731 Commits

Author SHA1 Message Date
Cohee
456c4c333f Creator notes in char list are no longer first line only. 2024-03-02 19:46:59 +02:00
Cohee
95c49029f7 Add aphrodite model selector 2024-03-01 23:02:43 +02:00
Cohee
d57b5ad6f7 Fix code style 2024-03-01 21:35:33 +02:00
Cohee
81bf6cb399
Merge pull request #1872 from Technologicat/fragment-search-chats
Fragment search (a.k.a. swoop) for Manage chat files
2024-03-01 21:30:41 +02:00
Cohee
b716dfbc0d
Merge pull request #1874 from deciare/underline-text-format
Support underlined text formatting
2024-03-01 17:49:14 +02:00
Deciare
d554edc023 Support underlined text formatting.
- Enable the `underline` option for Showdown.
- Implement option for underlined text colour.
- Update stylesheet.
2024-03-01 00:35:27 -05:00
Juha Jeronen
e3084dda17 Manage chat files: UX: focus the search field when the view opens 2024-02-29 14:22:51 +02:00
Juha Jeronen
f8f6dd1d90 Manage chat files: fragment search a.k.a. swoop 2024-02-29 14:22:35 +02:00
Cohee
3d84ae026d Fix formatting 2024-02-29 11:50:41 +02:00
berbant
a85a2bbab1
Merge branch 'SillyTavern:staging' into staging 2024-02-28 22:46:43 +04:00
Deciare
2a4b8ac438 Update displayed prompt bias when auto-saving edits.
When Auto-save Message Edits is enabled, the prompt bias string
displayed beneath the textarea wasn't being updated.
2024-02-27 05:17:38 -05:00
Deciare
7885f19e86 Perform macro substitution while updating message.
This addresses 3 issues:
1. Prompt bias string was not removed from the text of the edited
  message.
2. Macro substitition was not performed in the prompt bias string.
3. Macro substitution was not performed in the edited message text.
2024-02-27 05:17:31 -05:00
Cohee
f962ad5c02 Add OpenRouter as a text completion source 2024-02-25 22:47:07 +02:00
berbant
3c620effaf
Update script.js 2024-02-25 21:19:28 +04:00
Cohee
fc289126fa Add event type for text completion generation request settings ready 2024-02-24 21:45:33 +02:00
Cohee
d5bf9fc28c Non-streaming logprobs for Aphrodite 2024-02-24 20:53:23 +02:00
Cohee
d140b8d5be Parse non-streaming tabby logprobs 2024-02-24 20:10:53 +02:00
Cohee
3441667336 #1853 Add WI/Script link by entry automation id 2024-02-24 17:22:51 +02:00
Cohee
13aebc623a
Merge pull request #1854 from deciare/llamacpp-probs
Request and display token probabilities from llama.cpp backend
2024-02-24 15:06:28 +02:00
Cohee
eaadfea639 Extend debounce duration of logprobs renderer 2024-02-24 15:03:57 +02:00
Cohee
9287ff18de Fix for non-streaming 2024-02-24 14:50:06 +02:00
NWilson
f569424f3e Merge branch 'staging' into InfermaticAI 2024-02-22 08:32:10 -06:00
Cohee
711fd0517f Merge branch 'staging' into pygimport 2024-02-21 11:26:47 +02:00
Cohee
8e66a14e37 Add hints to doc strings about additional command prompts 2024-02-20 02:29:14 +02:00
Cohee
79ba026486
Merge pull request #1840 from Wolfsblvt/slash-commands-menu-actions-allow-custom-prompts
Extend impersonate/continue/regenerate with possible custom prompts (via slash commands and popup menu)
2024-02-20 02:26:41 +02:00
Cohee
061b7c6922 Don't try to execute script commands if the message doesn't start with slash 2024-02-20 02:09:01 +02:00
Wolfsblvt
a5ee46cb2a Only respect slash command, ignore text field 2024-02-19 22:36:32 +01:00
Wolfsblvt
550d8483cc Extend impersonate/continue/regenerate with possible custom prompts
- Use custom prompt provided via slash command arguments (similar to /sysgen and others)
- Use written text from textbox, if the popout menu actions are clicked
2024-02-19 22:23:58 +01:00
NWilson
030806bf1e Merge remote-tracking branch 'origin/staging' into InfermaticAI 2024-02-19 10:14:06 -06:00
Cohee
3c2113a6e7 Add ability to preserve file names when loading from assets downloader 2024-02-19 00:17:23 +02:00
Cohee
e4a48cd28f Add pyg hint to import UI 2024-02-17 03:54:13 +02:00
NWilson
8075e4cd1e Changes 2024-02-16 09:07:06 -06:00
NWilson
b5887960b6 Merge branch 'release' into InfermaticAI 2024-02-16 08:53:04 -06:00
Cohee
9d713825c2 #1827 Consolidate {{group}} macro behavior 2024-02-12 16:23:01 +02:00
Cohee
72256110a7 Unbreak current chat rename 2024-02-12 02:55:16 +02:00
Cohee
354c52d997 #1814 Fix regex placement attribution 2024-02-11 16:52:14 +02:00
Cohee
03ad72b6c7
Merge pull request #1802 from Technologicat/modelname
{{model}} substitution to get name of current LLM
2024-02-08 11:36:02 +02:00
Juha Jeronen
a49d0f1050 use getGeneratingModel 2024-02-08 11:13:54 +02:00
Cohee
04372848c8 Fix for undefined chats 2024-02-07 23:58:05 +02:00
Juha Jeronen
2dcb490e43 add {{model}} substitution macro to get name of current LLM
This is useful in the character card for an AI assistant, see #1774.

Tested with the Textgen backend, but should work with others too.

Horde will show only "Connected", and Novel will show the tier,
but Kobold and Textgen will show the model name.

If not connected, on any backend, will show "no_connection".
2024-02-07 23:29:32 +02:00
Juha Jeronen
c1a5b50aae improve description for consistency 2024-02-07 23:12:21 +02:00
Juha Jeronen
5183fb40a2 refactor to improve proposed implementation of /getchatname 2024-02-07 23:09:51 +02:00
Juha Jeronen
5d1f3b13ea add /getchatname slash command to get name of current chat file
Example:

/getchatname | /echo {{pipe}}
2024-02-07 22:51:41 +02:00
Cohee
8ecab19966
Merge pull request #1798 from oobabooga/staging
Add API key field for text-generation-webui
2024-02-07 19:24:42 +02:00
Juha Jeronen
f0cffb3dd9 fix /delchat for characters with lots of chat files 2024-02-07 15:20:37 +02:00
oobabooga
21fb143718 Add API key 2024-02-06 20:00:16 -08:00
Cohee
2815990589 Force personas sort before returning to caller 2024-02-05 10:58:35 +02:00
Cohee
f12aeeed90 Firefox copium for persona images 2024-02-05 02:18:44 +02:00
Cohee
7ac6ed267f #1782 OpenAI multiswipe 2024-02-04 03:36:37 +02:00
Cohee
37d94a4331 #1775 Fix personas name sorting 2024-02-03 01:52:57 +02:00