Rework LLM output parser + add narrator #475
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
- split off the part of a `sentence` that is relevant to an LLM into `sentence_content` - added `is_narration` bool identifier to `sentence_content` - extended formatting of sentences in `assistant_message` to treat sentences flagged as `is_narration` correctly - added `output_parser.py` with abstract class `output_parser` as well subclasses `clean_sentence_parser`, `change_character_parser`, `narration_parser`, `sentence_end_parser` and `actions_parser` - reworked `process_response()` in `ChatManager` to use the the output parsers - parsers are put into a chain/pipeline and get applied to the LLM output, each parser decides on it's own if it should cut the output and prepare the sentence - added config value `narration_handling` with options *Cut narration*, *Respective character speaks its narrations* and *Use narrator* - added config value `narrator_voice` - removed maximum sentence length restriction from generation and instead introduced abbreviation of the subtitle text before sending it to the game
…es instead of chars
… now variables config value to set them is still missing
art-from-the-machine
approved these changes
Jan 17, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
sentencethat is relevant to an LLM intosentence_contentis_narrationbool identifier tosentence_contentassistant_messageto treat sentences flagged asis_narrationcorrectlyoutput_parser.pywith abstract classoutput_parseras well subclassesclean_sentence_parser,change_character_parser,narration_parser,sentence_end_parserandactions_parserprocess_response()inChatManagerto use the the output parsersnarration_handlingwith options Cut narration, Respective character speaks its narrations and Use narratornarrator_voice