add endpoint to generate webvtt export

backend/openapi-schema.yml

@@ -327,6 +327,69 @@ components:
       - has_full_access
       title: DocumentWithAccessInfo
       type: object
+    ExportError:
+      properties:
+        error:
+          title: Error
+          type: string
+      required:
+      - error
+      title: ExportError
+      type: object
+    ExportFormat:
+      description: An enumeration.
+      enum:
+      - VTT
+      - SRT
+      title: ExportFormat
+      type: string
+    ExportResult:
+      properties:
+        result:
+          title: Result
+          type: string
+      required:
+      - result
+      title: ExportResult
+      type: object
+    ExportTask:
+      properties:
+        document_id:
+          format: uuid
+          title: Document Id
+          type: string
+        task_parameters:
+          $ref: '#/components/schemas/ExportTaskParameters'
+        task_type:
+          default: EXPORT
+          enum:
+          - EXPORT
+          title: Task Type
+          type: string
+      required:
+      - task_parameters
+      - document_id
+      title: ExportTask
+      type: object
+    ExportTaskParameters:
+      properties:
+        format:
+          $ref: '#/components/schemas/ExportFormat'
+        include_speaker_names:
+          title: Include Speaker Names
+          type: boolean
+        include_word_timing:
+          title: Include Word Timing
+          type: boolean
+        max_line_length:
+          title: Max Line Length
+          type: integer
+      required:
+      - format
+      - include_speaker_names
+      - include_word_timing
+      title: ExportTaskParameters
+      type: object
     HTTPValidationError:
       properties:
         detail:
@@ -529,6 +592,7 @@ components:
       - TRANSCRIBE
       - ALIGN
       - REENCODE
+      - EXPORT
       title: TaskType
       type: string
     TranscribeTask:
@@ -887,6 +951,57 @@ paths:
                 $ref: '#/components/schemas/HTTPValidationError'
           description: Validation Error
       summary: Update Document
+  /api/v1/documents/{document_id}/add_export_result/:
+    post:
+      operationId: add_export_result_api_v1_documents__document_id__add_export_result__post
+      parameters:
+      - in: path
+        name: document_id
+        required: true
+        schema:
+          format: uuid
+          title: Document Id
+          type: string
+      - in: query
+        name: task_id
+        required: true
+        schema:
+          title: Task Id
+          type: string
+      - in: header
+        name: authorization
+        required: false
+        schema:
+          title: Authorization
+          type: string
+      - in: header
+        name: Share-Token
+        required: false
+        schema:
+          title: Share-Token
+          type: string
+      requestBody:
+        content:
+          application/json:
+            schema:
+              anyOf:
+              - $ref: '#/components/schemas/ExportResult'
+              - $ref: '#/components/schemas/ExportError'
+              title: Result
+        required: true
+      responses:
+        '200':
+          content:
+            application/json:
+              schema: {}
+          description: Successful Response
+        '422':
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/HTTPValidationError'
+          description: Validation Error
+      summary: Add Export Result
   /api/v1/documents/{document_id}/add_media_file/:
     post:
       operationId: add_media_file_api_v1_documents__document_id__add_media_file__post
@@ -924,6 +1039,66 @@ paths:
                 $ref: '#/components/schemas/HTTPValidationError'
           description: Validation Error
       summary: Add Media File
+  /api/v1/documents/{document_id}/export/:
+    get:
+      operationId: export_api_v1_documents__document_id__export__get
+      parameters:
+      - in: path
+        name: document_id
+        required: true
+        schema:
+          format: uuid
+          title: Document Id
+          type: string
+      - in: query
+        name: format
+        required: true
+        schema:
+          $ref: '#/components/schemas/ExportFormat'
+      - in: query
+        name: include_speaker_names
+        required: true
+        schema:
+          title: Include Speaker Names
+          type: boolean
+      - in: query
+        name: include_word_timing
+        required: true
+        schema:
+          title: Include Word Timing
+          type: boolean
+      - in: query
+        name: max_line_length
+        required: false
+        schema:
+          title: Max Line Length
+          type: integer
+      - in: header
+        name: authorization
+        required: false
+        schema:
+          title: Authorization
+          type: string
+      - in: header
+        name: Share-Token
+        required: false
+        schema:
+          title: Share-Token
+          type: string
+      responses:
+        '200':
+          content:
+            text/plain:
+              schema:
+                type: string
+          description: Successful Response
+        '422':
+          content:
+            application/json:
+              schema:
+                $ref: '#/components/schemas/HTTPValidationError'
+          description: Validation Error
+      summary: Export
   /api/v1/documents/{document_id}/set_duration/:
     post:
       operationId: set_duration_api_v1_documents__document_id__set_duration__post
@@ -1211,6 +1386,7 @@ paths:
               - $ref: '#/components/schemas/SpeakerIdentificationTask'
               - $ref: '#/components/schemas/TranscribeTask'
               - $ref: '#/components/schemas/AlignTask'
+              - $ref: '#/components/schemas/ExportTask'
               - $ref: '#/components/schemas/UnknownTask'
               title: Task
         required: true

backend/pyproject.toml

@@ -10,6 +10,7 @@ authors = [
 ]
 
 dependencies = [
+    "redis>=5.0.1",
     "fastapi>=0.92.0",
     "uvicorn[standard]>=0.20.0",
     "sqlmodel @ git+https://github.com/transcribee/sqlmodel.git@transcribee_main",

backend/transcribee_backend/config.py

@@ -23,6 +23,9 @@ class Settings(BaseSettings):
     metrics_username = "transcribee"
     metrics_password = "transcribee"
 
+    redis_host = "localhost"
+    redis_port = 6379
+
 
 class ModelConfig(BaseModel):
     id: str

backend/transcribee_backend/db/__init__.py

@@ -6,10 +6,14 @@
 from fastapi import Request
 from prometheus_client import Histogram
 from prometheus_fastapi_instrumentator import routing
+from redis.asyncio import Redis
 from sqlalchemy import event
 from sqlmodel import Session, create_engine
 from starlette.websockets import WebSocket
 
+from transcribee_backend.config import settings
+from transcribee_backend.util.redis_task_channel import RedisTaskChannel
+
 DEFAULT_SOCKET_PATH = Path(__file__).parent.parent.parent / "db" / "sockets"
 
 DATABASE_URL = os.environ.get(
@@ -22,6 +26,8 @@
     pool_size=32,
     max_overflow=1024,  # we keep open a database connection for every worker
 )
+redis = Redis(host=settings.redis_host, port=settings.redis_port)
+redis_task_channel = RedisTaskChannel(redis)
 
 query_histogram = Histogram(
     "sql_queries",
@@ -31,6 +37,10 @@
 )
 
 
+def get_redis_task_channel():
+    return redis_task_channel
+
+
 def get_session(request: Request):
     handler = routing.get_route_name(request)
     with Session(engine) as session, query_counter(session, path=handler):

backend/transcribee_backend/models/task.py

@@ -7,7 +7,7 @@
 from sqlmodel import JSON, Column, Field, ForeignKey, Relationship, SQLModel, col
 from sqlmodel.sql.sqltypes import GUID
 from transcribee_proto.api import Document as ApiDocument
-from transcribee_proto.api import TaskType
+from transcribee_proto.api import ExportTaskParameters, TaskType
 from typing_extensions import Self
 
 from transcribee_backend.config import settings
@@ -291,9 +291,16 @@ class AlignTask(TaskBase):
     task_parameters: Dict[str, Any]
 
 
+class ExportTask(TaskBase):
+    task_type: Literal[TaskType.EXPORT] = TaskType.EXPORT
+    task_parameters: ExportTaskParameters
+
+
 class UnknownTask(TaskBase):
     task_type: str
     task_parameters: Dict[str, Any]
 
 
-CreateTask = SpeakerIdentificationTask | TranscribeTask | AlignTask | UnknownTask
+CreateTask = (
+    SpeakerIdentificationTask | TranscribeTask | AlignTask | ExportTask | UnknownTask
+)