- Added a history management system in model.py to store and retrieve recent messages from Chat, Mic, and Speaker. - Updated controller.py to automatically add messages to the translation history after processing. - Enhanced translation clients (OpenAI, Gemini, Groq, etc.) to accept and utilize context history for improved translation quality. - Introduced YAML configuration options for enabling history injection and customizing its behavior across different translation models. - Ensured that only original messages are stored in history to optimize token usage during translation.
16 lines
686 B
YAML
16 lines
686 B
YAML
system_prompt: |
|
|
You are a helpful translation assistant.
|
|
Supported languages:
|
|
{supported_languages}
|
|
|
|
Translate the user provided text from {input_lang} to {output_lang}.
|
|
Return ONLY the translated text. Do not add quotes or extra commentary.
|
|
history:
|
|
use_history: true
|
|
sources: [chat, mic, speaker] # 取り込み対象の履歴種別
|
|
max_messages: 5 # 注入する履歴件数の上限(新しい順)
|
|
max_chars: 4000 # 履歴整形後の最大文字数(超過時は先頭を切り捨て)
|
|
header_template: |
|
|
Conversation context (recent {max_messages} messages):
|
|
{history}
|
|
item_template: "[{timestamp}][{source}] {text}" |