selfhostyourtech/reflector
2
0
Fork 0
mirror of https://github.com/Monadical-SAS/reflector.git synced 2026-02-05 02:16:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

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

Browse Source 
* 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>
This commit is contained in:
Igor Monadical
2025-11-12 21:21:16 -05:00
committed by GitHub
parent 372202b0e1
commit 1473fd82dc
71 changed files with 4985 additions and 468 deletions
Download Patch File Download Diff File Expand all files Collapse all files

69
server/reflector/processors/summary/summary_builder.py
View File

@@ -165,6 +165,7 @@ class SummaryBuilder:
self.llm: LLM = llm
self.model_name: str = llm.model_name
self.logger = logger or structlog.get_logger()
self.participant_instructions: str | None = None
if filename:
self.read_transcript_from_file(filename)
@@ -191,14 +192,61 @@ class SummaryBuilder:
self, prompt: str, output_cls: Type[T], tone_name: str | None = None
) -> T:
"""Generic function to get structured output from LLM for non-function-calling models."""
# Add participant instructions to the prompt if available
enhanced_prompt = self._enhance_prompt_with_participants(prompt)
return await self.llm.get_structured_response(
prompt, [self.transcript], output_cls, tone_name=tone_name
enhanced_prompt, [self.transcript], output_cls, tone_name=tone_name
)
async def _get_response(
self, prompt: str, texts: list[str], tone_name: str | None = None
) -> str:
"""Get text response with automatic participant instructions injection."""
enhanced_prompt = self._enhance_prompt_with_participants(prompt)
return await self.llm.get_response(enhanced_prompt, texts, tone_name=tone_name)
def _enhance_prompt_with_participants(self, prompt: str) -> str:
"""Add participant instructions to any prompt if participants are known."""
if self.participant_instructions:
self.logger.debug("Adding participant instructions to prompt")
return f"{prompt}\n\n{self.participant_instructions}"
return prompt
# ----------------------------------------------------------------------------
# Participants
# ----------------------------------------------------------------------------
def set_known_participants(self, participants: list[str]) -> None:
"""
Set known participants directly without LLM identification.
This is used when participants are already identified and stored.
They are appended at the end of the transcript, providing more context for the assistant.
"""
if not participants:
self.logger.warning("No participants provided")
return
self.logger.info(
"Using known participants",
participants=participants,
)
participants_md = self.format_list_md(participants)
self.transcript += f"\n\n# Participants\n\n{participants_md}"
# Set instructions that will be automatically added to all prompts
participants_list = ", ".join(participants)
self.participant_instructions = dedent(
f"""
# IMPORTANT: Participant Names
The following participants are identified in this conversation: {participants_list}
You MUST use these specific participant names when referring to people in your response.
Do NOT use generic terms like "a participant", "someone", "attendee", "Speaker 1", "Speaker 2", etc.
Always refer to people by their actual names (e.g., "John suggested..." not "A participant suggested...").
"""
).strip()
async def identify_participants(self) -> None:
"""
From a transcript, try to identify the participants using TreeSummarize with structured output.
@@ -232,6 +280,19 @@ class SummaryBuilder:
if unique_participants:
participants_md = self.format_list_md(unique_participants)
self.transcript += f"\n\n# Participants\n\n{participants_md}"
# Set instructions that will be automatically added to all prompts
participants_list = ", ".join(unique_participants)
self.participant_instructions = dedent(
f"""
# IMPORTANT: Participant Names
The following participants are identified in this conversation: {participants_list}
You MUST use these specific participant names when referring to people in your response.
Do NOT use generic terms like "a participant", "someone", "attendee", "Speaker 1", "Speaker 2", etc.
Always refer to people by their actual names (e.g., "John suggested..." not "A participant suggested...").
"""
).strip()
else:
self.logger.warning("No participants identified in the transcript")
@@ -318,13 +379,13 @@ class SummaryBuilder:
for subject in self.subjects:
detailed_prompt = DETAILED_SUBJECT_PROMPT_TEMPLATE.format(subject=subject)
detailed_response = await self.llm.get_response(
detailed_response = await self._get_response(
detailed_prompt, [self.transcript], tone_name="Topic assistant"
)
paragraph_prompt = PARAGRAPH_SUMMARY_PROMPT
paragraph_response = await self.llm.get_response(
paragraph_response = await self._get_response(
paragraph_prompt, [str(detailed_response)], tone_name="Topic summarizer"
)
@@ -345,7 +406,7 @@ class SummaryBuilder:
recap_prompt = RECAP_PROMPT
recap_response = await self.llm.get_response(
recap_response = await self._get_response(
recap_prompt, [summaries_text], tone_name="Recap summarizer"
)

38
server/reflector/processors/transcript_final_summary.py
View File

@@ -26,7 +26,25 @@ class TranscriptFinalSummaryProcessor(Processor):
async def get_summary_builder(self, text) -> SummaryBuilder:
builder = SummaryBuilder(self.llm, logger=self.logger)
builder.set_transcript(text)
await builder.identify_participants()
# Use known participants if available, otherwise identify them
if self.transcript and self.transcript.participants:
# Extract participant names from the stored participants
participant_names = [p.name for p in self.transcript.participants if p.name]
if participant_names:
self.logger.info(
f"Using {len(participant_names)} known participants from transcript"
)
builder.set_known_participants(participant_names)
else:
self.logger.info(
"Participants field exists but is empty, identifying participants"
)
await builder.identify_participants()
else:
self.logger.info("No participants stored, identifying participants")
await builder.identify_participants()
await builder.generate_summary()
return builder
@@ -49,18 +67,30 @@ class TranscriptFinalSummaryProcessor(Processor):
speakermap = {}
if self.transcript:
speakermap = {
participant["speaker"]: participant["name"]
for participant in self.transcript.participants
p.speaker: p.name
for p in (self.transcript.participants or [])
if p.speaker is not None and p.name
}
self.logger.info(
f"Built speaker map with {len(speakermap)} participants",
speakermap=speakermap,
)
# build the transcript as a single string
# XXX: unsure if the participants name as replaced directly in speaker ?
# Replace speaker IDs with actual participant names if available
text_transcript = []
unique_speakers = set()
for topic in self.chunks:
for segment in topic.transcript.as_segments():
name = speakermap.get(segment.speaker, f"Speaker {segment.speaker}")
unique_speakers.add((segment.speaker, name))
text_transcript.append(f"{name}: {segment.text}")
self.logger.info(
f"Built transcript with {len(unique_speakers)} unique speakers",
speakers=list(unique_speakers),
)
text_transcript = "\n".join(text_transcript)
last_chunk = self.chunks[-1]

8
server/reflector/processors/transcript_topic_detector.py
View File

@@ -1,6 +1,6 @@
from textwrap import dedent
from pydantic import BaseModel, Field
from pydantic import AliasChoices, BaseModel, Field
from reflector.llm import LLM
from reflector.processors.base import Processor
@@ -36,15 +36,13 @@ class TopicResponse(BaseModel):
title: str = Field(
description="A descriptive title for the topic being discussed",
validation_alias="Title",
validation_alias=AliasChoices("title", "Title"),
)
summary: str = Field(
description="A concise 1-2 sentence summary of the discussion",
validation_alias="Summary",
validation_alias=AliasChoices("summary", "Summary"),
)
model_config = {"populate_by_name": True}
class TranscriptTopicDetectorProcessor(Processor):
"""