1c4bad35b2
#2085 Implement async token counting
2024-04-13 21:05:31 +03:00
ba397dd2a8
#2062 Extend unlock for MakerSuite models
2024-04-13 20:09:51 +03:00
9c218455c4
[chore] Run ESLint
2024-04-12 14:22:12 +03:00
34bca69950
system prompt support for gemini 1.5
2024-04-11 16:38:20 +10:00
53baa7aae7
#2051 #2031 Selectable prompt converter for custom OAI type
2024-04-10 21:12:57 +03:00
540cddf300
new turbo model
2024-04-10 14:24:43 +10:00
6d65d47f00
Fix macro not being subbed in example separators for instruct
2024-04-09 11:24:16 +03:00
42138ca09b
Add command-r-plus
2024-04-04 20:38:34 +03:00
51b3b8bfaa
Add smooth streaming
2024-04-02 14:56:15 +03:00
ac0a431cbe
fix: avoid skipping example chats in a dialogue when close to quota
2024-04-01 22:44:16 -03:00
d498458971
Merge pull request #1996 from aisu-wata0/staging
...
fix: "Squash system messages" would fail to skip example messages
2024-04-02 00:35:57 +03:00
9838ba8044
#1994 Add Cohere as a Chat Completion source
2024-04-02 00:20:17 +03:00
41860bdc57
fix: squashing system messages would fail to skip example messages
2024-04-01 01:24:29 -03:00
fcdd90cec4
Adjust last prompt line of quite gens
2024-03-28 21:51:02 +02:00
310acfe810
Use new instruct sequences in prompt formatting
2024-03-28 00:52:20 +02:00
01d17f4396
Export Chat Comps examples parser
2024-03-27 23:38:13 +02:00
6a51855f19
Update Makersuite models
2024-03-27 13:52:51 +10:00
0218eb1a18
Disable newline wrapping of in-chat extension prompts
2024-03-25 13:11:28 +02:00
e153861043
Hide radio controls in drawers
2024-03-24 21:25:27 +02:00
8a7ad5ef91
Indicate overridden prompts
2024-03-24 02:19:10 +02:00
3b637cc9a6
Add forbid overrides to prompts
2024-03-24 01:28:35 +02:00
c1ac34e001
Disable-able main prompt
2024-03-24 00:28:54 +02:00
7b9c0e303f
Clean-up continue nudge init
2024-03-23 23:11:05 +02:00
6665666098
Add continue postfix controls for Chat Completion
2024-03-23 23:02:42 +02:00
67e78fa456
Add roles to summary injects
2024-03-23 19:18:43 +02:00
607df2f555
Add ability to insert role-typed prompt injections
2024-03-23 17:36:43 +02:00
6fe1b0f0e2
#1933 Gemini 1.5 Pro
2024-03-21 19:25:54 +02:00
965bb54f7d
Option to add names to completion contents
2024-03-19 21:53:40 +02:00
4a5c1a5ac8
Remove vision model restrictions from OpenRouter.
2024-03-19 20:48:49 +02:00
46993384a3
Allow any model to send inline images in OpenAI custom endpoint mode
2024-03-14 00:33:04 +02:00
e24fbfdc1d
Update default OAI sampler parameters
2024-03-13 02:25:20 +02:00
15eb18740e
Pass char/user names for Claude example messages converter
2024-03-08 08:31:36 +02:00
00a4a12d7d
Remove "Exclude Assistant suffix" option
2024-03-05 20:41:53 +02:00
3e1d44fc29
remove deprecated option + reverse proxy support in claude vision
2024-03-06 02:47:00 +10:00
de0e0dad27
he forgor oop
2024-03-05 15:33:07 +10:00
8d9175f3f2
update default settings preset
2024-03-05 15:22:16 +10:00
64d9c9dc5d
anthropic captioning
2024-03-05 07:07:38 +10:00
7bb8741cfa
fix older model naming for the new api
2024-03-05 05:50:29 +10:00
04bb882e90
implement messages api and selector for nuclaude models
2024-03-05 04:40:19 +10:00
149a65cf62
migrate model name in old presets to new naming scheme
2024-02-27 02:23:07 +10:00
c9f0d61f19
#1851 Substitute macros in new example chat
2024-02-22 18:45:50 +02:00
ece3b2a7c1
Fix Chat Completions status check on settings loading if another API is selected
2024-02-22 04:36:06 +02:00
2e00a1baaf
[FEATURE_REQUEST] Can the unlocked max context size for OpenAI completion be increased from 102k to 200k for example? #1842
2024-02-19 19:37:18 +02:00
9d713825c2
#1827 Consolidate {{group}} macro behavior
2024-02-12 16:23:01 +02:00
33d93b9761
#1813 Fix squash system messages
2024-02-11 15:56:48 +02:00
18f84979f2
Use SSE streaming for MakerSuite
2024-02-10 02:43:50 +02:00
90231680a9
Remove extra space
2024-02-08 00:05:23 +02:00
dfc1719c3f
Use fuzzy name matching
2024-02-08 00:04:48 +02:00
b2eb361028
Update openai.js added /proxy command.
...
Added "proxy" slash command to openai.js to change between proxy presets in ST script.
2024-02-07 13:52:48 -05:00
634c9aad3b
add logsprobs support for custom OpenAI APIs
2024-02-04 23:11:45 +00:00
7ac6ed267f
#1782 OpenAI multiswipe
2024-02-04 03:36:37 +02:00
da7b435b7c
Merge pull request #1751 from kingbased/proxypreset
...
Reverse proxy presets
2024-01-29 22:09:33 +02:00
ee7ee9f60a
merged mistral proxy support
2024-01-27 06:26:23 +10:00
aa976d0de2
implemented proxy preset manager
2024-01-27 06:21:00 +10:00
4d534e3042
[BUG] Incorrect context size for gpt-4-turbo-0125 #1748
2024-01-26 18:51:20 +02:00
1647e5ae49
Merge pull request #1734 from khanonnie/alternative-tokens
...
Implement Token Probabilities UI panel using logprobs
2024-01-26 03:39:25 +02:00
60044c18a4
Implement Token Probabilities UI using logprobs
2024-01-25 18:34:46 -06:00
40476dca3b
New OAI models
2024-01-25 22:01:02 +02:00
515e3859ec
Merge pull request #1689 from h-a-s-k/staging
...
Group chat fixes
2024-01-25 20:51:55 +02:00
107fe85543
Add OpenRouter filtered reason display
2024-01-23 00:10:53 +02:00
0b322c0e3d
Add repetition penalty control for OpenRouter
2024-01-18 23:55:09 +02:00
074cc13e60
Fix group chat example messages not including character name
2024-01-13 14:34:17 -03:00
9354697753
Actually call them example chats
2024-01-13 13:06:51 -03:00
f4c7fff8c0
Mistral API got fixed
2024-01-12 18:17:43 +02:00
e33ac6a78a
Add min_p and top_a for OpenRouter
2024-01-12 17:15:13 +02:00
747a7824c0
OpenRouter model dropdown facelift
2024-01-11 20:27:59 +02:00
9b24e7dc67
Merge pull request #1596 from DonMoralez/staging
...
added exclude prefixes, modified sequence checker
2024-01-01 23:33:58 +02:00
9106696f2f
Render prompt manager when switching APIs
2024-01-01 17:06:10 +02:00
42aa7fd316
mistral proxy support
2023-12-31 06:21:40 +10:00
0d3505c44b
Remove OAI_BEFORE_CHATCOMPLETION
...
Not used in any internal code or extensions I can find.
2023-12-25 03:48:49 -05:00
a8e5285ff7
Merge remote-tracking branch 'upstream/staging' into staging
2023-12-25 01:19:30 +02:00
f8dece9d88
Always remove logit bias and stop from vision
2023-12-24 20:01:59 +02:00
6fb69d5929
Merge remote-tracking branch 'upstream/staging' into staging
2023-12-23 00:25:57 +02:00
89d70539b9
Alternative continue method for chat completions
2023-12-22 20:24:54 +02:00
e95482aea1
Merge remote-tracking branch 'upstream/staging' into staging
2023-12-22 17:12:59 +02:00
ee06a488b0
Add exclude prefixes checkbox, modified sequence checker
2023-12-22 17:04:58 +02:00
a85a6cf606
Allow displaying unreferenced macro in message texts
2023-12-21 20:49:03 +02:00
1c9643806b
Merge remote-tracking branch 'upstream/staging' into staging
2023-12-21 17:30:37 +02:00
b5e59c819c
Merge branch 'staging' into claude-rework
2023-12-21 16:52:43 +02:00
3001db3a47
Add additional parameters for custom endpoints
2023-12-20 23:39:10 +02:00
ae64c99835
Add custom caption source
2023-12-20 21:05:20 +02:00
5734dbd17c
Add custom endpoint type
2023-12-20 18:29:03 +02:00
50ece13752
Add restore button, def hum message, claude check
2023-12-18 02:25:17 +02:00
7835a1360f
Merge remote-tracking branch 'upstream/staging' into staging
2023-12-17 19:46:47 +02:00
ed96ec5c3e
reverse proxy condition fix
2023-12-16 12:02:34 +10:00
6b59014892
(Fix) "squash sys. messages" processed empty messages, adding \n
2023-12-16 00:24:48 +02:00
583f786d74
finish mistral frontend integration + apikey status check
2023-12-16 07:15:57 +10:00
041957975a
add mistral completion source to UI
2023-12-16 06:08:41 +10:00
10fb83ee53
Merge remote-tracking branch 'upstream/staging' into staging
2023-12-15 13:12:15 +02:00
cde9903fcb
Fix Bison models
2023-12-14 22:18:34 +02:00
6f16ccf01f
Merge branch 'staging' of https://github.com/DonMoralez/SillyTavern into staging
2023-12-14 20:17:41 +02:00
6bb894286e
Migrate palm source to makersuite
2023-12-14 19:54:31 +02:00
5071b9a369
webstorm moment
2023-12-15 02:01:42 +10:00
60880cfd4d
merge
2023-12-15 01:39:12 +10:00
698850b514
Merge remote-tracking branch 'fork/staging' into gemini
...
# Conflicts:
# server.js
# src/endpoints/prompt-converters.js
# src/endpoints/tokenizers.js
2023-12-15 01:35:17 +10:00
d5bcd96eef
message inlining vision support
2023-12-15 01:28:54 +10:00
0b7c1a98cd
added google vision caption support
2023-12-14 22:37:53 +10:00
ca87f29771
added streaming for google models
2023-12-14 21:03:41 +10:00
3e82a7d439
tokenizer changes and fixes. + a toggle
2023-12-14 16:31:08 +10:00
e26159c00d
refactor and rework palm request to work with the 'content' format and added an endpoint for googles tokenizer
2023-12-14 15:49:50 +10:00
be396991de
finish implementing ui changes for google models
2023-12-14 11:53:26 +10:00
69e24c9686
change palm naming in UI
2023-12-14 11:14:41 +10:00
22e048b5af
Rename generate_altscale endpoint
2023-12-13 18:53:46 -05:00
92bd766bcb
Rename chat completions endpoints
...
OpenAI calls this the "Chat Completions API", in contrast to their
previous "Text Completions API", so that's what I'm naming it; both
because other services besides OpenAI implement it, and to avoid
confusion with the existing /api/openai route used for OpenAI extras.
2023-12-13 18:52:08 -05:00
fec27820ff
(claude)reworked prefix assignment, sysprompt mode, console message display
2023-12-13 21:19:26 +02:00
9160de7714
Run macros on impersonation prompt
2023-12-12 19:24:32 +02:00
9176f46caf
Add /preset command
2023-12-12 19:14:17 +02:00
b0e7b73a32
Fix streaming processor error handler hooks
2023-12-08 02:01:08 +02:00
5569a63595
Remove legacy_streaming setting
...
This was a workaround for older versions of Slaude that implemented SSE
improperly. This was fixed in Slaude 7 months ago, so the workaround can
be removed.
2023-12-07 18:00:36 -05:00
cdcd913805
Don't stream events if the API returned a 4xx code
2023-12-07 18:00:36 -05:00
5540c165cf
Refactor server-sent events parsing
...
Create one server-sent events stream class which implements the entire
spec (different line endings, chunking, etc) and use it in all the
streaming generators.
2023-12-07 18:00:36 -05:00
72adb4c8aa
Fix window.ai streaming
2023-12-07 17:42:06 +02:00
671df1f62e
Fix constant usage
2023-12-04 00:24:23 +02:00
e33c8bd955
Replace use_[source] with chat_completion_source
...
Same as the is_[api] replacement--it's easier to have one enum field
than several mutually-exclusive boolean ones
2023-12-03 15:03:39 -05:00
8a1ead531c
Merge pull request #1439 from valadaptive/prompt-manager-class
...
Convert PromptManagerModule to a class
2023-12-03 21:52:27 +02:00
1786b0d340
#1403 Add Aphrodite multi-swipe
2023-12-03 20:40:09 +02:00
b8b24540a9
Rename PromptManagerModule to PromptManager
...
The one place where it was imported renamed it to PromptManager anyway.
2023-12-03 12:14:56 -05:00
a3bc51bcea
Fix type-in max context for OAI
2023-12-03 13:56:22 +02:00
64a3564892
lint: Comma dangle
2023-12-02 22:06:57 +02:00
c63cd87cc0
lint: Require semicolons
2023-12-02 21:11:06 +02:00
a37f874e38
Require single quotes
2023-12-02 13:04:51 -05:00
518bb58d5a
Enable no-unused-vars lint
...
This is the big one. Probably needs thorough review to make sure I
didn't accidentally remove any setInterval or fetch calls.
2023-12-02 12:11:19 -05:00
c893e2165e
Enable no-prototype-builtins lint
2023-12-02 12:10:31 -05:00
0a27275772
Enable no-extra-semi lint
2023-12-02 10:32:26 -05:00
367f3dba27
Enable no-unsafe-finally lint
2023-12-02 10:32:07 -05:00
19c6370fa5
Revert preset checkbox update logic
2023-12-01 11:55:05 +02:00
b96054f337
Update max token limit for palm2
2023-11-30 19:02:31 +02:00
e9ad55aef2
Add seed input field for OpenAI settings #1412
2023-11-30 02:54:52 +02:00
d263760b25
#1393 Configurable group nudges, scenario and personality templates for prompt manager
2023-11-27 23:57:56 +02:00
61908935f5
Stop string for user-continue. Trim spaces after name2
2023-11-22 16:16:48 +02:00
5f77b2f816
Add Claude 2.1
2023-11-21 20:07:37 +02:00
73e081dd99
Don't use global state to build Chat Completion prompts
2023-11-21 14:38:15 +02:00
0608c0afac
Add OpenRouter and Llava to captioning plugin.
2023-11-17 23:19:21 +02:00
323b338cdd
Add images to quiet prompts if inlining enabled
2023-11-17 01:30:32 +02:00
d114ebf6fa
Add default role for Message class if not set.
2023-11-16 16:20:33 +02:00
314aca3f2c
Allow disabling system marker prompts
2023-11-14 22:27:07 +02:00
d3e5f6ebc0
#1343 Move bypass check up
2023-11-12 23:08:24 +02:00
9a1d1594d6
Fix formatting in openai.js
2023-11-12 22:14:35 +02:00
cc0b4e8174
Access oai_settings instead of dom
2023-11-12 20:55:29 +01:00
3bbbf0d8e4
Put openrouter model sorting in drawer
...
Renames 'Infinity'k tokens to 'Free'
2023-11-12 19:02:41 +01:00
cb2644cdea
Add sorting for openrouter models
...
Alphabetically (default), price, context size
2023-11-12 18:27:56 +01:00
a16e34bcef
Add optional toggle for grouping openrouter models
...
By vendor
2023-11-12 15:15:30 +01:00
7afe9e6481
#1343 Add status check bypass
2023-11-12 13:23:46 +02:00
4c0b3fb7ae
Add null checks for OR pricing
2023-11-12 13:07:57 +02:00
879502c1e7
Only allow inlining if OAI is the selected API
2023-11-12 00:13:30 +02:00
2c4f53e7b5
Add native GPT-4V image inlining
2023-11-12 00:09:48 +02:00
2f5e7778cc
Don't add items of unknown type to chat completion
2023-11-10 01:08:18 +02:00
0e89bf90bc
Use correct tokenizers for logit bias for Mistral and Llama models over OpenRouter
2023-11-09 01:03:54 +02:00
d81354e2a5
Merge branch 'staging' of https://github.com/SillyTavern/SillyTavern into staging
2023-11-08 16:29:02 +02:00
dbf995fd24
Add character card macros
2023-11-08 16:28:55 +02:00
a5fd33d08a
Kobold sampler restyle
2023-11-08 23:24:28 +09:00
740f6548a2
Increase timeouts of OAI out of quota requests
2023-11-08 12:07:14 +02:00
b2629d9718
Refactor status checks and indicators.
2023-11-08 02:52:03 +02:00
2020d12217
Add new GPT 3.5 turbo model
2023-11-07 00:10:32 +02:00
9b0ac48cda
Add GPT-4 preview model
2023-11-06 23:29:45 +02:00
21e0a42060
Fix arch in models list, remove log
2023-11-05 22:03:20 +02:00
c1e126985d
Merge branch 'staging' of https://github.com/SillyTavern/SillyTavern into staging
2023-11-05 21:54:23 +02:00
fedc3b887f
Add llama2 tokenizer for OpenRouter models
2023-11-05 21:54:19 +02:00
88df8501b3
Fix continue on forced OR instruct. Display proper itemized prompt
2023-11-05 02:20:15 +02:00
f10833a516
Add prompt format override for OpenRouter
2023-11-03 00:34:22 +02:00
d50124e937
appwide slider overhaul
2023-10-26 13:20:47 +09:00
d0637750e7
Add system message collapse for chat comps
2023-10-14 22:05:09 +03:00
84098ae933
Fix injection order (again)
2023-10-11 22:56:17 +03:00
e2f0162e5a
Fix injection order
2023-10-11 22:42:25 +03:00
59ae661f62
Fix itemization viewer
2023-10-11 22:09:24 +03:00
abb78d1d6b
Add at-depth position for custom Prompt Manager prompts
2023-10-11 16:03:36 +03:00
82182015e2
Allow group nudge in chat completions.
2023-10-02 00:24:16 +03:00
bfda5a5492
Extra fixes ( #1185 )
2023-09-26 09:53:04 +03:00
03e5ca054d
Limit number of custom stop strings for Palm API
2023-09-25 23:12:14 +03:00
3e29d39f05
Fix Palm when streaming is enabled
2023-09-25 20:24:56 +03:00
edb79d8c53
Synchronize max depths for plugins
2023-09-25 19:29:24 +03:00
a081f78bd8
(WIP) PaLM API
2023-09-23 20:48:56 +03:00
902acc44a2
Support "before main prompt" extension position in prompt manager
2023-09-21 20:46:08 +03:00
158aa79aed
add model gpt-3.5-turbo-instruct and 0914 variant ( #1154 )
2023-09-19 23:50:27 +03:00
ab9aa28fe4
Move missed endpoints
2023-09-16 18:03:31 +03:00
61995bb33f
Move preset management into a separate file
2023-09-16 17:36:54 +03:00
eaca6ddaf0
Don't try to resolve unknown tiktoken models
2023-09-15 19:31:17 +03:00
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
65b4551864
Reserve 3 extra tokens for each chat completion
2023-09-11 17:22:31 +03:00
a5acc7872d
Add OpenAI vector source.
2023-09-08 13:57:27 +03:00
96df705409
Change insertion strategy to an extension block
2023-09-08 01:26:26 +03:00
5ef79bd64d
Remove NSFW avoidance prompt from Prompt Manager
2023-09-05 18:14:56 +03:00
67c8476cdf
Set 0 tokens for prompts with no content
2023-09-04 02:40:16 +03:00
80e286fed2
Fix double insertion of persona description to prompt manager if position set to A/N
2023-09-04 02:26:15 +03:00
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
636c06ffdd
Autosize prompt manager boxes
2023-08-27 21:28:13 +03:00
e74bca88f4
Disable OpenRouter fallback by default
2023-08-27 18:39:04 +03:00
44661d0e2b
Merge branch 'staging' into generate-array
2023-08-26 01:07:19 +03:00
42e6da4a36
Add support of stop strings to OpenAI / Claude
2023-08-26 00:12:11 +03:00
12f1cdb3fd
#1020 Fix summarize + prompt manager. Clarify naming for insertion position.
2023-08-25 20:03:31 +03:00
685e9b7e79
Stabilize extension injections order for prompt manager
2023-08-25 17:15:55 +03:00
aceb32cfe9
Fix freq pen overwrite by pres pen
2023-08-25 02:52:38 +03:00
4aa31fcba9
Add fallback option for OpenRouter
2023-08-24 03:21:17 +03:00
52c2fcd407
Fix OpenRouter model not persisting on page reload
2023-08-24 00:59:57 +03:00
65e595ad48
Increase prompt oder dummy user id by 1
2023-08-23 20:41:13 +02:00
5a02250a1f
Add persona description to prompt manager order
2023-08-23 20:40:26 +02:00
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
b385bd190a
Less strict rules for logit bias files import
2023-08-23 03:41:58 +03:00
f633f62065
Don't save null values to OpenAI logit bias
2023-08-23 03:36:04 +03:00
bc5fc67906
Put tokenizer functions to a separate file. Cache local models token counts
2023-08-23 02:38:43 +03:00
Cohee
based
Aisu Wata
EX3-0
anon
khanon
h-a-s-k
valadaptive
DonMoralez
artisticMink
RossAscends
Brian Dashore
Maks
Jason Wu
maver