Added script for video keyframe preannotation API functionality

.gitignore

@@ -30,3 +30,12 @@ download
 labellerr/__pycache__/
 env.*
 claude.md
+labellerr/notebooks/Labellerr_datasets/354681d3-034a-4d66-b070-365f4bd11d8a/2a8d96ca-9161-4dee-ad3b-a5faf301bc6c.mp4
+labellerr/notebooks/Labellerr_datasets/354681d3-034a-4d66-b070-365f4bd11d8a/7db3f60c-f6e5-4d3d-a63b-cb38530ee265.mp4
+labellerr/notebooks/PyScene_detects/354681d3-034a-4d66-b070-365f4bd11d8a/2a8d96ca-9161-4dee-ad3b-a5faf301bc6c/2a8d96ca-9161-4dee-ad3b-a5faf301bc6c_mapping.json
+labellerr/notebooks/PyScene_detects/354681d3-034a-4d66-b070-365f4bd11d8a/2a8d96ca-9161-4dee-ad3b-a5faf301bc6c/frames/316.jpg
+labellerr/notebooks/PyScene_detects/354681d3-034a-4d66-b070-365f4bd11d8a/7db3f60c-f6e5-4d3d-a63b-cb38530ee265/7db3f60c-f6e5-4d3d-a63b-cb38530ee265_mapping.json
+labellerr/notebooks/PyScene_detects/354681d3-034a-4d66-b070-365f4bd11d8a/2a8d96ca-9161-4dee-ad3b-a5faf301bc6c/frames/1406.jpg
+labellerr/notebooks/PyScene_detects/354681d3-034a-4d66-b070-365f4bd11d8a/2a8d96ca-9161-4dee-ad3b-a5faf301bc6c/frames/1064.jpg
+labellerr/notebooks/PyScene_detects/354681d3-034a-4d66-b070-365f4bd11d8a/2a8d96ca-9161-4dee-ad3b-a5faf301bc6c/frames/760.jpg
+labellerr/notebooks/dev.env

labellerr/core/constants.py

@@ -1,4 +1,4 @@
-BASE_URL = "https://api.labellerr.com"
+BASE_URL = "https://api-gateway-qcb3iv2gaa-uc.a.run.app"
 ALLOWED_ORIGINS = "https://pro.labellerr.com"
 
 
@@ -7,7 +7,7 @@
 TOTAL_FILES_SIZE_LIMIT_PER_DATASET = 2.5 * 1024 * 1024 * 1024  # 2.5GB
 TOTAL_FILES_COUNT_LIMIT_PER_DATASET = 2500
 
-ANNOTATION_FORMAT = ["json", "coco_json", "csv", "png"]
+ANNOTATION_FORMAT = ["json", "coco_json", "csv", "png", "video_json"]
 LOCAL_EXPORT_FORMAT = ["json", "coco_json", "csv", "png"]
 LOCAL_EXPORT_STATUS = [
     "review",

labellerr/core/files/base.py

@@ -112,3 +112,7 @@ def dataset_id(self):
     @property
     def metadata(self):
         return self.__file_data.get("file_metadata", {})
+
+    @property
+    def file_name(self):
+        return self.__file_data.get("file_name", "")

labellerr/core/files/video_file.py

@@ -61,6 +61,7 @@ def get_frames(self, frame_start: int = 0, frame_end: int | None = None):
                 "frame_end": frame_end,
                 "project_id": self.project_id,
                 "uuid": unique_id,
+                "client_id": self.client.client_id,
             }
 
             response = self.client.make_request(
@@ -115,8 +116,15 @@ def download_frames(
         :return: Dictionary with download statistics
         """
         try:
-            # Use file_id as folder name
-            folder_name = self.file_id
+            # Use [Dataset_id]+[File_id]+[File_name] as folder name
+            if self.dataset_id and self.file_name:
+                # Remove extension from file_name if present
+                base_name = os.path.splitext(self.file_name)[0]
+                folder_name = f"{self.dataset_id}+{self.file_id}+{base_name}"
+            elif self.dataset_id:
+                folder_name = f"{self.dataset_id}+{self.file_id}"
+            else:
+                folder_name = self.file_id
 
             # Set output path
             if output_folder:
@@ -207,7 +215,13 @@ def create_video(
 
         input_pattern = os.path.join(frames_folder, pattern)
         if output_file is None:
-            output_file = f"{self.file_id}.mp4"
+            # Use [Dataset_id]+[File_id]+[File_name] as default output filename
+            if self.dataset_id and self.file_name:
+                output_file = f"{self.dataset_id}+{self.file_id}+{self.file_name}"
+            elif self.dataset_id:
+                output_file = f"{self.dataset_id}+{self.file_id}.mp4"
+            else:
+                output_file = f"{self.file_id}.mp4"
 
         # FFmpeg command
         command = [
@@ -235,7 +249,7 @@ def create_video(
             raise LabellerrError(f"Error while joining frames: {str(e)}")
 
     def download_create_video_auto_cleanup(
-        self, output_folder: str = "./Labellerr_datastets"
+        self, output_folder: str = "./Labellerr_datasets"
     ):
         """
         Download frames, create video, and automatically clean up temporary frames.
@@ -258,36 +272,50 @@ def download_create_video_auto_cleanup(
             print(f"\n[1/4] Fetching frame data from API (0 to {total_frames})...")
             frames_data = self.get_frames(frame_start=0, frame_end=total_frames)
 
+            # print(frames_data)
+
             if not frames_data:
                 raise LabellerrError("No frame data retrieved from API")
 
             print(f"Retrieved {len(frames_data)} frames")
 
-            # Step 2: Create dataset folder structure
+            # Step 2: Create output folder structure
             print("\n[2/4] Setting up output folders...")
-            if self.dataset_id is None:
-                dataset_folder = output_folder
+            # Videos will be saved directly in output_folder (labellerr_datasets)
+            os.makedirs(output_folder, exist_ok=True)
+
+            # Define actual frames folder path using [Dataset_id]+[File_id]+[File_name] naming
+            # Frames will be temporarily stored in a subfolder for organization
+            if self.dataset_id and self.file_name:
+                base_name = os.path.splitext(self.file_name)[0]
+                folder_name = f"{self.dataset_id}+{self.file_id}+{base_name}"
+            elif self.dataset_id:
+                folder_name = f"{self.dataset_id}+{self.file_id}"
             else:
-                dataset_folder = os.path.join(output_folder, self.dataset_id)
-            os.makedirs(dataset_folder, exist_ok=True)
-
-            # Define actual frames folder path
-            actual_frames_folder = os.path.join(dataset_folder, self.file_id)
+                folder_name = self.file_id
+            actual_frames_folder = os.path.join(output_folder, folder_name)
 
             # Step 3: Download frames
             print("\n[3/4] Downloading frames...")
             download_result = self.download_frames(
-                frames_data=frames_data, output_folder=dataset_folder
+                frames_data=frames_data, output_folder=output_folder
             )
 
             if download_result["failed_downloads"] > 0:
                 print(
                     f"\nWarning: {download_result['failed_downloads']} frames failed to download"
                 )
 
-            # Step 4: Create video from downloaded frames
+            # Step 4: Create video from downloaded frames using [Dataset_id]+[File_id]+[File_name] naming
+            # Save video directly in output_folder (labellerr_datasets)
             print("\n[4/4] Creating video from frames...")
-            video_output_path = os.path.join(dataset_folder, f"{self.file_id}.mp4")
+            if self.dataset_id and self.file_name:
+                video_filename = f"{self.dataset_id}+{self.file_id}+{self.file_name}"
+            elif self.dataset_id:
+                video_filename = f"{self.dataset_id}+{self.file_id}.mp4"
+            else:
+                video_filename = f"{self.file_id}.mp4"
+            video_output_path = os.path.join(output_folder, video_filename)
 
             self.create_video(
                 frames_folder=actual_frames_folder, output_file=video_output_path
@@ -304,7 +332,7 @@ def download_create_video_auto_cleanup(
                 "file_id": self.file_id,
                 "dataset_id": self.dataset_id,
                 "video_path": video_output_path,
-                "output_folder": dataset_folder,
+                "output_folder": output_folder,
                 "frames_downloaded": download_result["successful_downloads"],
                 "frames_failed": download_result["failed_downloads"],
                 "failed_frames_info": download_result["failed_frames"],
@@ -313,19 +341,22 @@ def download_create_video_auto_cleanup(
             print(f"\n{'='*60}")
             print("Processing complete!")
             print(f"Video saved to: {video_output_path}")
-            print("{'='*60}\n")
+            print(f"{'='*60}\n")
 
             return result
 
         except Exception as e:
             # Attempt cleanup on error
-            # Get the frames folder path
+            # Get the frames folder path using [Dataset_id]+[File_id]+[File_name] naming
             if self.dataset_id is None:
                 cleanup_folder = os.path.join(output_folder, self.file_id)
             else:
-                cleanup_folder = os.path.join(
-                    output_folder, self.dataset_id, self.file_id
-                )
+                if self.file_name:
+                    base_name = os.path.splitext(self.file_name)[0]
+                    folder_name = f"{self.dataset_id}+{self.file_id}+{base_name}"
+                else:
+                    folder_name = f"{self.dataset_id}+{self.file_id}"
+                cleanup_folder = os.path.join(output_folder, folder_name)
 
             if os.path.exists(cleanup_folder):
                 shutil.rmtree(cleanup_folder)

labellerr/core/projects/video_project.py

@@ -1,5 +1,6 @@
+import os
 import uuid
-from typing import List
+from typing import Any, Dict, List
 
 from .. import constants
 from ..exceptions import LabellerrError
@@ -91,5 +92,56 @@ def delete_keyframes(self, file_id: str, keyframes: List[int]):
         except Exception as e:
             raise LabellerrError(f"Failed to delete key frames: {str(e)}")
 
+    def upload_keyframe_preannotations(self, video_json_file_path: str = None) -> Any:
+        """
+        Uploads pre-annotations for video project.
+
+        Supports both the parent signature and a video-specific signature for backward compatibility.
+
+        :param annotation_format: (Deprecated) The format of the preannotation data
+        :param annotation_file: (Deprecated) The file path of the preannotation data
+        :param conf_bucket: (Deprecated) Confidence bucket [low, medium, high]
+        :param _async: (Deprecated) Whether to return a future object
+        :param video_json_file_path: Path to the video JSON file containing pre-annotations
+        :return: Response from the API
+        """
+        # Support both old and new signatures
+        file_path = video_json_file_path
+
+        # Parameter validation
+        if not isinstance(file_path, str):
+            raise LabellerrError("file_path must be a str")
+
+        try:
+            # Validate if the file exists
+            if not os.path.exists(file_path):
+                raise LabellerrError(f"File not found: {file_path}")
+
+            unique_id = str(uuid.uuid4())
+            url = f"{constants.BASE_URL}/actions/upload_answers?project_id={self.project_id}&answer_format=video_json&client_id={self.client.client_id}&uuid={unique_id}"
+
+            # Get file name from path
+            file_name = os.path.basename(file_path)
+
+            # Open file and prepare multipart form data
+            with open(file_path, "rb") as f:
+                files = [("file", (file_name, f, "application/json"))]
+                payload: Dict[Any, Any] = {}
+
+                response = self.client.make_request(
+                    "POST",
+                    url,
+                    request_id=unique_id,
+                    handle_response=False,
+                    data=payload,
+                    files=files,
+                )
+
+            return self.client.handle_upload_response(response, unique_id)
+        except LabellerrError:
+            raise
+        except Exception as e:
+            raise LabellerrError(f"Failed to upload pre-annotations: {str(e)}")
+
 
 LabellerrProjectMeta._register(DatasetDataType.video, VideoProject)

labellerr/core/schemas/__init__.py

@@ -14,18 +14,29 @@
 # Import from autolabel.typings for backward compatibility
 from labellerr.core.autolabel.typings import *  # noqa: F403, F401
 
+# Export annotation templates
+from labellerr.core.schemas.annotation_templates import (
+    AnnotationQuestion,
+    CreateTemplateParams,
+    Option,
+    QuestionType,
+)
+
+# Autolabel schemas
+from labellerr.core.schemas.autolabel import Hyperparameters, KeyFrame, TrainingRequest
+
 # Base custom types
 from labellerr.core.schemas.base import DirPathStr, FilePathStr, NonEmptyStr
 
 # Connection schemas
 from labellerr.core.schemas.connectors import (
     AWSConnectionParams,
-    DatasetDataType,
-    DeleteConnectionParams,
-    GCSConnectionParams,
     AWSConnectionTestParams,
     ConnectionType,
     ConnectorType,
+    DatasetDataType,
+    DeleteConnectionParams,
+    GCSConnectionParams,
     GCSConnectionTestParams,
 )
 
@@ -43,6 +54,9 @@
     UploadFilesParams,
 )
 
+# Export schemas
+from labellerr.core.schemas.exports import CreateExportParams, ExportDestination
+
 # File operation schemas
 from labellerr.core.schemas.files import BulkAssignFilesParams, ListFileParams
 
@@ -65,25 +79,6 @@
     UpdateUserRoleParams,
 )
 
-# Autolabel schemas
-from labellerr.core.schemas.autolabel import (
-    Hyperparameters,
-    KeyFrame,
-    TrainingRequest,
-)
-
-# Export schemas
-from labellerr.core.schemas.exports import CreateExportParams, ExportDestination
-
-
-# Export annotation templates
-from labellerr.core.schemas.annotation_templates import (
-    AnnotationQuestion,
-    Option,
-    QuestionType,
-)
-
-
 __all__ = [
     # Base types
     "NonEmptyStr",
@@ -136,4 +131,5 @@
     "AnnotationQuestion",
     "Option",
     "QuestionType",
+    "CreateTemplateParams",
 ]

labellerr/core/schemas/annotation_templates.py

@@ -1,8 +1,10 @@
-from pydantic import BaseModel, Field
-from typing import List, Optional
-from enum import Enum
-from ..schemas import DatasetDataType
 import uuid
+from enum import Enum
+from typing import List, Optional
+
+from pydantic import BaseModel, Field
+
+from .base import DatasetDataType
 
 
 class QuestionType(str, Enum):

labellerr/core/schemas/projects.py

@@ -51,7 +51,6 @@ class CreateProjectParams(BaseModel):
 class CreateTemplateParams(BaseModel):
     """Parameters for creating an annotation template."""
 
-    client_id: str = Field(min_length=1)
     data_type: Literal["image", "video", "audio", "document", "text"]
     template_name: str = Field(min_length=1)
     questions: List[Question] = Field(min_length=1)