ibm-watsonx-orchestrate 1.11.0b0__py3-none-any.whl → 1.12.0b0__py3-none-any.whl

ibm_watsonx_orchestrate/client/service_instance.py

@@ -10,7 +10,7 @@ from ibm_cloud_sdk_core.authenticators import MCSPV2Authenticator
 from ibm_cloud_sdk_core.authenticators import IAMAuthenticator
 from ibm_cloud_sdk_core.authenticators import CloudPakForDataAuthenticator
 
-from ibm_watsonx_orchestrate.client.utils import check_token_validity, is_cpd_env
+from ibm_watsonx_orchestrate.client.utils import check_token_validity, is_cpd_env, is_ibm_cloud_platform
 from ibm_watsonx_orchestrate.client.base_service_instance import BaseServiceInstance
 from ibm_watsonx_orchestrate.cli.commands.environment.types import EnvironmentAuthType
 
@@ -21,14 +21,6 @@ from ibm_watsonx_orchestrate.client.client_errors import (
 import logging
 logger = logging.getLogger(__name__)
 
-from ibm_watsonx_orchestrate.cli.config import (
-    Config,
-    CONTEXT_SECTION_HEADER,
-    CONTEXT_ACTIVE_ENV_OPT,
-    ENVIRONMENTS_SECTION_HEADER,
-    ENV_WXO_URL_OPT
-)
-
 class ServiceInstance(BaseServiceInstance):
     """Connect, get details, and check usage of a Watson Machine Learning service instance."""
 
@@ -50,29 +42,28 @@ class ServiceInstance(BaseServiceInstance):
         return self._client.token
     
     def _create_token(self) -> str:
-        if not self._credentials.auth_type:
-            if ".cloud.ibm.com" in self._credentials.url:
-                logger.warning("Using IBM IAM Auth Type. If this is incorrect please use the '--type' flag to explicitly choose one of 'mcsp', 'mcsp_v1', 'mcsp_v2' or 'cpd' ")
-                return self._authenticate(EnvironmentAuthType.IBM_CLOUD_IAM)
-            elif is_cpd_env(self._credentials.url):
-                logger.warning("Using CPD Auth Type. If this is incorrect please use the '--type' flag to explicitly choose one of 'ibm_iam', 'mcsp', 'mcsp_v1' or 'mcsp_v2' ")
-                return self._authenticate(EnvironmentAuthType.CPD)
-            else:
-                logger.warning("Using MCSP Auth Type. If this is incorrect please use the '--type' flag to explicitly choose one of 'ibm_iam', 'mcsp_v1', 'mcsp_v2' or 'cpd' ")
-                try:
-                    return self._authenticate(EnvironmentAuthType.MCSP_V1)
-                except:
-                    return self._authenticate(EnvironmentAuthType.MCSP_V2)
-        auth_type = self._credentials.auth_type.lower()
+        inferred_auth_type = None
+        if is_ibm_cloud_platform(self._credentials.url):
+            inferred_auth_type = EnvironmentAuthType.IBM_CLOUD_IAM
+        elif is_cpd_env(self._credentials.url):
+            inferred_auth_type = EnvironmentAuthType.CPD
+        else:
+            inferred_auth_type = EnvironmentAuthType.MCSP
+        
+        if self._credentials.auth_type:
+            if self._credentials.auth_type != inferred_auth_type:
+                logger.warning(f"Overriding the default authentication type '{inferred_auth_type}' for url '{self._credentials.url}' with '{self._credentials.auth_type.lower()}'")
+            auth_type = self._credentials.auth_type.lower()
+        else:
+            inferred_type_options = [t for t in EnvironmentAuthType if t != inferred_auth_type]
+            logger.warning(f"Using '{inferred_auth_type}' Auth Type. If this is incorrect please use the '--type' flag to explicitly choose one of {', '.join(inferred_type_options[:-1])} or {inferred_type_options[-1]}")
+            auth_type = inferred_auth_type
+        
         if auth_type == "mcsp":
             try:
                 return self._authenticate(EnvironmentAuthType.MCSP_V1)
             except:
                 return self._authenticate(EnvironmentAuthType.MCSP_V2)
-        elif auth_type == "mcsp_v1":
-            return self._authenticate(EnvironmentAuthType.MCSP_V1)
-        elif auth_type == "mcsp_v2":
-            return self._authenticate(EnvironmentAuthType.MCSP_V2)
         else:
             return self._authenticate(auth_type)
 
@@ -100,13 +91,7 @@ class ServiceInstance(BaseServiceInstance):
                     if self._credentials.iam_url is not None: 
                         url = self._credentials.iam_url
                     else: 
-                        cfg = Config()
-                        env_cfg = cfg.get(ENVIRONMENTS_SECTION_HEADER)
-                        matching_wxo_url = next(
-                            (env_config['wxo_url'] for env_config in env_cfg.values() if 'bypass_ssl' in env_config and 'verify' in env_config),
-                            None
-                        )
-                        base_url = matching_wxo_url.split("/orchestrate")[0]
+                        base_url = self._credentials.url.split("/orchestrate")[0]
                         url = f"{base_url}/icp4d-api"
 
                     password = self._credentials.password if self._credentials.password is not None else None

ibm_watsonx_orchestrate/client/tools/tempus_client.py

@@ -42,4 +42,7 @@ class TempusClient(BaseAPIClient):
     
     def arun_flow(self, flow_id: str, input: dict) -> dict:
         return self._post(f"/flows/{flow_id}/versions/TIP/run/async", data=input)
+    
+    def get_flow_model(self, flow_id: str, version: str = "TIP") -> dict:
+        return self._get(f"/flow-models/{flow_id}/versions/{version}")
 

ibm_watsonx_orchestrate/client/tools/tool_client.py

@@ -10,7 +10,7 @@ class ToolClient(BaseAPIClient):
     def create(self, payload: dict) -> dict:
         return self._post("/tools", data=payload)
 
-    def get(self) -> dict:
+    def get(self) -> dict:        
         return self._get("/tools")
 
     def update(self, agent_id: str, data: dict) -> dict:
@@ -21,10 +21,13 @@ class ToolClient(BaseAPIClient):
 
     def upload_tools_artifact(self, tool_id: str, file_path: str) -> dict:
         return self._post(f"/tools/{tool_id}/upload", files={"file": (f"{tool_id}.zip", open(file_path, "rb"), "application/zip", {"Expires": "0"})})
-    
+
     def download_tools_artifact(self, tool_id: str) -> bytes:
         response = self._get(f"/tools/{tool_id}/download", return_raw=True)
         return response.content
+    
+    def download_tools_json(self, tool_id: str) -> dict:
+        return self.download_tools_artifact(tool_id)
 
     def get_draft_by_name(self, tool_name: str) -> List[dict]:
         return self.get_drafts_by_names([tool_name])

ibm_watsonx_orchestrate/client/utils.py

@@ -1,3 +1,5 @@
+import platform
+
 from ibm_watsonx_orchestrate.cli.config import (
     Config,
     DEFAULT_CONFIG_FILE_FOLDER,
@@ -66,7 +68,7 @@ def is_ibm_cloud_platform(url:str | None = None) -> bool:
     if url is None:
         url = get_current_env_url()
 
-    if url.__contains__("cloud.ibm.com"):
+    if ".cloud.ibm.com" in url:
         return True
     return False
 
@@ -161,6 +163,8 @@ def instantiate_client(client: type[T] , url: str | None=None) -> T:
                     client_instance = client(base_url=url, api_key=token, is_local=is_local_dev(url), verify=False)
                 elif verify is not None:
                     client_instance = client(base_url=url, api_key=token, is_local=is_local_dev(url), verify=verify)
+                else:
+                    client_instance = client(base_url=url, api_key=token, is_local=is_local_dev(url))
             else:
                 client_instance = client(base_url=url, api_key=token, is_local=is_local_dev(url))
 
@@ -168,4 +172,32 @@ def instantiate_client(client: type[T] , url: str | None=None) -> T:
     except FileNotFoundError as e:
         message = "No active environment found. Please run `orchestrate env activate` to activate an environment"
         logger.error(message)
-        raise FileNotFoundError(message)
+        raise FileNotFoundError(message)
+
+
+def get_architecture () -> str:
+    arch = platform.machine().lower()
+    if arch in ("amd64", "x86_64"):
+        return "amd64"
+
+    elif arch == "i386":
+        return "386"
+
+    elif arch in ("aarch64", "arm64", "arm"):
+        return "arm"
+
+    else:
+        raise Exception("Unsupported architecture %s" % arch)
+
+
+def is_arm_architecture () -> bool:
+    return platform.machine().lower() in ("aarch64", "arm64", "arm")
+
+
+def get_os_type () -> str:
+    system = platform.system().lower()
+    if system in ("linux", "darwin", "windows"):
+        return system
+
+    else:
+        raise Exception("Unsupported operating system %s" % system)

ibm_watsonx_orchestrate/docker/compose-lite.yml

@@ -133,8 +133,9 @@ services:
       DOCPROC_ENABLED: ${DOCPROC_ENABLED:-false}
       IS_OBSERVABILITY_FEATURE_ENABLED: "true"
       ALLOW_INSECURE_TLS: "true"
-      ENABLE_EDIT_PROMPTS: "true"
+      ENABLE_EDIT_PROMPTS: "false"
       LANGFLOW_ENABLED: ${LANGFLOW_ENABLED:-false}
+      ENABLE_EMBED_SCRIPT: "true"
     command: 'npm start'
     ports:
       - "4025:4025"
@@ -378,6 +379,7 @@ services:
       IS_WXO_LITE: "TRUE"
       TRM_BASE_URL: http://tools-runtime-manager:8080
       AGENT_STEP_DETAILS: redis://wxo-server-redis:6379/0
+      RECURSION_LIMIT: ${RECURSION_LIMIT}
       AGENT_GATEWAY_URI: http://wxo-agent-gateway:8989
       JWT_SECRET: ${JWT_SECRET}
       POSTGRES_URL: postgresql://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@wxo-server-db:5432/postgres
@@ -886,18 +888,18 @@ services:
       PREFLIGHT_MAX_SIZE: 10Mb
       PREFLIGHT_MAX_PAGES: 600
       RUNTIME_LIBRARY: "watson_doc_understanding"
-      WXAI_API_KEY: ${WXAI_API_KEY:-}
-      WXAI_IMAGE_DESCRIPTION_MODEL_ID: ${WXAI_IMAGE_DESCRIPTION_MODEL_ID:-mistralai/pixtral-12b}
-      WXAI_IMAGE_DESCRIPTION_PROJECT_ID: ${WXAI_IMAGE_DESCRIPTION_PROJECT_ID:-}
-      WXAI_KVP_MODEL_ID: ${WXAI_KVP_MODEL_ID:-}
-      WXAI_KVP_PROJECT_ID: ${WXAI_KVP_PROJECT_ID:-}
-      WXAI_SEMANTIC_KVP_PROJECT_ID: ${WXAI_SEMANTIC_KVP_PROJECT_ID:-}
-      WXAI_SEMANTIC_KVP_MODEL_ID: ${WXAI_SEMANTIC_KVP_MODEL_ID:-mistralai/pixtral-12b}
-      WXAI_SEMANTIC_KVP_SPACE_ID: ${WXAI_SEMANTIC_KVP_SPACE_ID:-}
-      WXAI_URL: ${WXAI_URL:-}
+      WXAI_API_KEY: ${WXAI_API_KEY:-"gateway"}
+      WXAI_IMAGE_DESCRIPTION_MODEL_ID: ${WXAI_IMAGE_DESCRIPTION_MODEL_ID:-mistralai/mistral-small-3-1-24b-instruct-2503}
+      WXAI_IMAGE_DESCRIPTION_SPACE_ID: ${WATSONX_SPACE_ID:-}
+      WXAI_KVP_MODEL_ID: ${WXAI_KVP_MODEL_ID:-mistralai/mistral-small-3-1-24b-instruct-2503}
+      WXAI_KVP_SPACE_ID: ${WATSONX_SPACE_ID:-}
+      WXAI_SEMANTIC_KVP_MODEL_ID: ${WXAI_SEMANTIC_KVP_MODEL_ID:-mistralai/mistral-small-3-1-24b-instruct-2503}
+      WXAI_SEMANTIC_KVP_SPACE_ID: ${WATSONX_SPACE_ID:-}
+      WXAI_URL: ${AI_GATEWAY_BASE_URL:-}
       WXAI_USERNAME: ${WXAI_USERNAME:-}
       WXAI_INSTANCE_ID: ${WXAI_INSTANCE_ID:-}
-      WXAI_VERSION: ${WXAI_VERSION:-5.1}
+      WXAI_VERSION: ${WXAI_VERSION:-2023-05-29}
+      WXAI_PROVIDER: ${WXAI_PROVIDER:-gateway}
       
     profiles:
       - docproc
@@ -1139,7 +1141,7 @@ services:
     environment:
       LANGFLOW_PORT: 7861
       LANGFLOW_DATABASE_URL: postgresql://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD:-postgres}@wxo-server-db:5432/langflow
-      LANGFLOW_CONFIG_DIR: app/langflow
+      LANGFLOW_CONFIG_DIR: /app/app/langflow
     volumes:
       - langflow-data:/app/langflow
 

ibm_watsonx_orchestrate/docker/default.env

@@ -36,7 +36,7 @@ DB_ENCRYPTION_KEY=dummy_db_encryption_key
 BASE_URL=dummy_base_url
 SERVER_TYPE=CELERY
 SQLALCHEMY_DEBUG=false
-
+RECURSION_LIMIT=50
 LANGFUSE_HOST=http://host.docker.internal:3010
 LANGFUSE_EMAIL=orchestrate@ibm.com
 LANGFUSE_USERNAME=orchestrate
@@ -58,10 +58,10 @@ REGISTRY_URL=
 
 
 
-SERVER_TAG=29-08-2025-59ef405
+SERVER_TAG=09-09-2025-2164abd
 SERVER_REGISTRY=
 
-WORKER_TAG=29-08-2025-cf32b2d
+WORKER_TAG=09-09-2025-2164abd
 WORKER_REGISTRY=
 
 AI_GATEWAY_TAG=20-08-2025-9ed6d40
@@ -73,9 +73,9 @@ AGENT_GATEWAY_REGISTRY=
 DB_REGISTRY=
 # If you build multiarch set all three of these to the same, we have a pr against main
 # to not have this separation, but we can merge it later
-DBTAG=29-07-2025-9f3661b
-AMDDBTAG=29-07-2025-9f3661b
-ARM64DBTAG=29-07-2025-9f3661b
+DBTAG=09-09-2025-fb76647
+AMDDBTAG=09-09-2025-fb76647
+ARM64DBTAG=09-09-2025-fb76647
 
 UI_REGISTRY=
 UITAG=29-08-2025
@@ -83,16 +83,16 @@ UITAG=29-08-2025
 CM_REGISTRY=
 CM_TAG=24-07-2025
 
-TRM_TAG=19-08-2025-fe105eb0b950ff304f712a1a5b9fa3cba92d09da
+TRM_TAG=09-09-2025-6e9d73d
 TRM_REGISTRY=
 
-TR_TAG=25-08-2025-58ae475
+TR_TAG=09-09-2025-6e9d73d
 TR_REGISTRY=
 
-BUILDER_TAG=27-08-2025-7432aca
+BUILDER_TAG=12-09-2025-e441686
 BUILDER_REGISTRY=
 
-FLOW_RUNTIME_TAG=26-08-2025-3b7f19e
+FLOW_RUNTIME_TAG=15-09-2025-2e8478c
 FLOW_RUMTIME_REGISTRY=
 
 
@@ -105,23 +105,23 @@ JAEGER_PROXY_REGISTRY=
 SOCKET_HANDLER_TAG=29-05-2025
 SOCKET_HANDLER_REGISTRY=
 
-CPE_TAG=18-08-2025-ae1308e
+CPE_TAG=29-08-2025-e612bea
 CPE_REGISTRY=
 
-VOICE_CONTROLLER_TAG=12-08-2025
+VOICE_CONTROLLER_TAG=12-09-2025-0e04772
 VOICE_CONTROLLER_REGISTRY=
 
 LANGFLOW_TAG=
 LANGFLOW_IMAGE=
 
 # IBM Document Processing
-WDU_TAG=2.6.1
+WDU_TAG=2.7.0
 WDU_REGISTRY=
 
-DOCPROC_DPS_TAG=20250815-010747-277-173db2a
-DOCPROC_LLMSERVICE_TAG=20250820-153924-128-55cf4d5
-DOCPROC_CACHE_TAG=20250814-master-82-cf33f87
-DOCPROC_DPI_TAG=20250815-004755-273-e65f26b4
+DOCPROC_DPS_TAG=20250904-181617-287-1ca2bf1
+DOCPROC_LLMSERVICE_TAG=20250904-main-136-b94360e
+DOCPROC_CACHE_TAG=20250902-master-83-748d456
+DOCPROC_DPI_TAG=20250905-092707-286-8c6b8f92
 DOCPROC_REGISTRY=
 
 # END -- IMAGE REGISTRIES AND TAGS

ibm_watsonx_orchestrate/flow_builder/flows/flow.py

@@ -440,7 +440,7 @@ class Flow(Node):
         node = self._add_node(node)
         return cast(PromptNode, node)
     
-    def docclassfier(self, 
+    def docclassifier(self, 
             name: str, 
             llm : str = "watsonx/meta-llama/llama-3-2-90b-vision-instruct",
             version: str = "TIP",
@@ -607,6 +607,7 @@ class Flow(Node):
             display_name: str|None=None,
             description: str | None = None,
             input_map: DataMap = None,
+            document_structure: bool = False,
             kvp_schemas: list[DocProcKVPSchema] = None,
             enable_hw: bool = False) -> DocProcNode:
 
@@ -631,6 +632,7 @@ class Flow(Node):
             output_schema=_get_tool_response_body(output_schema_obj),
             output_schema_object = output_schema_obj,
             task=task,
+            document_structure=document_structure,
             plain_text_reading_order=plain_text_reading_order,
             enable_hw=enable_hw,
             kvp_schemas=kvp_schemas

ibm_watsonx_orchestrate/flow_builder/types.py

@@ -338,13 +338,15 @@ class DocProcSpec(DocProcCommonNodeSpec):
         description="Optional list of key-value pair schemas to use for extraction.",
         default=None)
     plain_text_reading_order : PlainTextReadingOrder = Field(default=PlainTextReadingOrder.block_structure)
-
+    document_structure: bool = Field(default=False,description="Requests the entire document structure computed by WDU to be returned")
+    
     def __init__(self, **data):
         super().__init__(**data)
         self.kind = "docproc"
 
     def to_json(self) -> dict[str, Any]:
         model_spec = super().to_json()
+        model_spec["document_structure"] = self.document_structure
         model_spec["task"] = self.task
         if self.plain_text_reading_order != PlainTextReadingOrder.block_structure:
             model_spec["plain_text_reading_order"] = self.plain_text_reading_order
@@ -1000,6 +1002,255 @@ class Assignment(BaseModel):
     default_value: Any | None = None
     metadata: dict = Field(default_factory=dict[str, Any])
 
+class Style(BaseModel):
+    style_id: str = Field(default="", description="Style Identifier which will be used for reference in other objects")
+    font_size: str = Field(default="", description="Font size")
+    font_name: str = Field(default="", description="Font name")
+    is_bold: str = Field(default="", description="Whether or not the the font is bold")
+    is_italic: str = Field(default="", description="Whether or not the the font is italic")
+
+class PageMetadata(BaseModel):
+    page_number: Optional[int] = Field(default=None, description="Page number, starting from 1")
+    page_image_width: Optional[int] = Field(default=None, description="Width of the page in pixels, assuming the page is an image with default 72 DPI")
+    page_image_height: Optional[int] = Field(default=None, description="Height of the page in pixels, assuming the page is an image with default 72 DPI")
+    dpi: Optional[int] = Field(default=None, description="The DPI to use for the page image, as specified in the input to the API")
+    document_type: Optional[str] = Field(default="", description="Document type")
+
+class Metadata(BaseModel):
+    num_pages: int = Field(description="Total number of pages in the document")
+    title: Optional[str] = Field(default=None, description="Document title as obtained from source document")
+    language: Optional[str] = Field(default=None, description="Determined by the lang specifier in the <html> tag, or <meta> tag")
+    url: Optional[str] = Field(default=None, description="URL of the document")
+    keywords: Optional[str] = Field(default=None, description="Keywords associated with document")
+    author: Optional[str] = Field(default=None, description="Author of the document")
+    publication_date: Optional[str] = Field(default=None, description="Best effort bases for a publication date (may be the creation date)")
+    subject: Optional[str] = Field(default=None, description="Subject as obtained from the source document")
+    charset: str = Field(default="", description="Character set used for the output")
+    output_tokens_flag: Optional[bool] = Field(default=None, description="Whether individual tokens are output, as specified in the input to the API")
+    output_bounding_boxes_flag: Optional[bool] = Field(default=None, description="Whether bounding boxes are output, as requested in the input to the API")
+    pages_metadata: Optional[List[PageMetadata]] = Field(default=[], description="List of page-level metadata objects")
+
+class Section(BaseModel):
+    id: str = Field(default="", description="Unique identifier for the section")
+    parent_id: str = Field(default="", description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(default="", description="Unique Ids of first level children structures under this structure in correct sequence")
+    section_number: str = Field(default="", description="Section identifier identified in the document")
+    section_level: str = Field(default="", description="Nesting level of section identified in the document")
+    bbox_list: Optional[List[DocProcBoundingBox]] = Field(default=None, description="Cross-pages bounding boxes of that section")
+
+
+class SectionTitle(BaseModel):
+    id: str = Field(default="", description="Unique identifier for the section")
+    parent_id: str = Field(default="", description="Unique identifier which denotes parent of this structure")
+    children_ids: Optional[List[str]] = Field(default=None, description="Unique Ids of first level children structures under this structure in correct sequence")
+    text_alignment: Optional[str] = Field(default="", description="Text alignment of the section title")
+    text: str = Field(default="", description="Text property added to all objects")
+    bbox: Optional[DocProcBoundingBox] = Field(default=None, description="The bounding box of the section title")
+
+class List_(BaseModel):
+    id: str = Field(..., description="Unique identifier for the list")
+    title: Optional[str] = Field(None, description="List title")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(..., description="Unique Ids of first level children structures under this structure in correct sequence")
+    bbox_list: Optional[List[DocProcBoundingBox]] = Field(None, description="Cross-pages bounding boxes of that table")
+
+
+class ListItem(BaseModel):
+    id: str = Field(..., description="Unique identifier for the list item")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: Optional[List[str]] = Field(None, description="Unique Ids of first level children structures under this structure in correct sequence")
+    text: str = Field(..., description="Text property added to all objects")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the list item")
+
+
+class ListIdentifier(BaseModel):
+    id: str = Field(..., description="Unique identifier for the list item")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(..., description="Unique Ids of first level children structures under this structure in correct sequence")
+
+class Table(BaseModel):
+    id: str = Field(..., description="Unique identifier for the table")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(..., description="Unique Ids of first level children structures under this structure in correct sequence, in this case, table rows")
+    bbox_list: Optional[List[DocProcBoundingBox]] = Field(None, description="Cross-pages bounding boxes of that table")
+
+
+class TableRow(BaseModel):
+    id: str = Field(..., description="Unique identifier for the table row")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(..., description="Unique Ids of first level children structures under this structure in correct sequence, in this case, table cells")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the table row")
+
+
+class TableCell(BaseModel):
+    id: str = Field(..., description="Unique identifier for the table cell")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    is_row_header: bool = Field(..., description="Whether the cell is part of row header or not")
+    is_col_header: bool = Field(..., description="Whether the cell is part of column header or not")
+    col_span: int = Field(..., description="Column span of the cell")
+    row_span: int = Field(..., description="Row span of the cell")
+    col_start: int = Field(..., description="Column start of the cell within the table")
+    row_start: int = Field(..., description="Row start of the cell within the table")
+    children_ids: Optional[List[str]] = Field(None, description="Children structures, e.g., paragraphs")
+    text: str = Field(..., description="Text property added to all objects")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the table cell")
+
+class Subscript(BaseModel):
+    id: str = Field(..., description="Unique identifier for the subscript")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(default_factory=list, description="Unique Ids of first level children structures under this structure in correct sequence")
+    token_id_ref: Optional[str] = Field(None, description="Id of the token to which the subscript belongs")
+    text: str = Field(..., description="Text property added to all objects")
+
+
+class Superscript(BaseModel):
+    id: str = Field(..., description="Unique identifier for the superscript")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    footnote_ref: str = Field(..., description="Matching footnote id found on the page")
+    token_id_ref: Optional[str] = Field(None, description="Id of the token to which the superscript belongs")
+    children_ids: List[str] = Field(default_factory=list, description="Unique Ids of first level children structures under this structure in correct sequence")
+    text: str = Field(..., description="Text property added to all objects")
+
+
+class Footnote(BaseModel):
+    id: str = Field(..., description="Unique identifier for the footnote")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(default_factory=list, description="Unique Ids of first level children structures under this structure in correct sequence")
+    text: str = Field(..., description="Text property added to all objects")
+
+
+class Paragraph(BaseModel):
+    id: str = Field(..., description="Unique identifier for the paragraph")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(default_factory=list, description="Unique Ids of first level children structures under this structure in correct sequence, in this case, tokens")
+    text_alignment: Optional[str] = Field(None, description="Text alignment of the paragraph")
+    indentation: Optional[int] = Field(None, description="Paragraph indentation")
+    text: str = Field(..., description="Text property added to all objects")
+    bbox_list: Optional[DocProcBoundingBox] = Field(default=None, description="Cross-pages bounding boxes of that Paragraph")
+
+
+class CodeSnippet(BaseModel):
+    id: str = Field(..., description="Unique identifier for the code snippet")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(default_factory=list, description="Unique Ids of first level children structures under this structure in correct sequence, in this case, tokens")
+    text: str = Field(..., description="Text of the code snippet. It can contain multiple lines, including empty lines or lines with leading spaces.")
+
+
+class Picture(BaseModel):
+    id: str = Field(..., description="Unique identifier for the picture")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    children_ids: List[str] = Field(default_factory=list, description="Unique identifiers of the tokens extracted from this picture, if any")
+    text: Optional[str] = Field(None, description="Text extracted from this picture")
+    verbalization: Optional[str] = Field(None, description="Verbalization of this picture")
+    path: Optional[str] = Field(None, description="Path in the output location where the picture itself was saved")
+    picture_class: Optional[str] = Field(None, description="The classification result of the picture")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the picture in the context of the page, expressed as pixel coordinates with respect to pages_metadata.page_image_height and pages_metadata.page_image_width")
+
+
+class PageHeader(BaseModel):
+    id: str = Field(..., description="Unique identifier for the page header")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    text: Optional[str] = Field(None, description="The page header text")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the page header")
+    children_ids: List[str] = Field(default_factory=list, description="Unique Ids of first level children structures under this structure in correct sequence, in this case, tokens")
+
+
+class PageFooter(BaseModel):
+    id: str = Field(..., description="Unique identifier for the page footer")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    text: Optional[str] = Field(None, description="The page footer text")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the page footer")
+    children_ids: List[str] = Field(default_factory=list, description="Unique Ids of first level children structures under this structure in correct sequence, in this case, tokens")
+
+
+class BarCode(BaseModel):
+    id: str = Field(..., description="Unique identifier for the bar code")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    text: Optional[str] = Field(None, description="The value of the bar code")
+    format: Optional[str] = Field(None, description="The format of the bar code")
+    path: Optional[str] = Field(None, description="Path in the output location where the var code picture is saved")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the bar code in the context of the page, expressed as pixel coordinates with respect to pages_metadata.page_image_height and pages_metadata.page_image_width")
+
+
+class QRCode(BaseModel):
+    id: str = Field(..., description="Unique identifier for the QR code")
+    parent_id: str = Field(..., description="Unique identifier which denotes parent of this structure")
+    text: Optional[str] = Field(None, description="The value of the QR code")
+    path: Optional[str] = Field(None, description="Path in the output location where the var code picture is saved")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the bar code in the context of the page, expressed as pixel coordinates with respect to pages_metadata.page_image_height and pages_metadata.page_image_width")
+
+
+class Token(BaseModel):
+    id: str = Field(..., description="Unique identifier for the list identifier")
+    parent_id: Optional[str] = Field(None, description="Unique identifier which denotes parent of this structure")
+    style_id: Optional[str] = Field(None, description="Identifier of the style object associated with this token")
+    text: str = Field(..., description="Actual text of the token")
+    bbox: Optional[DocProcBoundingBox] = Field(None, description="The bounding box of the token in the context of the page, expressed as pixel coordinates with respect to pages_metadata.page_image_height and pages_metadata.page_image_width")
+    confidence: Optional[float] = Field(None, description="Confidence score for the token")
+
+class Structures(BaseModel):
+    sections: Optional[List[Section]] = Field(
+        default=None, description="All Section objects found in the document"
+    )
+    section_titles: Optional[List[SectionTitle]] = Field(
+        default=None, description="All SectionTitle objects found in the document"
+    )
+    lists: Optional[List[List_]] = Field(
+        default=None, description="All List objects found in the document"
+    )
+    list_items: Optional[List[ListItem]] = Field(
+        default=None, description="All ListItem objects found in the document"
+    )
+    list_identifiers: Optional[List[ListIdentifier]] = Field(
+        default=None, description="All ListIdentifier objects found in the document"
+    )
+    tables: Optional[List[Table]] = Field(
+        default=None, description="All Table objects found in the document"
+    )
+    table_rows: Optional[List[TableRow]] = Field(
+        default=None, description="All TableRow objects found in the document"
+    )
+    table_cells: Optional[List[TableCell]] = Field(
+        default=None, description="All TableCell objects found in the document"
+    )
+    subscripts: Optional[List[Subscript]] = Field(
+        default=None, description="All Subscript objects found in the document"
+    )
+    superscripts: Optional[List[Superscript]] = Field(
+        default=None, description="All Superscript objects found in the document"
+    )
+    footnotes: Optional[List[Footnote]] = Field(
+        default=None, description="All Footnote objects found in the document"
+    )
+    paragraphs: Optional[List[Paragraph]] = Field(
+        default=None, description="All Paragraph objects found in the document"
+    )
+    code_snippets: Optional[List[CodeSnippet]] = Field(
+        default=None, description="All CodeSnippet objects found in the document"
+    )
+    pictures: Optional[List[Picture]] = Field(
+        default=None, description="All Picture objects found in the document"
+    )
+    page_headers: Optional[List[PageHeader]] = Field(
+        default=None, description="All PageHeader objects found in the document"
+    )
+    page_footers: Optional[List[PageFooter]] = Field(
+        default=None, description="All PageFooter objects found in the document"
+    )
+    bar_codes: Optional[List[BarCode]] = Field(
+        default=None, description="All BarCode objects found in the document"
+    )
+    tokens: Optional[List[Token]] = Field(
+        default=None, description="All Token objects found in the document"
+    )
+
+class AssemblyJsonOutput(BaseModel):
+    metadata: Metadata = Field(description="Metadata about this document")
+    styles: Optional[List[Style]] = Field(description="Font styles used in this document")
+    kvps: Optional[DocProcKVP] = Field(description="Key value pairs found in the document")
+    top_level_structures: List[str] = Field(default=[], description="Array of ids of the top level structures which belong directly under the document")
+    all_structures: Structures = Field(default=None, description="An object containing of all flattened structures identified in the document")
+
 class LanguageCode(StrEnum):
     '''
     The ISO-639 language codes understood by Document Processing functions.