robosystems-client 0.2.2__py3-none-any.whl → 0.2.3__py3-none-any.whl

robosystems_client/api/tables/update_file_status.py

@@ -0,0 +1,539 @@
+from http import HTTPStatus
+from typing import Any, Optional, Union, cast
+
+import httpx
+
+from ... import errors
+from ...client import AuthenticatedClient, Client
+from ...models.error_response import ErrorResponse
+from ...models.file_status_update import FileStatusUpdate
+from ...models.http_validation_error import HTTPValidationError
+from ...models.update_file_status_response_updatefilestatus import (
+  UpdateFileStatusResponseUpdatefilestatus,
+)
+from ...types import UNSET, Response, Unset
+
+
+def _get_kwargs(
+  graph_id: str,
+  file_id: str,
+  *,
+  body: FileStatusUpdate,
+  token: Union[None, Unset, str] = UNSET,
+  authorization: Union[None, Unset, str] = UNSET,
+) -> dict[str, Any]:
+  headers: dict[str, Any] = {}
+  if not isinstance(authorization, Unset):
+    headers["authorization"] = authorization
+
+  params: dict[str, Any] = {}
+
+  json_token: Union[None, Unset, str]
+  if isinstance(token, Unset):
+    json_token = UNSET
+  else:
+    json_token = token
+  params["token"] = json_token
+
+  params = {k: v for k, v in params.items() if v is not UNSET and v is not None}
+
+  _kwargs: dict[str, Any] = {
+    "method": "patch",
+    "url": f"/v1/graphs/{graph_id}/tables/files/{file_id}",
+    "params": params,
+  }
+
+  _kwargs["json"] = body.to_dict()
+
+  headers["Content-Type"] = "application/json"
+
+  _kwargs["headers"] = headers
+  return _kwargs
+
+
+def _parse_response(
+  *, client: Union[AuthenticatedClient, Client], response: httpx.Response
+) -> Optional[
+  Union[
+    Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus
+  ]
+]:
+  if response.status_code == 200:
+    response_200 = UpdateFileStatusResponseUpdatefilestatus.from_dict(response.json())
+
+    return response_200
+
+  if response.status_code == 400:
+    response_400 = ErrorResponse.from_dict(response.json())
+
+    return response_400
+
+  if response.status_code == 401:
+    response_401 = cast(Any, None)
+    return response_401
+
+  if response.status_code == 403:
+    response_403 = ErrorResponse.from_dict(response.json())
+
+    return response_403
+
+  if response.status_code == 404:
+    response_404 = ErrorResponse.from_dict(response.json())
+
+    return response_404
+
+  if response.status_code == 413:
+    response_413 = ErrorResponse.from_dict(response.json())
+
+    return response_413
+
+  if response.status_code == 422:
+    response_422 = HTTPValidationError.from_dict(response.json())
+
+    return response_422
+
+  if response.status_code == 500:
+    response_500 = cast(Any, None)
+    return response_500
+
+  if client.raise_on_unexpected_status:
+    raise errors.UnexpectedStatus(response.status_code, response.content)
+  else:
+    return None
+
+
+def _build_response(
+  *, client: Union[AuthenticatedClient, Client], response: httpx.Response
+) -> Response[
+  Union[
+    Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus
+  ]
+]:
+  return Response(
+    status_code=HTTPStatus(response.status_code),
+    content=response.content,
+    headers=response.headers,
+    parsed=_parse_response(client=client, response=response),
+  )
+
+
+def sync_detailed(
+  graph_id: str,
+  file_id: str,
+  *,
+  client: AuthenticatedClient,
+  body: FileStatusUpdate,
+  token: Union[None, Unset, str] = UNSET,
+  authorization: Union[None, Unset, str] = UNSET,
+) -> Response[
+  Union[
+    Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus
+  ]
+]:
+  r""" Update File Upload Status
+
+     Update file status after upload completes.
+
+    **Purpose:**
+    Mark files as uploaded after successful S3 upload. The backend validates
+    the file, calculates size and row count, enforces storage limits, and
+    registers the DuckDB table for queries.
+
+    **Status Values:**
+    - `uploaded`: File successfully uploaded to S3 (triggers validation)
+    - `disabled`: Exclude file from ingestion
+    - `archived`: Soft delete file
+
+    **What Happens on 'uploaded' Status:**
+    1. Verify file exists in S3
+    2. Calculate actual file size
+    3. Enforce tier storage limits
+    4. Calculate or estimate row count
+    5. Update table statistics
+    6. Register DuckDB external table
+    7. File ready for ingestion
+
+    **Row Count Calculation:**
+    - **Parquet**: Exact count from file metadata
+    - **CSV**: Count rows (minus header)
+    - **JSON**: Count array elements
+    - **Fallback**: Estimate from file size if reading fails
+
+    **Storage Limits:**
+    Enforced per subscription tier:
+    - Prevents uploads exceeding tier limit
+    - Returns HTTP 413 if limit exceeded
+    - Check current usage before large uploads
+
+    **Example Response:**
+    ```json
+    {
+      \"status\": \"success\",
+      \"file_id\": \"f123\",
+      \"upload_status\": \"uploaded\",
+      \"file_size_bytes\": 1048576,
+      \"row_count\": 5000,
+      \"message\": \"File validated and ready for ingestion\"
+    }
+    ```
+
+    **Example Usage:**
+    ```bash
+    # After uploading file to S3 presigned URL
+    curl -X PATCH \"https://api.robosystems.ai/v1/graphs/kg123/tables/files/f123\" \
+      -H \"Authorization: Bearer YOUR_TOKEN\" \
+      -H \"Content-Type: application/json\" \
+      -d '{\"status\": \"uploaded\"}'
+    ```
+
+    **Tips:**
+    - Always call this after S3 upload completes
+    - Check response for actual row count
+    - Storage limit errors (413) mean tier upgrade needed
+    - DuckDB registration failures are non-fatal (retried later)
+
+    **Note:**
+    Status updates are included - no credit consumption.
+
+    Args:
+        graph_id (str): Graph database identifier
+        file_id (str): File identifier
+        token (Union[None, Unset, str]): JWT token for SSE authentication
+        authorization (Union[None, Unset, str]):
+        body (FileStatusUpdate):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[Union[Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus]]
+     """
+
+  kwargs = _get_kwargs(
+    graph_id=graph_id,
+    file_id=file_id,
+    body=body,
+    token=token,
+    authorization=authorization,
+  )
+
+  response = client.get_httpx_client().request(
+    **kwargs,
+  )
+
+  return _build_response(client=client, response=response)
+
+
+def sync(
+  graph_id: str,
+  file_id: str,
+  *,
+  client: AuthenticatedClient,
+  body: FileStatusUpdate,
+  token: Union[None, Unset, str] = UNSET,
+  authorization: Union[None, Unset, str] = UNSET,
+) -> Optional[
+  Union[
+    Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus
+  ]
+]:
+  r""" Update File Upload Status
+
+     Update file status after upload completes.
+
+    **Purpose:**
+    Mark files as uploaded after successful S3 upload. The backend validates
+    the file, calculates size and row count, enforces storage limits, and
+    registers the DuckDB table for queries.
+
+    **Status Values:**
+    - `uploaded`: File successfully uploaded to S3 (triggers validation)
+    - `disabled`: Exclude file from ingestion
+    - `archived`: Soft delete file
+
+    **What Happens on 'uploaded' Status:**
+    1. Verify file exists in S3
+    2. Calculate actual file size
+    3. Enforce tier storage limits
+    4. Calculate or estimate row count
+    5. Update table statistics
+    6. Register DuckDB external table
+    7. File ready for ingestion
+
+    **Row Count Calculation:**
+    - **Parquet**: Exact count from file metadata
+    - **CSV**: Count rows (minus header)
+    - **JSON**: Count array elements
+    - **Fallback**: Estimate from file size if reading fails
+
+    **Storage Limits:**
+    Enforced per subscription tier:
+    - Prevents uploads exceeding tier limit
+    - Returns HTTP 413 if limit exceeded
+    - Check current usage before large uploads
+
+    **Example Response:**
+    ```json
+    {
+      \"status\": \"success\",
+      \"file_id\": \"f123\",
+      \"upload_status\": \"uploaded\",
+      \"file_size_bytes\": 1048576,
+      \"row_count\": 5000,
+      \"message\": \"File validated and ready for ingestion\"
+    }
+    ```
+
+    **Example Usage:**
+    ```bash
+    # After uploading file to S3 presigned URL
+    curl -X PATCH \"https://api.robosystems.ai/v1/graphs/kg123/tables/files/f123\" \
+      -H \"Authorization: Bearer YOUR_TOKEN\" \
+      -H \"Content-Type: application/json\" \
+      -d '{\"status\": \"uploaded\"}'
+    ```
+
+    **Tips:**
+    - Always call this after S3 upload completes
+    - Check response for actual row count
+    - Storage limit errors (413) mean tier upgrade needed
+    - DuckDB registration failures are non-fatal (retried later)
+
+    **Note:**
+    Status updates are included - no credit consumption.
+
+    Args:
+        graph_id (str): Graph database identifier
+        file_id (str): File identifier
+        token (Union[None, Unset, str]): JWT token for SSE authentication
+        authorization (Union[None, Unset, str]):
+        body (FileStatusUpdate):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Union[Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus]
+     """
+
+  return sync_detailed(
+    graph_id=graph_id,
+    file_id=file_id,
+    client=client,
+    body=body,
+    token=token,
+    authorization=authorization,
+  ).parsed
+
+
+async def asyncio_detailed(
+  graph_id: str,
+  file_id: str,
+  *,
+  client: AuthenticatedClient,
+  body: FileStatusUpdate,
+  token: Union[None, Unset, str] = UNSET,
+  authorization: Union[None, Unset, str] = UNSET,
+) -> Response[
+  Union[
+    Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus
+  ]
+]:
+  r""" Update File Upload Status
+
+     Update file status after upload completes.
+
+    **Purpose:**
+    Mark files as uploaded after successful S3 upload. The backend validates
+    the file, calculates size and row count, enforces storage limits, and
+    registers the DuckDB table for queries.
+
+    **Status Values:**
+    - `uploaded`: File successfully uploaded to S3 (triggers validation)
+    - `disabled`: Exclude file from ingestion
+    - `archived`: Soft delete file
+
+    **What Happens on 'uploaded' Status:**
+    1. Verify file exists in S3
+    2. Calculate actual file size
+    3. Enforce tier storage limits
+    4. Calculate or estimate row count
+    5. Update table statistics
+    6. Register DuckDB external table
+    7. File ready for ingestion
+
+    **Row Count Calculation:**
+    - **Parquet**: Exact count from file metadata
+    - **CSV**: Count rows (minus header)
+    - **JSON**: Count array elements
+    - **Fallback**: Estimate from file size if reading fails
+
+    **Storage Limits:**
+    Enforced per subscription tier:
+    - Prevents uploads exceeding tier limit
+    - Returns HTTP 413 if limit exceeded
+    - Check current usage before large uploads
+
+    **Example Response:**
+    ```json
+    {
+      \"status\": \"success\",
+      \"file_id\": \"f123\",
+      \"upload_status\": \"uploaded\",
+      \"file_size_bytes\": 1048576,
+      \"row_count\": 5000,
+      \"message\": \"File validated and ready for ingestion\"
+    }
+    ```
+
+    **Example Usage:**
+    ```bash
+    # After uploading file to S3 presigned URL
+    curl -X PATCH \"https://api.robosystems.ai/v1/graphs/kg123/tables/files/f123\" \
+      -H \"Authorization: Bearer YOUR_TOKEN\" \
+      -H \"Content-Type: application/json\" \
+      -d '{\"status\": \"uploaded\"}'
+    ```
+
+    **Tips:**
+    - Always call this after S3 upload completes
+    - Check response for actual row count
+    - Storage limit errors (413) mean tier upgrade needed
+    - DuckDB registration failures are non-fatal (retried later)
+
+    **Note:**
+    Status updates are included - no credit consumption.
+
+    Args:
+        graph_id (str): Graph database identifier
+        file_id (str): File identifier
+        token (Union[None, Unset, str]): JWT token for SSE authentication
+        authorization (Union[None, Unset, str]):
+        body (FileStatusUpdate):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Response[Union[Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus]]
+     """
+
+  kwargs = _get_kwargs(
+    graph_id=graph_id,
+    file_id=file_id,
+    body=body,
+    token=token,
+    authorization=authorization,
+  )
+
+  response = await client.get_async_httpx_client().request(**kwargs)
+
+  return _build_response(client=client, response=response)
+
+
+async def asyncio(
+  graph_id: str,
+  file_id: str,
+  *,
+  client: AuthenticatedClient,
+  body: FileStatusUpdate,
+  token: Union[None, Unset, str] = UNSET,
+  authorization: Union[None, Unset, str] = UNSET,
+) -> Optional[
+  Union[
+    Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus
+  ]
+]:
+  r""" Update File Upload Status
+
+     Update file status after upload completes.
+
+    **Purpose:**
+    Mark files as uploaded after successful S3 upload. The backend validates
+    the file, calculates size and row count, enforces storage limits, and
+    registers the DuckDB table for queries.
+
+    **Status Values:**
+    - `uploaded`: File successfully uploaded to S3 (triggers validation)
+    - `disabled`: Exclude file from ingestion
+    - `archived`: Soft delete file
+
+    **What Happens on 'uploaded' Status:**
+    1. Verify file exists in S3
+    2. Calculate actual file size
+    3. Enforce tier storage limits
+    4. Calculate or estimate row count
+    5. Update table statistics
+    6. Register DuckDB external table
+    7. File ready for ingestion
+
+    **Row Count Calculation:**
+    - **Parquet**: Exact count from file metadata
+    - **CSV**: Count rows (minus header)
+    - **JSON**: Count array elements
+    - **Fallback**: Estimate from file size if reading fails
+
+    **Storage Limits:**
+    Enforced per subscription tier:
+    - Prevents uploads exceeding tier limit
+    - Returns HTTP 413 if limit exceeded
+    - Check current usage before large uploads
+
+    **Example Response:**
+    ```json
+    {
+      \"status\": \"success\",
+      \"file_id\": \"f123\",
+      \"upload_status\": \"uploaded\",
+      \"file_size_bytes\": 1048576,
+      \"row_count\": 5000,
+      \"message\": \"File validated and ready for ingestion\"
+    }
+    ```
+
+    **Example Usage:**
+    ```bash
+    # After uploading file to S3 presigned URL
+    curl -X PATCH \"https://api.robosystems.ai/v1/graphs/kg123/tables/files/f123\" \
+      -H \"Authorization: Bearer YOUR_TOKEN\" \
+      -H \"Content-Type: application/json\" \
+      -d '{\"status\": \"uploaded\"}'
+    ```
+
+    **Tips:**
+    - Always call this after S3 upload completes
+    - Check response for actual row count
+    - Storage limit errors (413) mean tier upgrade needed
+    - DuckDB registration failures are non-fatal (retried later)
+
+    **Note:**
+    Status updates are included - no credit consumption.
+
+    Args:
+        graph_id (str): Graph database identifier
+        file_id (str): File identifier
+        token (Union[None, Unset, str]): JWT token for SSE authentication
+        authorization (Union[None, Unset, str]):
+        body (FileStatusUpdate):
+
+    Raises:
+        errors.UnexpectedStatus: If the server returns an undocumented status code and Client.raise_on_unexpected_status is True.
+        httpx.TimeoutException: If the request takes longer than Client.timeout.
+
+    Returns:
+        Union[Any, ErrorResponse, HTTPValidationError, UpdateFileStatusResponseUpdatefilestatus]
+     """
+
+  return (
+    await asyncio_detailed(
+      graph_id=graph_id,
+      file_id=file_id,
+      client=client,
+      body=body,
+      token=token,
+      authorization=authorization,
+    )
+  ).parsed

robosystems_client/extensions/graph_client.py

@@ -58,6 +58,7 @@ class GraphClient:
     self,
     metadata: GraphMetadata,
     initial_entity: Optional[InitialEntityData] = None,
+    create_entity: bool = True,
     timeout: int = 60,
     poll_interval: int = 2,
     on_progress: Optional[Callable[[str], None]] = None,
@@ -68,6 +69,9 @@ class GraphClient:
     Args:
         metadata: Graph metadata
         initial_entity: Optional initial entity data
+        create_entity: Whether to create the entity node and upload initial data.
+            Only applies when initial_entity is provided. Set to False to create
+            graph without populating entity data (useful for file-based ingestion).
         timeout: Maximum time to wait in seconds
         poll_interval: Time between status checks in seconds
         on_progress: Callback for progress updates
@@ -121,6 +125,7 @@ class GraphClient:
     graph_create = CreateGraphRequest(
       metadata=api_metadata,
       initial_entity=initial_entity_dict,
+      create_entity=create_entity,
     )
 
     if on_progress:

robosystems_client/extensions/table_ingest_client.py

@@ -11,20 +11,20 @@ import json
 import logging
 import httpx
 
-from ..api.tables.get_upload_url_v1_graphs_graph_id_tables_table_name_files_post import (
+from ..api.tables.get_upload_url import (
   sync_detailed as get_upload_url,
 )
-from ..api.tables.update_file_v1_graphs_graph_id_tables_files_file_id_patch import (
-  sync_detailed as update_file,
+from ..api.tables.update_file_status import (
+  sync_detailed as update_file_status,
 )
-from ..api.tables.list_tables_v1_graphs_graph_id_tables_get import (
+from ..api.tables.list_tables import (
   sync_detailed as list_tables,
 )
-from ..api.tables.ingest_tables_v1_graphs_graph_id_tables_ingest_post import (
+from ..api.tables.ingest_tables import (
   sync_detailed as ingest_tables,
 )
 from ..models.file_upload_request import FileUploadRequest
-from ..models.file_update_request import FileUpdateRequest
+from ..models.file_status_update import FileStatusUpdate
 from ..models.bulk_ingest_request import BulkIngestRequest
 
 logger = logging.getLogger(__name__)
@@ -95,7 +95,7 @@ class TableIngestClient:
     This method handles the complete 3-step upload process:
     1. Get presigned upload URL
     2. Upload file to S3
-    3. Update file metadata
+    3. Mark file as 'uploaded' (backend validates, calculates size/row count)
 
     Args:
         graph_id: The graph ID
@@ -104,7 +104,7 @@ class TableIngestClient:
         options: Upload options
 
     Returns:
-        UploadResult with upload details
+        UploadResult with upload details (size/row count calculated by backend)
     """
     if options is None:
       options = UploadOptions()
@@ -216,12 +216,10 @@ class TableIngestClient:
           # BinaryIO or file-like object
           file_or_buffer.seek(0)
           file_content = file_or_buffer.read()
-        file_size = len(file_content)
       else:
         # Read from file path
         with open(file_path, "rb") as f:
           file_content = f.read()
-        file_size = len(file_content)
 
       s3_response = self._http_client.put(
         upload_url,
@@ -230,54 +228,47 @@ class TableIngestClient:
       )
       s3_response.raise_for_status()
 
-      # Step 3: Get row count and update file metadata
+      # Step 3: Mark file as uploaded (backend validates and calculates size/row count)
       if options.on_progress:
-        options.on_progress(f"Updating file metadata for {file_name}...")
+        options.on_progress(f"Marking {file_name} as uploaded...")
 
-      try:
-        import pyarrow.parquet as pq
-
-        if is_buffer:
-          # Read from buffer for row count
-          if hasattr(file_or_buffer, "seek"):
-            file_or_buffer.seek(0)
-          parquet_table = pq.read_table(file_or_buffer)
-        else:
-          # Read from file path
-          parquet_table = pq.read_table(file_path)
-
-        row_count = parquet_table.num_rows
-      except ImportError:
-        logger.warning(
-          "pyarrow not installed, row count will be estimated from file size"
-        )
-        # Rough estimate: ~100 bytes per row for typical data
-        row_count = file_size // 100
-
-      metadata_update = FileUpdateRequest(
-        file_size_bytes=file_size, row_count=row_count
-      )
+      status_update = FileStatusUpdate(status="uploaded")
 
       kwargs = {
         "graph_id": graph_id,
         "file_id": file_id,
         "client": client,
-        "body": metadata_update,
+        "body": status_update,
       }
 
-      update_response = update_file(**kwargs)
+      update_response = update_file_status(**kwargs)
 
       if not update_response.parsed:
+        logger.error(
+          f"No parsed response from update_file_status. Status code: {update_response.status_code}"
+        )
         return UploadResult(
           file_id=file_id,
-          file_size=file_size,
-          row_count=row_count,
+          file_size=0,
+          row_count=0,
           table_name=table_name,
           file_name=file_name,
           success=False,
-          error="Failed to update file metadata",
+          error="Failed to complete file upload",
         )
 
+      response_data = update_response.parsed
+
+      if isinstance(response_data, dict):
+        file_size = response_data.get("file_size_bytes", 0)
+        row_count = response_data.get("row_count", 0)
+      elif hasattr(response_data, "additional_properties"):
+        file_size = response_data.additional_properties.get("file_size_bytes", 0)
+        row_count = response_data.additional_properties.get("row_count", 0)
+      else:
+        file_size = getattr(response_data, "file_size_bytes", 0)
+        row_count = getattr(response_data, "row_count", 0)
+
       if options.on_progress:
         options.on_progress(
           f"✅ Uploaded {file_name} ({file_size:,} bytes, {row_count:,} rows)"