Prep 0.11.0 (#19)

* dolphin mistral template

* removate trailing \n before attaching the model response

* improve prompt and validator for generated human age

* fix issue where errors during character creation process would not be
communicated to the ux and the character creator would appear stuck

* add dolphin mistral to list

* add talemate_env

* poetry relock

* add json schema for talemate scene files

* fix issues with pydantic after version upgrade

* add json extrac util functions

* fix pydantic model

* use extract json function

* scene generator, better scene name prompt

* OpenHermes-2-Mistral

* alpaca base template
Amethyst 20B template

* character description is no longer part of the sheet and needs to be added separately

* fix pydantic validation

* fix issue where sometimes partial emote strings were kept at the end of dialogue

* no need to commit character name to memory

* dedupe prompts

* clean up extra linebreaks in prompts

* experimental editor agent
agent signals first progress

* take out hardcoded example

* amethyst llm prompt template

* editor agent disableable
agent edit modal tweaks

* world state agent
agent action config schema

* director agent disableable
remove automatic actions config from ux (deprecated)

* fix responsive update when toggling enable on or off in agent dialog

* prompt adjustments
fix divine intellect preset (mirostat values were way off)
fix world state regenerating every turn regardless of setting

* move templates for world state from summarizer to worldstate agent

* conversation agent generation lenght setting

* conversation agent jiggle attribute (randomize offset to certain inference parameters)

* relabel

* scene cover image set to cover as much space as it can

* add character sheet to dialogue example generate prompt

* character creator agent mixin use set_processing

* add <|im_end|> to stopping strings

* add random number gen to template functions

* SynthIA and Tiefighter

* create new persisted characters ouf of world state
natural flow option for conversation agent to help guide multi character conversations

* conversation agent natural flow improvements

* fix bug with 1h time passage option

* some templates

* poetry relock

* fix config validation

* fix issues when detemrining scene history context length to stay within budget

* fixes to world state json parsing
fixes to conversation context length

* remove unused import

* update windows install scripts

* zephyr

* </s> stopping string

* dialog cleanup utils improved

* add agents and clients key to the config example

pyproject.toml

@@ -27,8 +27,8 @@ typing-inspect = "0.8.0"
 typing_extensions = "^4.5.0"
 uvicorn = "^0.23"
 blinker = "^1.6.2"
-pydantic = "<2"
-langchain = "0.0.213"
+pydantic = "<3"
+langchain = ">0.0.213"
 beautifulsoup4 = "^4.12.2"
 python-dotenv = "^1.0.0"
 websockets = "^11.0.3"
@@ -36,6 +36,7 @@ structlog = "^23.1.0"
 runpod = "==1.2.0"
 nest_asyncio = "^1.5.7"
 isodate = ">=0.6.1"
+thefuzz = ">=0.20.0"
 
 # ChromaDB
 chromadb = ">=0.4,<1"