server/www: rename topic text field to transcript

This aleviate the current issue with vercel deployment

server/migrations/versions/38a927dcb099_rename_back_text_to_transcript.py

@@ -0,0 +1,80 @@
+"""rename back text to transcript
+
+Revision ID: 38a927dcb099
+Revises: 9920ecfe2735
+Create Date: 2023-11-02 19:53:09.116240
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.sql import table, column
+from sqlalchemy import select
+
+
+# revision identifiers, used by Alembic.
+revision: str = '38a927dcb099'
+down_revision: Union[str, None] = '9920ecfe2735'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    # bind the engine
+    bind = op.get_bind()
+
+    # Reflect the table
+    transcript = table("transcript", column("id", sa.String), column("topics", sa.JSON))
+
+    # Select all rows from the transcript table
+    results = bind.execute(select([transcript.c.id, transcript.c.topics]))
+
+    for row in results:
+        transcript_id = row["id"]
+        topics_json = row["topics"]
+
+        # Process each topic in the topics JSON array
+        updated_topics = []
+        for topic in topics_json:
+            if "text" in topic:
+                # Rename key 'text' back to 'transcript'
+                topic["transcript"] = topic.pop("text")
+            updated_topics.append(topic)
+
+        # Update the transcript table
+        bind.execute(
+            transcript.update()
+            .where(transcript.c.id == transcript_id)
+            .values(topics=updated_topics)
+        )
+
+
+def downgrade() -> None:
+    # bind the engine
+    bind = op.get_bind()
+
+    # Reflect the table
+    transcript = table("transcript", column("id", sa.String), column("topics", sa.JSON))
+
+    # Select all rows from the transcript table
+    results = bind.execute(select([transcript.c.id, transcript.c.topics]))
+
+    for row in results:
+        transcript_id = row["id"]
+        topics_json = row["topics"]
+
+        # Process each topic in the topics JSON array
+        updated_topics = []
+        for topic in topics_json:
+            if "transcript" in topic:
+                # Rename key 'transcript' to 'text'
+                topic["text"] = topic.pop("transcript")
+            updated_topics.append(topic)
+
+        # Update the transcript table
+        bind.execute(
+            transcript.update()
+            .where(transcript.c.id == transcript_id)
+            .values(topics=updated_topics)
+        )

server/migrations/versions/9920ecfe2735_rename_transcript_to_text.py

@@ -9,7 +9,6 @@ from typing import Sequence, Union
 
 from alembic import op
 import sqlalchemy as sa
-import json
 from sqlalchemy.sql import table, column
 from sqlalchemy import select
 

server/reflector/db/transcripts.py

@@ -63,7 +63,7 @@ class TranscriptTopic(BaseModel):
     summary: str
     timestamp: float
     duration: float | None = 0
-    text: str | None = None
+    transcript: str | None = None
     words: list[ProcessorWord] = []
 
 

server/reflector/pipelines/main_live_pipeline.py

@@ -162,7 +162,7 @@ class PipelineMainBase(PipelineRunner):
             title=data.title,
             summary=data.summary,
             timestamp=data.timestamp,
-            text=data.transcript.text,
+            transcript=data.transcript.text,
             words=data.transcript.words,
         )
         if isinstance(data, TitleSummaryWithIdProcessorType):

server/reflector/views/transcripts.py

@@ -121,7 +121,7 @@ class GetTranscriptTopic(BaseModel):
     title: str
     summary: str
     timestamp: float
-    text: str
+    transcript: str
     segments: list[GetTranscriptSegmentTopic] = []
 
     @classmethod
@@ -154,7 +154,7 @@ class GetTranscriptTopic(BaseModel):
             title=topic.title,
             summary=topic.summary,
             timestamp=topic.timestamp,
-            text=text,
+            transcript=text,
             segments=segments,
         )
 

server/tests/test_transcripts_rtc_ws.py

@@ -167,7 +167,7 @@ async def test_transcript_rtc_and_websocket(
     ev = events[eventnames.index("TOPIC")]
     assert ev["data"]["id"]
     assert ev["data"]["summary"] == "LLM SUMMARY"
-    assert ev["data"]["text"].startswith("Hello world.")
+    assert ev["data"]["transcript"].startswith("Hello world.")
     assert ev["data"]["timestamp"] == 0.0
 
     assert "FINAL_LONG_SUMMARY" in eventnames
@@ -316,7 +316,7 @@ async def test_transcript_rtc_and_websocket_and_fr(
     ev = events[eventnames.index("TOPIC")]
     assert ev["data"]["id"]
     assert ev["data"]["summary"] == "LLM SUMMARY"
-    assert ev["data"]["text"].startswith("Hello world.")
+    assert ev["data"]["transcript"].startswith("Hello world.")
     assert ev["data"]["timestamp"] == 0.0
 
     assert "FINAL_LONG_SUMMARY" in eventnames