rixty/SillyTavern
1
0
Fork 0
mirror of https://github.com/SillyTavern/SillyTavern.git synced 2025-06-05 21:59:27 +02:00
Code Issues Packages Projects Releases Wiki Activity
9,466 Commits 15 Branches 92 Tags
8161690ce622a7250330611f1ff2ed4de883f945
Commit Graph

62 Commits

Author SHA1 Message Date
Cohee
3b9fcfae60 Console log Ollama model pulls 2025-03-05 21:42:56 +02:00
Cohee
861c502e44 Return type casts where they were 2025-02-25 22:12:22 +02:00
Cohee
3f03936125 Add config value type converters for numbers and booleans 2025-02-20 21:53:48 +02:00
Cohee
dd7391caaf Ollama: Add num_batch config value 2025-02-13 20:17:33 +02:00
Eradev
055a6527fc PR fixes 2025-02-02 03:10:32 -05:00
Eradev
1f9fa74786 Rewritten minLogLevel feature 2025-01-15 10:02:32 -05:00
Cohee
3167019faf Add generic text completion API type (100% OAI compatible) 2024-12-13 01:12:10 +02:00
Cohee
a86735d743 Fix sendless statuses 2024-11-30 19:30:14 +02:00
Cohee
803b7fca89 Remove custom header 2024-11-23 17:50:32 +02:00
Cohee
362bdf0c46 Don't log when no endpoint available. Remove pointless header 2024-11-23 17:32:12 +02:00
Cohee
049ae541aa Add 'node:' prefix to import 2024-11-23 16:03:13 +02:00
Karl-Johan Alm
c30dde8471 rename /chat_template to /props, and switch to non-trimmed hashes 2024-11-21 11:38:57 +09:00
Karl-Johan Alm
4214c9d894 trim chat template before hashing 2024-11-20 15:12:42 +09:00
Karl-Johan Alm
bb062f5ec9 update endpoint to reflect koboldcpp update 2024-11-20 13:11:51 +09:00
Karl-Johan Alm
feb1b91619 template derivation: add support for llama.cpp server backend 2024-11-19 23:38:38 +09:00
Karl-Johan Alm
cdc0147490 fix error console.log message 2024-11-19 21:41:57 +09:00
Karl-Johan Alm
c2eaae3d42 switch to crypto lib 2024-11-19 21:39:35 +09:00
Karl-Johan Alm
f25ea9f6d6 template derivation: move hash part to backend 2024-11-19 20:09:29 +09:00
Karl-Johan Alm
0e2fdf37a8 feature: derived templates 
This PR adds a simple hash based method for picking context and instruct templates based on the chat template, when provided by the back end.
 2024-11-19 17:27:25 +09:00
Cohee
24884b3206 TextGenWebUI: remove legacy API mode 2024-10-15 00:32:56 +03:00
Cohee
4fcad0752f [chore] Fix type errors 2024-10-11 21:33:36 +03:00
Cohee
d52b4fbbde Node: Migrate to ES Modules 2024-10-10 22:37:22 +03:00
Cohee
93bf87b035 Shut tokenization errors if not using ooba 
Closes #2849
 2024-09-22 17:44:19 +03:00
Cohee
2bc87a401e Try detect LM Studio in status check 
Fixes #2849
 2024-09-15 08:24:28 +03:00
Wolfsblvt
f5b68893d0 Improve error handling of /genraw and /gen 
- /generate TC backend returns more status/error texts
- Fix /genraw and /gen returning null/undefined
- Logging errors on /genraw if backend throws an error
- Fixes #2836
 2024-09-12 22:41:53 +02:00
Cohee
f305ba7ce7 Configurable ollama keep_alive 
Closes #1859
 2024-08-11 17:32:31 +03:00
Cohee
5f2a73ac9f Expose "Allow fallback providers" for OpenRouter 2024-07-19 23:34:16 +03:00
Cohee
f7e2d72ac7 Fix eslint 2024-07-07 22:40:03 +03:00
kingbri
0672c8422e Textgen: Add permissions check for TabbyAPI keys 
There's no formal permissions checking in ST's UI, so add a temporary
check in the server endpoint before requesting a download.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-07-07 14:40:24 -04:00
kingbri
69077f6a6e Textgen: Add model downloading for TabbyAPI 
Tabby has a HuggingFace downloader API endpoint. Add direct support
in SillyTavern by using the same method as ollama, but with the correct
parameters exposed.

Signed-off-by: kingbri <bdashore3@proton.me>
 2024-07-07 14:04:04 -04:00
Cohee
4e33253a91 Code clean-up 2024-06-28 19:12:56 +03:00
Cohee
b62cbdeebd Merge branch 'staging' into DarokCx/release 2024-06-28 19:09:12 +03:00
Cohee
bbb1a6e578 Add huggingface inference as text completion source 2024-06-28 18:17:27 +03:00
DarokCx
8608bc92ae no authorization 2024-06-27 10:02:28 -04:00
DarokCx
bd5592de7b Added featherless, connect button not working 2024-06-27 09:06:11 -04:00
Cohee
41ab90bb8e Support more parameters for Infermatic 2024-06-24 19:16:20 +03:00
Cohee
7063fce2af Selectable openrouter providers 2024-05-06 19:26:20 +03:00
sasha0552
2bd239fe81 Initial vLLM support 2024-05-02 22:40:40 +00:00
joenunezb
890cf81627 Fix: InformaticAI response without message in choices 2024-04-23 03:56:50 -07:00
Cohee
9c218455c4 [chore] Run ESLint 2024-04-12 14:22:12 +03:00
sasha0552
7348199f73 Add llama.cpp slots info endpoint (#2070) 2024-04-11 23:53:32 +03:00
sasha0552
becd17d7d2 Add some llama.cpp-specific endpoints 2024-04-10 08:11:59 +00:00
DreamGenX
bf787a9445 support dreamgen non-streaming 2024-03-08 08:32:47 +01:00
DreamGenX
5c410986a4 Add support for DreamGen API. 
API docs: https://dreamgen.com/docs/models/opus/v1
API keys: https://dreamgen.com/account/api-keys

I decided to base this on the text-completion API since it's more
flexible with SillyTavern's prompt formating capabilities.

This also means that custom context and instruct settings are required.

Will add documentation in a followup PR.
 2024-03-07 12:25:48 +01:00
Cohee
29c4334c46 #1859 Set keep_alive for ollama 2024-02-26 21:09:21 +02:00
Cohee
f962ad5c02 Add OpenRouter as a text completion source 2024-02-25 22:47:07 +02:00
NWilson
f82740a238 Change Non-streaming Handler 2024-02-22 15:51:11 -06:00
NWilson
7c12c836f2 Implement Key Filter 2024-02-20 09:40:35 -06:00
NWilson
90d5fbc182 Fix non streaming 2024-02-19 09:46:56 -06:00
NWilson
8075e4cd1e Changes 2024-02-16 09:07:06 -06:00