feat: daily.co support as alternative to whereby (#691)

* llm instructions * vibe dailyco * vibe dailyco * doc update (vibe) * dont show recording ui on call * stub processor (vibe) * stub processor (vibe) self-review * stub processor (vibe) self-review * chore(main): release 0.14.0 (#670) * Add multitrack pipeline * Mixdown audio tracks * Mixdown with pyav filter graph * Trigger multitrack processing for daily recordings * apply platform from envs in priority: non-dry * Use explicit track keys for processing * Align tracks of a multitrack recording * Generate waveforms for the mixed audio * Emit multriack pipeline events * Fix multitrack pipeline track alignment * dailico docs * Enable multitrack reprocessing * modal temp files uniform names, cleanup. remove llm temporary docs * docs cleanup * dont proceed with raw recordings if any of the downloads fail * dry transcription pipelines * remove is_miltitrack * comments * explicit dailyco room name * docs * remove stub data/method * frontend daily/whereby code self-review (no-mistake) * frontend daily/whereby code self-review (no-mistakes) * frontend daily/whereby code self-review (no-mistakes) * consent cleanup for multitrack (no-mistakes) * llm fun * remove extra comments * fix tests * merge migrations * Store participant names * Get participants by meeting session id * pop back main branch migration * s3 paddington (no-mistakes) * comment * pr comments * pr comments * pr comments * platform / meeting cleanup * Use participant names in summary generation * platform assignment to meeting at controller level * pr comment * room playform properly default none * room playform properly default none * restore migration lost * streaming WIP * extract storage / use common storage / proper env vars for storage * fix mocks tests * remove fall back * streaming for multifile * cenrtal storage abstraction (no-mistakes) * remove dead code / vars * Set participant user id for authenticated users * whereby recording name parsing fix * whereby recording name parsing fix * more file stream * storage dry + tests * remove homemade boto3 streaming and use proper boto * update migration guide * webhook creation script - print uuid --------- Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com> Co-authored-by: Mathieu Virbel <mat@meltingrocks.com> Co-authored-by: Sergey Mankovsky <sergey@monadical.com>
2025-12-24 14:19:05 +00:00 · 2025-11-12 21:21:16 -05:00
parent 372202b0e1
commit 1473fd82dc
71 changed files with 4985 additions and 468 deletions
--- a/server/reflector/pipelines/topic_processing.py
+++ b/server/reflector/pipelines/topic_processing.py
@@ -0,0 +1,109 @@
+"""
+Topic processing utilities
+==========================
+
+Shared topic detection, title generation, and summarization logic
+used across file and multitrack pipelines.
+"""
+
+from typing import Callable
+
+import structlog
+
+from reflector.db.transcripts import Transcript
+from reflector.processors import (
+    TranscriptFinalSummaryProcessor,
+    TranscriptFinalTitleProcessor,
+    TranscriptTopicDetectorProcessor,
+)
+from reflector.processors.types import TitleSummary
+from reflector.processors.types import Transcript as TranscriptType
+
+
+class EmptyPipeline:
+    def __init__(self, logger: structlog.BoundLogger):
+        self.logger = logger
+
+    def get_pref(self, k, d=None):
+        return d
+
+    async def emit(self, event):
+        pass
+
+
+async def detect_topics(
+    transcript: TranscriptType,
+    target_language: str,
+    *,
+    on_topic_callback: Callable,
+    empty_pipeline: EmptyPipeline,
+) -> list[TitleSummary]:
+    chunk_size = 300
+    topics: list[TitleSummary] = []
+
+    async def on_topic(topic: TitleSummary):
+        topics.append(topic)
+        return await on_topic_callback(topic)
+
+    topic_detector = TranscriptTopicDetectorProcessor(callback=on_topic)
+    topic_detector.set_pipeline(empty_pipeline)
+
+    for i in range(0, len(transcript.words), chunk_size):
+        chunk_words = transcript.words[i : i + chunk_size]
+        if not chunk_words:
+            continue
+
+        chunk_transcript = TranscriptType(
+            words=chunk_words, translation=transcript.translation
+        )
+
+        await topic_detector.push(chunk_transcript)
+
+    await topic_detector.flush()
+    return topics
+
+
+async def generate_title(
+    topics: list[TitleSummary],
+    *,
+    on_title_callback: Callable,
+    empty_pipeline: EmptyPipeline,
+    logger: structlog.BoundLogger,
+):
+    if not topics:
+        logger.warning("No topics for title generation")
+        return
+
+    processor = TranscriptFinalTitleProcessor(callback=on_title_callback)
+    processor.set_pipeline(empty_pipeline)
+
+    for topic in topics:
+        await processor.push(topic)
+
+    await processor.flush()
+
+
+async def generate_summaries(
+    topics: list[TitleSummary],
+    transcript: Transcript,
+    *,
+    on_long_summary_callback: Callable,
+    on_short_summary_callback: Callable,
+    empty_pipeline: EmptyPipeline,
+    logger: structlog.BoundLogger,
+):
+    if not topics:
+        logger.warning("No topics for summary generation")
+        return
+
+    processor = TranscriptFinalSummaryProcessor(
+        transcript=transcript,
+        callback=on_long_summary_callback,
+        on_short_summary=on_short_summary_callback,
+    )
+    processor.set_pipeline(empty_pipeline)
+
+    for topic in topics:
+        await processor.push(topic)
+
+    await processor.flush()