mirror of
https://github.com/Monadical-SAS/reflector.git
synced 2025-12-24 06:09:07 +00:00
594bcc09e0
* parallelize hatchet (no-mistakes) * dry (no-mistakes) (minimal) * comments * self-review * self-review * self-review * self-review * pr comments * pr comments --------- Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>
31 lines
858 B
Python
31 lines
858 B
Python
"""
|
|
LLM prompts for transcript processing.
|
|
|
|
Extracted to a separate module to avoid circular imports when importing
|
|
from processor modules (which import LLM/settings at module level).
|
|
"""
|
|
|
|
from textwrap import dedent
|
|
|
|
TOPIC_PROMPT = dedent(
|
|
"""
|
|
Analyze the following transcript segment and extract the main topic being discussed.
|
|
Focus on the substantive content and ignore small talk or administrative chatter.
|
|
|
|
Create a title that:
|
|
- Captures the specific subject matter being discussed
|
|
- Is descriptive and self-explanatory
|
|
- Uses professional language
|
|
- Is specific rather than generic
|
|
|
|
For the summary:
|
|
- Summarize the key points in maximum two sentences
|
|
- Focus on what was discussed, decided, or accomplished
|
|
- Be concise but informative
|
|
|
|
<transcript>
|
|
{text}
|
|
</transcript>
|
|
"""
|
|
).strip()
|