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

templates/llm-prompt/std/Alpaca.jinja2

@@ -0,0 +1,7 @@
+{{ system_message }}
+
+### Instruction:
+{{ user_message }}
+
+### Response:
+{{ coercion_message }}

templates/llm-prompt/std/ChatML.jinja2

@@ -0,0 +1,6 @@
+<|im_start|>system
+{{ system_message }}<|im_end|>
+<|im_start|>user
+{{ user_message }}<|im_end|>
+<|im_start|>assistant
+{{ coercion_message }}

templates/llm-prompt/std/InstructionInputResponse.jinja2

@@ -0,0 +1,8 @@
+### Instruction:
+{{ system_message }}
+
+### Input:
+{{ user_message }}
+
+### Response:
+{{ coercion_message }}

templates/llm-prompt/std/Llama2.jinja2

@@ -0,0 +1 @@
+<s>[INST] {{ system_message }} {{ user_message }} [/INST] {{ coercion_message }}

templates/llm-prompt/std/OpenChat.jinja2

@@ -0,0 +1 @@
+GPT4 Correct System: {{ system_message }}<|end_of_turn|>GPT4 Correct User: {{ user_message }}<|end_of_turn|>GPT4 Correct Assistant: {{ coercion_message }}

templates/llm-prompt/std/USER_ASSISTANT.jinja2

@@ -0,0 +1 @@
+USER: {{ system_message }} {{ user_message }} ASSISTANT: {{ coercion_message }}

templates/llm-prompt/std/UserAssistant.jinja2

@@ -0,0 +1,2 @@
+User: {{ system_message }} {{ user_message }}
+Assistant: {{ coercion_message }}

templates/llm-prompt/std/Vicuna.jinja2

@@ -0,0 +1,3 @@
+SYSTEM: {{ system_message }}
+USER: {{ user_message }}
+ASSISTANT: {{ coercion_message }}

templates/llm-prompt/std/Zephyr.jinja2

@@ -0,0 +1,6 @@
+<|system|>
+{{ system_message }}</s>
+<|user|>
+{{ user_message }}</s>
+<|assistant|>
+{{ coercion_message }}

templates/llm-prompt/talemate/Umbra.jinja2

@@ -0,0 +1,5 @@
+### System:{{ system_message }}
+
+### USER:{{ user_message }}
+
+### Assistant:{{ coercion_message }}

templates/llm-prompt/talemate/mixtral_11bx2_moe.jinja2

@@ -1,5 +1,4 @@
 {{ system_message }}
 
 ### Instruction:
-
 {{ set_response(prompt, "\n\n### Response:\n") }}