726 Commits

Author	SHA1	Message	Date
Cohee	fedc3b887f	Add llama2 tokenizer for OpenRouter models	2023-11-05 21:54:19 +02:00
Cohee	88df8501b3	Fix continue on forced OR instruct. Display proper itemized prompt	2023-11-05 02:20:15 +02:00
Cohee	f10833a516	Add prompt format override for OpenRouter	2023-11-03 00:34:22 +02:00
RossAscends	d50124e937	appwide slider overhaul	2023-10-26 13:20:47 +09:00
Cohee	d0637750e7	Add system message collapse for chat comps	2023-10-14 22:05:09 +03:00
Cohee	84098ae933	Fix injection order (again)	2023-10-11 22:56:17 +03:00
Cohee	e2f0162e5a	Fix injection order	2023-10-11 22:42:25 +03:00
Cohee	59ae661f62	Fix itemization viewer	2023-10-11 22:09:24 +03:00
Cohee	abb78d1d6b	Add at-depth position for custom Prompt Manager prompts	2023-10-11 16:03:36 +03:00
Cohee	82182015e2	Allow group nudge in chat completions.	2023-10-02 00:24:16 +03:00
Brian Dashore	bfda5a5492	Extra fixes (#1185)	2023-09-26 09:53:04 +03:00
Cohee	03e5ca054d	Limit number of custom stop strings for Palm API	2023-09-25 23:12:14 +03:00
Cohee	3e29d39f05	Fix Palm when streaming is enabled	2023-09-25 20:24:56 +03:00
Cohee	edb79d8c53	Synchronize max depths for plugins	2023-09-25 19:29:24 +03:00
Cohee	a081f78bd8	(WIP) PaLM API	2023-09-23 20:48:56 +03:00
Cohee	902acc44a2	Support "before main prompt" extension position in prompt manager	2023-09-21 20:46:08 +03:00
Maks	158aa79aed	add model gpt-3.5-turbo-instruct and 0914 variant (#1154)	2023-09-19 23:50:27 +03:00
Cohee	ab9aa28fe4	Move missed endpoints	2023-09-16 18:03:31 +03:00
Cohee	61995bb33f	Move preset management into a separate file	2023-09-16 17:36:54 +03:00
Cohee	eaca6ddaf0	Don't try to resolve unknown tiktoken models	2023-09-15 19:31:17 +03:00
Jason Wu	7a3869c476	Enable Smart Context (ChromaDB) support within OpenAI API (#1125) ... * Add JetBrains IDE .idea folder to .gitignore * Enable Smart Context (ChromaDB) support within OpenAI API	2023-09-13 13:01:56 +03:00
Cohee	65b4551864	Reserve 3 extra tokens for each chat completion	2023-09-11 17:22:31 +03:00
Cohee	a5acc7872d	Add OpenAI vector source.	2023-09-08 13:57:27 +03:00
Cohee	96df705409	Change insertion strategy to an extension block	2023-09-08 01:26:26 +03:00
Cohee	5ef79bd64d	Remove NSFW avoidance prompt from Prompt Manager	2023-09-05 18:14:56 +03:00
Cohee	67c8476cdf	Set 0 tokens for prompts with no content	2023-09-04 02:40:16 +03:00
Cohee	80e286fed2	Fix double insertion of persona description to prompt manager if position set to A/N	2023-09-04 02:26:15 +03:00
Cohee	4a6705cea8	Prompt manager configuration fixes (#1078) ... * Refactor oai preset change event into before and after * Simplify and reinforce prompt manager render without character * Check if main prompt exists before adding nsfwAvoidance * Sanitize prompt manager configuration on preset loading --------- Co-authored-by: maver <kentucky@posteo.de>	2023-09-01 23:23:03 +03:00
Cohee	636c06ffdd	Autosize prompt manager boxes	2023-08-27 21:28:13 +03:00
Cohee	e74bca88f4	Disable OpenRouter fallback by default	2023-08-27 18:39:04 +03:00
Cohee	44661d0e2b	Merge branch 'staging' into generate-array	2023-08-26 01:07:19 +03:00
Cohee	42e6da4a36	Add support of stop strings to OpenAI / Claude	2023-08-26 00:12:11 +03:00
Cohee	12f1cdb3fd	#1020 Fix summarize + prompt manager. Clarify naming for insertion position.	2023-08-25 20:03:31 +03:00
Cohee	685e9b7e79	Stabilize extension injections order for prompt manager	2023-08-25 17:15:55 +03:00
Cohee	aceb32cfe9	Fix freq pen overwrite by pres pen	2023-08-25 02:52:38 +03:00
Cohee	4aa31fcba9	Add fallback option for OpenRouter	2023-08-24 03:21:17 +03:00
Cohee	52c2fcd407	Fix OpenRouter model not persisting on page reload	2023-08-24 00:59:57 +03:00
maver	65e595ad48	Increase prompt oder dummy user id by 1	2023-08-23 20:41:13 +02:00
maver	5a02250a1f	Add persona description to prompt manager order	2023-08-23 20:40:26 +02:00
Cohee	e77da62b85	Add padding to cache key. Fix Safari display issues. Fix 400 on empty translate. Reset bias cache on changing model.	2023-08-23 10:32:48 +03:00
Cohee	b385bd190a	Less strict rules for logit bias files import	2023-08-23 03:41:58 +03:00
Cohee	f633f62065	Don't save null values to OpenAI logit bias	2023-08-23 03:36:04 +03:00
Cohee	bc5fc67906	Put tokenizer functions to a separate file. Cache local models token counts	2023-08-23 02:38:43 +03:00
Cohee	7250770c5d	Don't reduce Claude token counts by 2	2023-08-22 23:20:53 +03:00
Cohee	41cc86af9f	Add example extension for chat variables. Allow registering custom text processing functions for extensions	2023-08-22 17:46:37 +03:00
based	3716fd51ef	add example names to initial system prompt	2023-08-22 22:29:57 +10:00
based	ba925f388c	added more options to the scale request	2023-08-22 21:29:18 +10:00
based	06902279a9	merge	2023-08-22 21:17:18 +10:00
Cohee	57b126bfbf	Save chat completions settings to an object. Update numeric setting types	2023-08-22 00:35:46 +03:00
maver	cb5b410daf	Fix group nudge causing error	2023-08-20 20:18:10 +02:00