Commit Graph

1658 Commits

Author SHA1 Message Date
Cohee
d38a4dc6c1 Fix abort group generation 2023-12-11 20:03:31 +02:00
Cohee
0302686a96 Return from Generate if calling circuit breaker 2023-12-11 19:07:33 +02:00
Cohee
e96fb0c1b5 Fix group wrapper not resolving to a valid text 2023-12-11 19:00:42 +02:00
Cohee
0fcf8fd491 Typing indicator fixed 2023-12-11 18:23:00 +02:00
valadaptive
33f969f097 Have Generate() return a promise
Generate(), being async, now returns a promise-within-a-promise.
If called with `let p = await Generate(...)`, it'll wait for generation
to *start*. If you then `await p`, you'll wait for generation to
*finish*. This makes it much easier to tell exactly when generation's
done. generateGroupWrapper has been similarly modified.
2023-12-10 12:30:10 -05:00
valadaptive
03884b29ad Always call resolve in Generate()
This lets us get rid of the janky hack in group-chats to tell when a
message is done generating.
2023-12-10 12:26:30 -05:00
valadaptive
f5d2e50f5e Remove isGenerationAborted
Just check the AbortSignal.
2023-12-10 12:24:18 -05:00
Cohee
dbd52a7994
Merge pull request #1482 from valadaptive/sse-stream
Refactor server-sent events parsing
2023-12-10 18:32:19 +02:00
Cohee
af89cfa870 Code clean-up 2023-12-10 16:48:25 +02:00
Cohee
5054de247b Merge branch 'staging' into qr-editor-tab-support 2023-12-10 16:36:28 +02:00
Cohee
9acef0fae6 Horde doesn't support API tokenizers 2023-12-10 16:21:06 +02:00
Cohee
f54bf99006 Fix token ids not displaying in "API_CURRENT" mode for TextGen 2023-12-10 16:09:00 +02:00
Cohee
6957d9e7cf Fix display names of Best match tokenizers 2023-12-10 16:03:25 +02:00
Cohee
6e5eea5dba Unbreak previously selected API tokenizer in dropdown 2023-12-10 15:56:38 +02:00
Cohee
d5140142fb Merge branch 'staging' into tokenizers-cleanup 2023-12-10 15:51:15 +02:00
Cohee
5f1683f43a More input padding and stricter sanitation 2023-12-10 15:07:39 +02:00
valadaptive
0201a0260c Default event type to 'message' if it's empty
Added to the upstream test suite. Matches the spec.
2023-12-10 04:45:10 -05:00
valadaptive
55976e61a3 Fix tokenizer override
I searched for all users of tokenizers.API, but missed that the menu
converts the numerical select values directly to enum values. I've used
the special tokenizer value 98 to represent "the tokenizer API for
whichever backend we're currently using".
2023-12-09 23:57:21 -05:00
valadaptive
0fce475a95 Implement random sort with a shuffle
Sorting with a random comparator doesn't actually shuffle an array.
Depending on the sorting algorithm used, there will be a bias to the
shuffle (see https://bost.ocks.org/mike/shuffle/compare.html).
If you open that link in Firefox, the bias will be especially bad.
Instead of implementing "random" character sort using a random sort
comparator, use the shuffle function instead.
2023-12-09 22:52:38 -05:00
valadaptive
014416546c Add padding once in getTokenCount
This means we don't have to pass the "padding" parameter into every
function so they can add the padding themselves--we can do it in just
one place instead.
2023-12-09 20:53:16 -05:00
valadaptive
2f2cd197cc Clean up tokenizer API code
Store the URLs for each tokenizer's action in one place at the top of
the file, instead of in a bunch of switch-cases. The URLs for the
textgen and Kobold APIs don't change and hence don't need to be
function arguments.
2023-12-09 20:48:41 -05:00
valadaptive
09465fbb97 Inline most get(...)TokenizerParams calls
For everything except textgenerationwebui, these params are now simple
enough that it doesn't make sense for them to be in a separate function.
2023-12-09 20:35:11 -05:00
valadaptive
30502ac949 Split up Kobold and textgenerationwebui endpoints
The endpoint was one big if/else statement that did two entirely
different things depending on the value of main_api. It makes more sense
for those to be two separate endpoints.
2023-12-09 20:26:24 -05:00
valadaptive
7486ab3886 Separate textgen and Kobold tokenization APIs
They function differently and have different logic and API parameters,
so it makes sense to count them as two different APIs. Kobold's API
doesn't return tokens, so it can only be used to count them.

There's still a lot of duplicate code which I will clean up in the
following commits.
2023-12-09 20:24:56 -05:00
valadaptive
18177c147d Separate remote and server tokenization code paths
This lets us remove extraneous API params from paths where they aren't
needed.
2023-12-09 20:08:48 -05:00
valadaptive
ddd73a204a Remove "remote" language from tokenizer functions
We'll be making a distinction between tokenizing *on* the server itself,
and tokenizing via the server having the AI service do it. It makes more
sense to use the term "remote" for the latter.
2023-12-09 19:49:22 -05:00
valadaptive
8bad059a62 Rename /tokenize_via_api endpoint
No redirect for this since I don't expect any extensions to be calling this directly.
2023-12-09 19:29:24 -05:00
LenAnderson
a3ec8d709d add support for tab and shift-tab in QR editor 2023-12-09 17:56:36 +00:00
Cohee
2d7811fa46
Merge pull request #1499 from LenAnderson/qr-execute-from-any-preset
Allow /run for quick replies from any preset
2023-12-09 19:49:03 +02:00
LenAnderson
d00861d913 allow /run for quick replies from other presets
/run otherPresetName.quickReplyLabel
2023-12-09 17:20:15 +00:00
Cohee
e79f6d82da
Merge pull request #1498 from artisticMink/bulkedit-delete-optimization
Only refresh character list after all deletions have been processed.
2023-12-09 18:07:44 +02:00
Cohee
b915b89ca9 Fix ESLint 2023-12-09 16:09:10 +02:00
Cohee
ad9130b538 Single doc mode: edit on click 2023-12-09 16:01:43 +02:00
artisticMink
dfd41a110a Prevent 'no such file or directory' error when mass deleting characters 2023-12-09 14:36:37 +01:00
artisticMink
ba3966e148 Only refresh character list after all deletions have been processed. 2023-12-09 14:31:18 +01:00
valadaptive
d735b12399 Refactor event stream parsing
I was really overcomplicating this before; this is simpler and faster.
Passes my existing test suite.
2023-12-08 15:05:57 -05:00
valadaptive
699c369443 Remove ignoreBOM
Apparently the ignoreBOM option actually means "include the BOM". I've
added a test for this in my own repository, and will also be submitting
a pull request to MDN to clarify this in their documentation.
2023-12-07 23:15:55 -05:00
Cohee
b0e7b73a32 Fix streaming processor error handler hooks 2023-12-08 02:01:08 +02:00
valadaptive
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
valadaptive
cdcd913805 Don't stream events if the API returned a 4xx code 2023-12-07 18:00:36 -05:00
valadaptive
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
Cohee
6f610204d6
Merge pull request #1488 from LenAnderson/add-index-argument-to-setvar-/-setglobalvar
Add index argument to setvar / setglobalvar
2023-12-08 00:40:14 +02:00
Cohee
2607e787ff Put comment command on hold 2023-12-08 00:38:13 +02:00
Cohee
e2f886d796 Revert pipe caching 2023-12-08 00:33:27 +02:00
Cohee
7f7ad6f523 Merge branch 'staging' into backgrounds-endpoint 2023-12-07 23:16:33 +02:00
Cohee
404b1562e5
Merge pull request #1491 from valadaptive/stats-endpoint
Move stats endpoints into their own module
2023-12-07 23:11:12 +02:00
valadaptive
2367f4f38f Rename backgrounds API endpoints 2023-12-07 15:17:19 -05:00
LenAnderson
65f2cc1952 add a comment slash commend /#
for commenting longer ST scripts
2023-12-07 18:29:28 +00:00
LenAnderson
d52b5fb947 pass prev pipeResult through if result undefined 2023-12-07 18:28:58 +00:00
LenAnderson
5a719d635a use isArray instead of instanceof 2023-12-07 18:27:11 +00:00