Files
talemate/pyproject.toml

90 lines
1.6 KiB
TOML
Raw Normal View History

2023-05-05 00:50:02 +03:00
[build-system]
requires = ["poetry>=0.12"]
build-backend = "poetry.masonry.api"
[tool.poetry]
name = "talemate"
2024-05-31 13:10:23 +03:00
version = "0.25.6"
2023-09-18 10:59:57 +03:00
description = "AI-backed roleplay and narrative tools"
2023-09-17 18:35:32 +03:00
authors = ["FinalWombat"]
license = "GNU Affero General Public License v3.0"
2023-05-05 00:50:02 +03:00
[tool.poetry.dependencies]
0.22.0 (#89) * linux dev instance shortcuts * add voice samples to gitignore * direction mode: inner monologue * actor direction fixes * py script support for scene logic * fix end_simulation call * port sim suite logic to python * remove dupe log * fix typing * section off the text * fix end simulation command * simulation goal, prompt tweaks * prompt tweaks * dialogue format improvements * director action logged with message * call director action log and other fixes * generate character dialogue instructions, prompt fixes, director action ux * fix question / answer call * generate dialogue instructions when loading from character cards * more dialogue format improvements * set scene content context more reliably. * fix innermonologue perspective * conversation prompt should honor the client's decensor setting * fix comfyui checkpoint list not loading * more dialogue format fixes * prompt tweaks * fix sim suite group characters, prompt fixes * npm relock * handle inanimate objects, handle player name change issues * don't rename details if the original name was "You" * As the conversation goes on, dialogue instructions should be moved backwards further to have a weaker effect on immediate generations. * add more context to character creation prompt * fix select next talking actor when natural language flow is turned on and the LLM returns multiple character names * prompt fixes for dialogue generation * summarization fixes * default to script format * seperate dialogue prompt by formatting style, tweak conversation system prompt * remove cruft * add gen format to agent details * relock * relock * prep 0.22.0 * add claude-3-haiku-20240307 * readme
2024-03-29 21:37:28 +02:00
python = ">=3.10,<3.12"
2023-05-05 00:50:02 +03:00
astroid = "^2.8"
jedi = "^0.18"
black = "*"
rope = "^0.22"
isort = "^5.10"
jinja2 = "^3.0"
Prep 0.12.0 (#26) * no " or * just treat as spoken words * chromadb perist to db * collect name should contain embedding so switching between chromadb configurations doesn't brick your scenes * fix save-as long term memory transfer * add chroma * director agent refactor * tweak director command, prompt reset, ux display * tweak director message ux * allow clearing of prompt log * remove auto adding of quotes if neither quote or * are present * command to reset long term memory for the scene * improve summarization template as it would cause some llms to add extra details * rebuilding history will now also rebuild long term memory * direct scene template * fix scene time reset * dialogue template tweaks * better dialog format fixing * some dialogue template adjustments * adjust default values of director agent * keep track of scene saved/unsaved status and confirm loading a different scene if current scene is unsaved * prompt fixes * remove the collection on recommitting the seen to memory, as the embeddings may have changed * change to the official python api for the openai client and make it async * prompt tweaks * world state prompt parsing fixes * improve handling of json responses * 0 seconds ago changed to moments ago * move memory context closer to scene * token counts for openai client * narrator agent option: narrate passage of time * gitignore * remove memory id * refactor world state with persistence to chromadb (wip) * remove world state update instructions * dont display blank emotion in world state * openai gpt-4 turbo support * conversation agent extra instructions * track prompt response times * Yi and UtopiaXL * long term memory retrieval improvements during conversations * narrate scene tweaks * conversation ltm augment tweaks * hide subconfig if parent config isnt enabled * ai assisted memory recall during conversation default to off * openai json_object coersion only on model that supports it openai client emit prompt processing time * 0.12.0 * remove prompt number from prompt debug list * add prompt number back in but shift it to the upper row * narrate time passage hard content limit restriction for now as gpt-4 would just write a whole chapter. * relock
2023-11-10 22:45:50 +02:00
openai = ">=1"
0.23.0 (#91) * dockerfiles and docker-compose * containerization fixes * docker instructions * readme * readme * dont mount src by default, readme * hf template determine fixes * auto determine prompt template * script to start talemate listening only to 127.0.0.1 * prompt tweaks * auto narrate round every 3 rounds * tweaks * Add return to startscreen button * Only show return to start screen button if scene is active * improvements to character creation * dedicated property for scene title separate fromn the save directory name * filter out negations into negative keywords * increase auto narrate delay * add character portrait keyword * summarization should ignore most recent message, as it is often regenerated. * cohere client * specify python3 * improve viable runpod text gen detection * fix formatting in template preview * cohere command-r plus template that i am not sure if correct or not * mistral client set to decensor * fix issue with parsing json responses * command-r prompts updated * use official mistralai python client * send max_tokens * new input autocomplete functionality * prompt tweeaks * llama 3 templates * add <|eot_id|> to stopping strings * prompt tweak * tooltip * llama-3 identifier * command-r and command-r plus prompt identifiers * text-gen-webui client tweaks to make llama3 eos tokens work correctly * better llama-3 detection * better llama-3 finalizing of parameters * streamline client prompt finalizers reduce YY model smoothing factor from 0.3 to 0.1 for text-generation-webui client * relock * linting * set 0.23.0 * add new gpt-4 models * set 0.23.0 * add note about conecting to text-gen-webui from docker * fix openai image generation no longer working * default to concept_art
2024-04-20 01:01:06 +03:00
mistralai = ">=0.1.8"
cohere = ">=5.2.2"
anthropic = ">=0.19.1"
groq = ">=0.5.0"
2023-05-05 00:50:02 +03:00
requests = "^2.26"
colorama = ">=0.4.6"
Prep 0.19.0 (#67) * linting * improve prompt devtools: test changes, show more information * some more polish for the new promp devtools * up default conversation gen length to 128 * openai client tweaks, talemate sets max_tokens on gpt-3.5 generations * support new openai embeddings (and default to text-embedding-3-small) * ux polish for character sheet and character state ux * actor instructions * experiment using # for context / instructions * fix bug where regenerating history would mess up time stamps * remove trailing ] * prevent client ctx from being unset * fix issue where sometimes you'd need to delete a client twice for it to disappear * upgrade dependencies * set 0.19.0 * fix performance degradation caused by circular loading animation * remove coqui studio support * fix issue when switching from unsaved creative mode to loading a scene * third party client / agent support * edit dialogue examples through character / actor editor * remove "edit dialogue" action from editor - replaced by character actor instructions * different icon for delete * prompt adjustment for acting instructions * adhoc context generation for character attributes and details * add adhoc generation for character description * contextual generation tweaks * contextual generation for dialogue examples fix some formatting issues * contextual generation for world entries * prepopulate initial recen scenarios with demo scenes add experimental holodeck scenario * scene info scene experimental * assortment of fixes for holodeck improvements * more holodeck fixes * refactor holodeck instructions * rename holodeck to simulation suite * better scene status messages * add new gpt-3.5-turbo model, better json response coercion for older models * allow exclusion of characters when persisting based on world state * better error handling of world state response * better error handling of world state response * more simulation suite fixes * progress color * world state character name mapping support * if neither quote nor asterisk is in message default to quotes * fix rerun of new paraphrase op * sim suite ping that ensure's characters are not aware of sim * fixes for better character name assessment simulation suite can now give the player character a proper name * fix bug with new status notifications * sim suite adjustments and fixes and tuning * sim suite tweaks * impl scene restore from file * prompting tweaks for reinforcement messages and acting instructions * more tweaks * dialogue prompt tweaks for rerun + rewrite * fix bug with character entry / exit with narration * linting * simsuite screenshots * screenshots
2024-02-06 00:40:55 +02:00
Pillow = ">=9.5"
2023-05-05 00:50:02 +03:00
httpx = "<1"
piexif = "^1.1"
typing-inspect = "0.8.0"
typing_extensions = "^4.5.0"
uvicorn = "^0.23"
blinker = "^1.6.2"
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
2023-10-28 11:33:51 +03:00
pydantic = "<3"
2023-05-05 00:50:02 +03:00
beautifulsoup4 = "^4.12.2"
python-dotenv = "^1.0.0"
websockets = "^11.0.3"
structlog = "^23.1.0"
Prep 0.16.0 (#40) * remove dbg message * more work to make clients and agents modular allow conversation and narrator to attempt to auto break AI repetition * application settings refactor setup third party api keys through application settings * runpod docs * fix wording * docs * improvements to auto-break-repetition functionality * more auto-break-repetition improvements * some cleanup to narrate on dialogue chance calculations * changing api keys via ux should now reflect to ux instantly. * memory agent / chromadb agent - wrap blocking functions calls in asyncio * clean up narrate progression prompt and function * turn off dedupe debug message for now * encourage the AI to break repetition as well * indicate if the current model is missing a LLM prompt template add prompt template to client modal fix a bunch of bad vue code * only show llm prompt when editing client * OpenHermes-2.5-neural-chat RpBird-Yi-34B * fix bug with auto rep break when no repetition was found * allow giving extra instructions to narrator agent * emit agents as needed, not constantly * fix a bunch of vue alerts * fix request-client-status event * remove undefined reference * log client / status emit * worldstate component track scene time * Tess Noromaid * fix narrate-character prompt context length overflow issues * disable worldstate refresh button while waiting for response * history timestamp moved to tooltip off of history button * fixes #39: using openai embeddings for chromadb tends to error * adjust conversation again default instructions * poetry lock * remove debug message * chromadb - agent status error if openai embeddings are selected in api key isn't set * prep 0.16.0
2023-12-08 22:57:44 +02:00
runpod = "^1.2.0"
0.25.0 (#100) * flip title and name in recent scenes * fix issue where a message could not be regenerated after applying continuity error fixes * prompt tweaks * allow json parameters for commands * autocomplete improvements * dialogue cleanup fixes * fix issue with narrate after dialogue and llama3 (and other models that don't have a line break after the user prompt in their prompt template. * expose ability to auto generate dialogue instructions to wsm character ux * use b64_json response type * move tag checks up so they match first * fix typo * prompt tweak * api key support * prompt tweaks * editable parameters in prompt debugger / tester * allow reseting of prompt params * codemirror for prompt editor * prompt tweaks * more prompt debug tool tweaks * some extra control for `context_history` * new analytical preset (testing) * add `join` and `llm_can_be_coerced` to jinja env * support factual list summaries * prompt tweaks to continuity check and fix * new summarization method `facts` exposed to ux * clamp mistral ai temperature according to their new requirements * prompt tweaks * better parsing of fixed dialogue response * prompt tweaks * fix intermittent empty meta issue * history regen status progression and small ux tweaks * summary entries should always be condensed * google gemini support * relock to install google-cloud-aiplatform for vertex ai inference * fix instruction link * better error handling of google safety validation and allow disabling of safety validation * docs * clarify credentials path requirements * tweak error line identification * handle quota limit error * autocomplete ux wired to assistant plugin instead of command * autocomplete narrative editing and fixes to autocomplete during dialog edit * main input autocomplete tweaks * allow new lines in main input * 0.25.0 and relock * fix issue with autocomplete elsewhere locking out main input * better way to determine remote service * prompt tweak * fix rubberbanding issue when editing character attributes * add open mistral 8x22 * fix continuity error check summary inclusion of target entry * docs * default context length to 8192 * linting
2024-05-05 22:16:03 +03:00
google-cloud-aiplatform = ">=1.50.0"
2023-05-05 00:50:02 +03:00
nest_asyncio = "^1.5.7"
isodate = ">=0.6.1"
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
2023-10-28 11:33:51 +03:00
thefuzz = ">=0.20.0"
Prep 0.12.0 (#26) * no " or * just treat as spoken words * chromadb perist to db * collect name should contain embedding so switching between chromadb configurations doesn't brick your scenes * fix save-as long term memory transfer * add chroma * director agent refactor * tweak director command, prompt reset, ux display * tweak director message ux * allow clearing of prompt log * remove auto adding of quotes if neither quote or * are present * command to reset long term memory for the scene * improve summarization template as it would cause some llms to add extra details * rebuilding history will now also rebuild long term memory * direct scene template * fix scene time reset * dialogue template tweaks * better dialog format fixing * some dialogue template adjustments * adjust default values of director agent * keep track of scene saved/unsaved status and confirm loading a different scene if current scene is unsaved * prompt fixes * remove the collection on recommitting the seen to memory, as the embeddings may have changed * change to the official python api for the openai client and make it async * prompt tweaks * world state prompt parsing fixes * improve handling of json responses * 0 seconds ago changed to moments ago * move memory context closer to scene * token counts for openai client * narrator agent option: narrate passage of time * gitignore * remove memory id * refactor world state with persistence to chromadb (wip) * remove world state update instructions * dont display blank emotion in world state * openai gpt-4 turbo support * conversation agent extra instructions * track prompt response times * Yi and UtopiaXL * long term memory retrieval improvements during conversations * narrate scene tweaks * conversation ltm augment tweaks * hide subconfig if parent config isnt enabled * ai assisted memory recall during conversation default to off * openai json_object coersion only on model that supports it openai client emit prompt processing time * 0.12.0 * remove prompt number from prompt debug list * add prompt number back in but shift it to the upper row * narrate time passage hard content limit restriction for now as gpt-4 would just write a whole chapter. * relock
2023-11-10 22:45:50 +02:00
tiktoken = ">=0.5.1"
nltk = ">=3.8.1"
Prep 0.18.0 (#58) * vuetify update recent saves * use placeholder instead of prefilling text * fix scene loading when no coverage image is set * improve summarize and pin response quality * summarization use previous entries as informative context * fixes #49: auto save indicator missleading * regenerate with instructions * allow resetting of state reinforcement * creative tools: introduce new character creative tools: introduce passive character as active character * character creation adjustments * no longer needed * activate, deactivate characters (work in progress) * worldstate manager show inactive characters * allow setting of llm prompt template from ux reorganize llm prompt template directory for easier local overriding support a more sane way to write llm prompt templates * determine prompt template from huggingface * ignore user overrides * fix issue with removing narrator messages * summarization agent config for prev entry inclusion agent config attribute notes * client code clean up to allow modularity of clients + generic openai compatible api client * more client cleanup * remove debug msg, step size for ctx upped to 1024 * wip on stepped history summarization * summarization prompt fixes * include time message for hisory context pushed in scene.context_history * add / remove characters toggle narration of via ctrl * fix pydantic namespace warning fix client emit after reconfig * set memory ids on character detail entries * deal with chromadb race condition (maybe) * activate / deactivate characters from creative editor switch creative editor to edit characters through world state manager * set 0.18.0 * relock dependencies * openai client shortcut to set api key if not set * set error_action to null * if scene has just started provide intro for extra context in is_prsent and is_leaving queries * nice error if determine template via huggingface doesn't work * fix issue where regenerate would sometimes pick the wrong npc if there are multiple characters talking * add new openai models * default to gpt-4-turbo-preview
2024-01-26 12:42:21 +02:00
huggingface-hub = ">=0.20.2"
0.22.0 (#89) * linux dev instance shortcuts * add voice samples to gitignore * direction mode: inner monologue * actor direction fixes * py script support for scene logic * fix end_simulation call * port sim suite logic to python * remove dupe log * fix typing * section off the text * fix end simulation command * simulation goal, prompt tweaks * prompt tweaks * dialogue format improvements * director action logged with message * call director action log and other fixes * generate character dialogue instructions, prompt fixes, director action ux * fix question / answer call * generate dialogue instructions when loading from character cards * more dialogue format improvements * set scene content context more reliably. * fix innermonologue perspective * conversation prompt should honor the client's decensor setting * fix comfyui checkpoint list not loading * more dialogue format fixes * prompt tweaks * fix sim suite group characters, prompt fixes * npm relock * handle inanimate objects, handle player name change issues * don't rename details if the original name was "You" * As the conversation goes on, dialogue instructions should be moved backwards further to have a weaker effect on immediate generations. * add more context to character creation prompt * fix select next talking actor when natural language flow is turned on and the LLM returns multiple character names * prompt fixes for dialogue generation * summarization fixes * default to script format * seperate dialogue prompt by formatting style, tweak conversation system prompt * remove cruft * add gen format to agent details * relock * relock * prep 0.22.0 * add claude-3-haiku-20240307 * readme
2024-03-29 21:37:28 +02:00
RestrictedPython = ">7.1"
2023-05-05 00:50:02 +03:00
# ChromaDB
chromadb = ">=0.4.17,<1"
2023-05-05 00:50:02 +03:00
InstructorEmbedding = "^1.0.1"
torch = ">=2.1.0"
torchaudio = ">=2.3.0"
# locked for instructor embeddings
sentence-transformers="==2.2.2"
2023-05-05 00:50:02 +03:00
[tool.poetry.dev-dependencies]
pytest = "^6.2"
mypy = "^0.910"
[tool.poetry.scripts]
talemate = "talemate:cli.main"
[tool.black]
line-length = 88
target-version = ['py38']
include = '\.pyi?$'
exclude = '''
/(
\.git
| \.hg
| \.mypy_cache
| \.tox
| \.venv
| _build
| buck-out
| build
| dist
)/
'''
[tool.isort]
profile = "black"
multi_line_output = 3
include_trailing_comma = true
force_grid_wrap = 0
use_parentheses = true
ensure_newline_before_comments = true
2023-09-17 18:35:32 +03:00
line_length = 88