Commit Graph

945 Commits

Author SHA1 Message Date
Kwaroran
821ba1812f Merge branch 'main' of https://github.com/kwaroran/RisuAI 2025-01-02 03:03:03 +09:00
Kwaroran
866996ba1e chore: update version to 145.3.0 2025-01-02 03:02:54 +09:00
LightningHyperBlaze45654
d2042116aa Fix: Token counting fix 2024-12-31 21:52:13 -08:00
Kwaroran
cd092a5a01 feat: add translation feature and ban character set functionality 2024-12-29 04:03:21 +09:00
kwaroran
03acfdc306 Bugfix on hypaV2 (#696)
# PR Checklist
- [ ] Have you checked if it works normally in all models? *Ignore this
if it doesn't use models.*
- [ ] Have you checked if it works normally in all web, local, and node
hosted versions? If it doesn't, have you blocked it in those versions?
- [ ] Have you added type definitions?

# Description
When chat imported from json, it breaks
Fixed by changing the list back to set

Need to check if there is any bug on token counting(unknown issue, so
currently re-calculating the token accurately)
2024-12-28 05:36:22 +09:00
HyperBlaze
9c1f65e518 Merge branch 'kwaroran:main' into main 2024-12-26 23:53:59 -08:00
LightningHyperBlaze45654
e51ec6c739 bugfix(read desc)
need to check if the token count is still bugged.
2024-12-26 23:53:05 -08:00
Kwaroran
ebdcd5ffcd Add new catagory 2024-12-27 16:16:36 +09:00
Kwaroran
cc223dfefa feat: limit thoughts extraction based on maxThoughtTagDepth setting 2024-12-27 15:56:48 +09:00
Kwaroran
191be6d5c1 feat: add image translation feature and enhance regex list functionality 2024-12-27 15:51:29 +09:00
poroyo
823541af40 Fix sayTTS missing break in gptsovits case 2024-12-27 04:00:19 +09:00
kwaroran
b874ed42ed HypaV2 context deletion safety (#680)
# PR Checklist
- [x] Did you check if it works normally in all models? *ignore this
when it dosen't uses models*
- [] Did you check if it works normally in all of web, local and node
hosted versions? if it dosen't, did you blocked it in those versions? <<
Checked on browser only, works fine
- [x] Did you added a type def?

# Description
HypaV2 data's large type definition update.
```ts
    mainChunks: { // summary itself
        id: number;
        text: string;
        chatMemos: Set<string>; // UUIDs of summarized chats
        lastChatMemo: string;
    }[];
    chunks: { // split mainChunks for retrieval or something. Although quite uncomfortable logic, so maybe I will delete it soon.
        mainChunkID: number;
        text:string;
    }[];
```
With this, ensure that mainChunks is relevant on chat context change by
deletion

If there is no UUID in the chat context, but it exists on chatMemos on
certain mainChunk, removes it.

Changed index.svelte.ts to update args on each call to ensure hypav2 to
stay adaptive on this change without refreshing the page

Also changed mainChunks to be pushed instead of unshifted
2024-12-26 05:02:33 +09:00
Kwaroran
2672195d92 Add preset related features 2024-12-26 04:29:14 +09:00
Kwaroran
c6cc258a50 Refactor preset handling and improve database snapshot logic 2024-12-26 03:18:00 +09:00
Kwaroran
28d8bfdd22 Fix nativeFetch and comfy 2024-12-25 21:06:52 +09:00
Kwaroran
1c51afc626 Enhance plugin functionality by adding optional provider parameters and improving thoughts extraction regex 2024-12-25 04:55:05 +09:00
Kwaroran
8b6fc5bc8b Add max_tokens parameter to plugin documentation and request function 2024-12-25 00:31:28 +09:00
kwaroran
98ca1736ab Fix thoughts extraction regex for multiline content handling (#687)
# PR Checklist
- [x] Did you check if it works normally in all models? *ignore this
when it dosen't uses models*
- [x] Did you check if it works normally in all of web, local and node
hosted versions? if it dosen't, did you blocked it in those versions?
- [ ] Did you added a type def?

# Description

This PR updates the regex used for extracting <Thoughts> content to
handle multiline cases reliably. The previous regex (.+?) had
limitations when processing text spanning multiple lines, as it could
not match content with line breaks.
2024-12-24 23:16:20 +09:00
Kwaroran
027a591424 Remove V1 Plugin 2024-12-24 23:14:49 +09:00
Kwaroran
8f667d6394 Add Saving Icon 2024-12-23 17:07:19 +09:00
LightningHyperBlaze45654
4ddb932237 add: convert previous version's hypaV2Data 2024-12-20 23:38:40 -08:00
HyperBlaze
ea2fc1ad26 Merge branch 'kwaroran:main' into main 2024-12-20 23:36:41 -08:00
Bo26fhmC5M
6d182a8ad3 Fix thoughts extraction regex for multiline content handling 2024-12-21 13:07:57 +09:00
Kwaroran
50cf5e65b8 Remove thoughts property from OpenAIChatExtra interface and clean up related request processing 2024-12-21 06:35:05 +09:00
Kwaroran
d4db95070e Update plugin documentation and types to support ReadableStream in provider results 2024-12-21 06:33:00 +09:00
Kwaroran
7cd49fc8c3 Add V2 plugin 2024-12-20 23:45:07 +09:00
Kwaroran
e5e01d0688 Fix error handling in gemini and add dataItem hotkey 2024-12-20 18:11:11 +09:00
Kwaroran
cc4bbdc8e2 Enhance LLM model flags to include requiresAlternateRole and update request processing to handle multimodal and thoughts data 2024-12-20 04:31:23 +09:00
Kwaroran
01da904c9b Gemini change thinking 2024-12-20 03:14:06 +09:00
Kwaroran
c937a65b1f Fix formatting of thoughts in request processing to ensure proper line breaks 2024-12-20 02:55:10 +09:00
Kwaroran
4afe32a2c2 Add geminiThinking flag and enhance thoughts handling in chat processing 2024-12-20 02:53:58 +09:00
Kwaroran
73e94658fd Add thoughts 2024-12-20 02:15:48 +09:00
Kwaroran
c05aa389b9 Fix devrole 2024-12-18 03:45:11 +09:00
Kwaroran
a961a553d8 Move DeveloperRole 2024-12-18 03:38:20 +09:00
Kwaroran
f09cb1bd69 Add DeveloperRole flag and update role handling in OpenAIChatExtra 2024-12-18 03:37:41 +09:00
Kwaroran
6d3fdadf55 Merge branch 'main' of https://github.com/kwaroran/RisuAI 2024-12-18 03:26:55 +09:00
Kwaroran
5df9e68bae Add o1 and fix some mistakes 2024-12-18 03:26:02 +09:00
shirosaki-hana
a092d1f482 Fixed “Separate Parameters” scaling issue
Fixed an issue where the “Temperature” parameter was not scaled correctly when using the “Separate Parameters” feature.
2024-12-17 11:30:16 +09:00
HyperBlaze
cd3294d529 Merge branch 'kwaroran:main' into main 2024-12-15 14:13:02 -08:00
Kwaroran
dcc48d5cb3 Add subtitle 2024-12-15 19:33:26 +09:00
Kwaroran
7d4030cf7a Readd Gemini stream 2024-12-14 20:10:07 +09:00
Kwaroran
f4b78480f3 Rework realm and several bug fixes 2024-12-14 19:09:28 +09:00
Kwaroran
a984b823a6 Update inlay syntax to support 'inlayed' type and adjust parsing logic 2024-12-13 00:09:13 +09:00
Kwaroran
fcd049eae8 Refactor parameter handling in requestGoogleCloudVertex function to filter parameters based on modelInfo 2024-12-12 12:56:17 +09:00
Kwaroran
146aaa1e7c Skip setting value for 'top_k' when 'ignoreTopKIfZero' is true and 'top_k' is 0 2024-12-12 12:34:10 +09:00
Kwaroran
fc571d45ac Rename parameter 'ignoreTopKIfOne' to 'ignoreTopKIfZero' 2024-12-12 10:43:18 +09:00
Kwaroran
5174082796 Add Gemini related features 2024-12-12 08:38:33 +09:00
Kwaroran
61763deaa7 Update Gemini parameters 2024-12-12 07:57:01 +09:00
Kwaroran
64e759e187 Fix mistral top_p and fix seperateParameters 2024-12-11 03:44:07 +09:00
LightningHyperBlaze45654
69f44c03c6 Merge remote-tracking branch 'upstream/main' 2024-12-08 20:08:25 -08:00