text (str, none_type): The full text representation of a document if the feature is enabled and the file format supported. [optional]  # noqa: E501
-            language (str, none_type): * `spanish` - spanish * `german` - german * `english` - english * `french` - french * `italian` - italian. [optional]  # noqa: E501
+            language (str, none_type): * `german` - german * `english` - english * `italian` - italian * `french` - french * `spanish` - spanish. [optional]  # noqa: E501
         """
 
         _check_type = kwargs.pop('_check_type', True)
@@ -237,7 +237,7 @@ def __init__(self, *args, **kwargs):  # noqa: E501
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
             text (str, none_type): The full text representation of a document if the feature is enabled and the file format supported. [optional]  # noqa: E501
-            language (str, none_type): * `spanish` - spanish * `german` - german * `english` - english * `french` - french * `italian` - italian. [optional]  # noqa: E501
+            language (str, none_type): * `german` - german * `english` - english * `italian` - italian * `french` - french * `spanish` - spanish. [optional]  # noqa: E501
         """
 
         _check_type = kwargs.pop('_check_type', True)
diff --git a/bimdata_api_client/model/patched_document_text_request.py b/bimdata_api_client/model/patched_document_text_request.py
@@ -58,11 +58,11 @@ class PatchedDocumentTextRequest(ModelNormal):
     allowed_values = {
         ('language',): {
             'None': None,
-            'SPANISH': "spanish",
             'GERMAN': "german",
             'ENGLISH': "english",
-            'FRENCH': "french",
             'ITALIAN': "italian",
+            'FRENCH': "french",
+            'SPANISH': "spanish",
             'NULL': "null",
         },
     }
@@ -147,7 +147,7 @@ def _from_openapi_data(cls, *args, **kwargs):  # noqa: E501
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
             text (str, none_type): The full text representation of a document if the feature is enabled and the file format supported. [optional]  # noqa: E501
-            language (str, none_type): * `spanish` - spanish * `german` - german * `english` - english * `french` - french * `italian` - italian. [optional]  # noqa: E501
+            language (str, none_type): * `german` - german * `english` - english * `italian` - italian * `french` - french * `spanish` - spanish. [optional]  # noqa: E501
         """
 
         _check_type = kwargs.pop('_check_type', True)
@@ -230,7 +230,7 @@ def __init__(self, *args, **kwargs):  # noqa: E501
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
             text (str, none_type): The full text representation of a document if the feature is enabled and the file format supported. [optional]  # noqa: E501
-            language (str, none_type): * `spanish` - spanish * `german` - german * `english` - english * `french` - french * `italian` - italian. [optional]  # noqa: E501
+            language (str, none_type): * `german` - german * `english` - english * `italian` - italian * `french` - french * `spanish` - spanish. [optional]  # noqa: E501
         """
 
         _check_type = kwargs.pop('_check_type', True)
diff --git a/bimdata_api_client/model/write_folder.py b/bimdata_api_client/model/write_folder.py
@@ -107,17 +107,17 @@ def openapi_types():
         """
         lazy_import()
         return {
-            'type': (str,),  # noqa: E501
-            'user_permission': (int,),  # noqa: E501
+            'id': (int,),  # noqa: E501
+            'updated_at': (datetime,),  # noqa: E501
             'groups_permissions': ([GroupFolderRead],),  # noqa: E501
             'created_at': (datetime,),  # noqa: E501
-            'nature': (str,),  # noqa: E501
-            'updated_at': (datetime,),  # noqa: E501
-            'created_by': (bool, date, datetime, dict, float, int, list, str, none_type,),  # noqa: E501
             'name': (str,),  # noqa: E501
-            'id': (int,),  # noqa: E501
-            'parent_id': (int, none_type,),  # noqa: E501
+            'user_permission': (int,),  # noqa: E501
+            'type': (str,),  # noqa: E501
+            'created_by': (bool, date, datetime, dict, float, int, list, str, none_type,),  # noqa: E501
+            'nature': (str,),  # noqa: E501
             'default_permission': (int,),  # noqa: E501
+            'parent_id': (int, none_type,),  # noqa: E501
             'children': ([WriteFolder], none_type,),  # noqa: E501
         }
 
@@ -127,48 +127,48 @@ def discriminator():
 
 
     attribute_map = {
-        'type': 'type',  # noqa: E501
-        'user_permission': 'user_permission',  # noqa: E501
+        'id': 'id',  # noqa: E501
+        'updated_at': 'updated_at',  # noqa: E501
         'groups_permissions': 'groups_permissions',  # noqa: E501
         'created_at': 'created_at',  # noqa: E501
-        'nature': 'nature',  # noqa: E501
-        'updated_at': 'updated_at',  # noqa: E501
-        'created_by': 'created_by',  # noqa: E501
         'name': 'name',  # noqa: E501
-        'id': 'id',  # noqa: E501
-        'parent_id': 'parent_id',  # noqa: E501
+        'user_permission': 'user_permission',  # noqa: E501
+        'type': 'type',  # noqa: E501
+        'created_by': 'created_by',  # noqa: E501
+        'nature': 'nature',  # noqa: E501
         'default_permission': 'default_permission',  # noqa: E501
+        'parent_id': 'parent_id',  # noqa: E501
         'children': 'children',  # noqa: E501
     }
 
     read_only_vars = {
-        'type',  # noqa: E501
-        'user_permission',  # noqa: E501
+        'id',  # noqa: E501
+        'updated_at',  # noqa: E501
         'groups_permissions',  # noqa: E501
         'created_at',  # noqa: E501
-        'nature',  # noqa: E501
-        'updated_at',  # noqa: E501
+        'user_permission',  # noqa: E501
+        'type',  # noqa: E501
         'created_by',  # noqa: E501
-        'id',  # noqa: E501
+        'nature',  # noqa: E501
     }
 
     _composed_schemas = {}
 
     @classmethod
     @convert_js_args_to_python_args
-    def _from_openapi_data(cls, type, user_permission, groups_permissions, created_at, nature, updated_at, created_by, name, id, *args, **kwargs):  # noqa: E501
+    def _from_openapi_data(cls, id, updated_at, groups_permissions, created_at, name, user_permission, type, created_by, nature, *args, **kwargs):  # noqa: E501
         """WriteFolder - a model defined in OpenAPI
 
         Args:
-            type (str): DEPRECATED: Use 'nature' instead. Value is \"Folder\". It is usefull to parse the tree and discriminate folders and files
-            user_permission (int): Aggregate of group user permissions and folder default permission
+            id (int):
+            updated_at (datetime): Date of the last update
             groups_permissions ([GroupFolderRead]): List of group permissions
             created_at (datetime): Creation date
-            nature (str): Value is \"Folder\". It is usefull to parse the tree and discriminate folders and files
-            updated_at (datetime): Date of the last update
-            created_by (bool, date, datetime, dict, float, int, list, str, none_type):
             name (str): Name of the folder
-            id (int):
+            user_permission (int): Aggregate of group user permissions and folder default permission
+            type (str): DEPRECATED: Use 'nature' instead. Value is \"Folder\". It is usefull to parse the tree and discriminate folders and files
+            created_by (bool, date, datetime, dict, float, int, list, str, none_type):
+            nature (str): Value is \"Folder\". It is usefull to parse the tree and discriminate folders and files
 
         Keyword Args:
             _check_type (bool): if True, values for parameters in openapi_types
@@ -201,8 +201,8 @@ def _from_openapi_data(cls, type, user_permission, groups_permissions, created_a
                                 Animal class but this time we won't travel
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
-            parent_id (int, none_type): [optional]  # noqa: E501
             default_permission (int): Permission for a Folder  * `1` - denied * `50` - read_only * `100` - read_write. [optional]  # noqa: E501
+            parent_id (int, none_type): [optional]  # noqa: E501
             children ([WriteFolder], none_type): [optional]  # noqa: E501
         """
 
@@ -231,15 +231,15 @@ def _from_openapi_data(cls, type, user_permission, groups_permissions, created_a
         self._configuration = _configuration
         self._visited_composed_classes = _visited_composed_classes + (self.__class__,)
 
-        self.type = type
-        self.user_permission = user_permission
+        self.id = id
+        self.updated_at = updated_at
         self.groups_permissions = groups_permissions
         self.created_at = created_at
-        self.nature = nature
-        self.updated_at = updated_at
-        self.created_by = created_by
         self.name = name
-        self.id = id
+        self.user_permission = user_permission
+        self.type = type
+        self.created_by = created_by
+        self.nature = nature
         for var_name, var_value in kwargs.items():
             if var_name not in self.attribute_map and \
                         self._configuration is not None and \
@@ -295,8 +295,8 @@ def __init__(self, name, *args, **kwargs):  # noqa: E501
                                 Animal class but this time we won't travel
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
-            parent_id (int, none_type): [optional]  # noqa: E501
             default_permission (int): Permission for a Folder  * `1` - denied * `50` - read_only * `100` - read_write. [optional]  # noqa: E501
+            parent_id (int, none_type): [optional]  # noqa: E501
             children ([WriteFolder], none_type): [optional]  # noqa: E501
         """
 
diff --git a/bimdata_api_client/model/write_folder_request.py b/bimdata_api_client/model/write_folder_request.py
@@ -102,8 +102,8 @@ def openapi_types():
         lazy_import()
         return {
             'name': (str,),  # noqa: E501
-            'parent_id': (int, none_type,),  # noqa: E501
             'default_permission': (int,),  # noqa: E501
+            'parent_id': (int, none_type,),  # noqa: E501
             'children': ([WriteFolder], none_type,),  # noqa: E501
         }
 
@@ -114,8 +114,8 @@ def discriminator():
 
     attribute_map = {
         'name': 'name',  # noqa: E501
-        'parent_id': 'parent_id',  # noqa: E501
         'default_permission': 'default_permission',  # noqa: E501
+        'parent_id': 'parent_id',  # noqa: E501
         'children': 'children',  # noqa: E501
     }
 
@@ -163,8 +163,8 @@ def _from_openapi_data(cls, name, *args, **kwargs):  # noqa: E501
                                 Animal class but this time we won't travel
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
-            parent_id (int, none_type): [optional]  # noqa: E501
             default_permission (int): Permission for a Folder  * `1` - denied * `50` - read_only * `100` - read_write. [optional]  # noqa: E501
+            parent_id (int, none_type): [optional]  # noqa: E501
             children ([WriteFolder], none_type): [optional]  # noqa: E501
         """
 
@@ -251,8 +251,8 @@ def __init__(self, name, *args, **kwargs):  # noqa: E501
                                 Animal class but this time we won't travel
                                 through its discriminator because we passed in
                                 _visited_composed_classes = (Animal,)
-            parent_id (int, none_type): [optional]  # noqa: E501
             default_permission (int): Permission for a Folder  * `1` - denied * `50` - read_only * `100` - read_write. [optional]  # noqa: E501
+            parent_id (int, none_type): [optional]  # noqa: E501
             children ([WriteFolder], none_type): [optional]  # noqa: E501
         """
 
diff --git a/docs/CollaborationApi.md b/docs/CollaborationApi.md
@@ -1808,14 +1808,14 @@ with bimdata_api_client.ApiClient(configuration) as api_client:
     id = 1 # int | A unique integer value identifying this project.
     write_folder_request = [
         WriteFolderRequest(
-            parent_id=1,
-            default_permission=1,
             name="name_example",
+            default_permission=1,
+            parent_id=1,
             children=[
                 WriteFolder(
-                    parent_id=1,
-                    default_permission=1,
                     name="name_example",
+                    default_permission=1,
+                    parent_id=1,
                     children=None,
                 ),
             ],
@@ -1872,7 +1872,7 @@ Name | Type | Description  | Notes
 
 Create a document
 
-Create a document. If the document is one of {'POINT_CLOUD', 'IFC', 'OBJ', 'DXF', 'DWG', 'GLTF', 'PHOTOSPHERE'}, a model will be created and attached to this document  Required scopes: document:write
+Create a document. If the document is one of {'IFC', 'POINT_CLOUD', 'OBJ', 'GLTF', 'PHOTOSPHERE', 'DXF', 'DWG'}, a model will be created and attached to this document  Required scopes: document:write
 
 ### Example
 
@@ -11251,7 +11251,7 @@ with bimdata_api_client.ApiClient(configuration) as api_client:
     project_pk = 1 # int | A unique integer value identifying this project.
     patched_document_text_request = PatchedDocumentTextRequest(
         text="text_example",
-        language="spanish",
+        language="german",
     ) # PatchedDocumentTextRequest |  (optional)
 
     # example passing only required values which don't have defaults set
diff --git a/docs/DocumentText.md b/docs/DocumentText.md
@@ -6,7 +6,7 @@ Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
 **id** | **int** |  | [readonly] 
 **text** | **str, none_type** | The full text representation of a document if the feature is enabled and the file format supported | [optional] 
-**language** | **str, none_type** | * &#x60;spanish&#x60; - spanish * &#x60;german&#x60; - german * &#x60;english&#x60; - english * &#x60;french&#x60; - french * &#x60;italian&#x60; - italian | [optional] 
+**language** | **str, none_type** | * &#x60;german&#x60; - german * &#x60;english&#x60; - english * &#x60;italian&#x60; - italian * &#x60;french&#x60; - french * &#x60;spanish&#x60; - spanish | [optional] 
 **any string name** | **bool, date, datetime, dict, float, int, list, str, none_type** | any string name can be used but the value must be the correct type | [optional]
 
 [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
diff --git a/docs/PatchedDocumentTextRequest.md b/docs/PatchedDocumentTextRequest.md
@@ -5,7 +5,7 @@
 Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
 **text** | **str, none_type** | The full text representation of a document if the feature is enabled and the file format supported | [optional] 
-**language** | **str, none_type** | * &#x60;spanish&#x60; - spanish * &#x60;german&#x60; - german * &#x60;english&#x60; - english * &#x60;french&#x60; - french * &#x60;italian&#x60; - italian | [optional] 
+**language** | **str, none_type** | * &#x60;german&#x60; - german * &#x60;english&#x60; - english * &#x60;italian&#x60; - italian * &#x60;french&#x60; - french * &#x60;spanish&#x60; - spanish | [optional] 
 **any string name** | **bool, date, datetime, dict, float, int, list, str, none_type** | any string name can be used but the value must be the correct type | [optional]
 
 [[Back to Model list]](../README.md#documentation-for-models) [[Back to API list]](../README.md#documentation-for-api-endpoints) [[Back to README]](../README.md)
diff --git a/docs/WriteFolder.md b/docs/WriteFolder.md
@@ -4,17 +4,17 @@
 ## Properties
 Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
-**type** | **str** | DEPRECATED: Use &#39;nature&#39; instead. Value is \&quot;Folder\&quot;. It is usefull to parse the tree and discriminate folders and files | [readonly] 
-**user_permission** | **int** | Aggregate of group user permissions and folder default permission | [readonly] 
+**id** | **int** |  | [readonly] 
+**updated_at** | **datetime** | Date of the last update | [readonly] 
 **groups_permissions** | [**[GroupFolderRead]**](GroupFolderRead.md) | List of group permissions | [readonly] 
 **created_at** | **datetime** | Creation date | [readonly] 
-**nature** | **str** | Value is \&quot;Folder\&quot;. It is usefull to parse the tree and discriminate folders and files | [readonly] 
-**updated_at** | **datetime** | Date of the last update | [readonly] 
-**created_by** | **bool, date, datetime, dict, float, int, list, str, none_type** |  | [readonly] 
 **name** | **str** | Name of the folder | 
-**id** | **int** |  | [readonly] 
-**parent_id** | **int, none_type** |  | [optional] 
+**user_permission** | **int** | Aggregate of group user permissions and folder default permission | [readonly] 
+**type** | **str** | DEPRECATED: Use &#39;nature&#39; instead. Value is \&quot;Folder\&quot;. It is usefull to parse the tree and discriminate folders and files | [readonly] 
+**created_by** | **bool, date, datetime, dict, float, int, list, str, none_type** |  | [readonly] 
+**nature** | **str** | Value is \&quot;Folder\&quot;. It is usefull to parse the tree and discriminate folders and files | [readonly] 
 **default_permission** | **int** | Permission for a Folder  * &#x60;1&#x60; - denied * &#x60;50&#x60; - read_only * &#x60;100&#x60; - read_write | [optional] 
+**parent_id** | **int, none_type** |  | [optional] 
 **children** | [**[WriteFolder], none_type**](WriteFolder.md) |  | [optional] 
 **any string name** | **bool, date, datetime, dict, float, int, list, str, none_type** | any string name can be used but the value must be the correct type | [optional]
 
diff --git a/docs/WriteFolderRequest.md b/docs/WriteFolderRequest.md
@@ -5,8 +5,8 @@
 Name | Type | Description | Notes
 ------------ | ------------- | ------------- | -------------
 **name** | **str** | Name of the folder | 
-**parent_id** | **int, none_type** |  | [optional] 
 **default_permission** | **int** | Permission for a Folder  * &#x60;1&#x60; - denied * &#x60;50&#x60; - read_only * &#x60;100&#x60; - read_write | [optional] 
+**parent_id** | **int, none_type** |  | [optional] 
 **children** | [**[WriteFolder], none_type**](WriteFolder.md) |  | [optional] 
 **any string name** | **bool, date, datetime, dict, float, int, list, str, none_type** | any string name can be used but the value must be the correct type | [optional]
 
