AI/text-generation-webui
1
0
Fork 0
mirror of https://github.com/oobabooga/text-generation-webui.git synced 2024-10-01 01:26:03 -04:00
Code Issues Packages Projects Releases Wiki Activity
2,533 Commits 3 Branches 50 Tags 72 MiB
644a9b8765
Commit Graph

295 Commits

Author SHA1 Message Date
oobabooga
a84f499718 Allow extensions to define custom CSS and JS 2023-05-17 00:30:54 -03:00
pixel
458a627ab9
fix: elevenlabs cloned voices do not show up in webui after entering API key (#2107) 2023-05-16 20:21:36 -03:00
Orbitoid
428261eede
fix: elevenlabs removed the need for the api key for refreshing voices (#2097) 2023-05-16 13:34:49 -03:00
atriantafy
26cf8c2545
add api port options (#1990) 2023-05-15 20:44:16 -03:00
oobabooga
897fa60069 Sort selected superbooga chunks by insertion order 
For better coherence
 2023-05-14 22:19:29 -03:00
Luis Lopez
b07f849e41
Add superbooga chunk separator option (#2051) 2023-05-14 21:44:52 -03:00
matatonic
ab08cf6465
[extensions/openai] clip extra leading space (#2042) 2023-05-14 12:57:52 -03:00
oobabooga
5f6cf39f36 Change the injection context string 2023-05-13 14:23:02 -03:00
oobabooga
7cc17e3f1f Refactor superbooga 2023-05-13 14:15:40 -03:00
oobabooga
826c74c201 Expand superbooga to instruct mode and change the chat implementation 2023-05-13 12:50:19 -03:00
oobabooga
c746a5bd00 Add .rstrip(' ') to openai api 2023-05-12 14:40:48 -03:00
Damian Stewart
3f1bfba718
Clarify how to start server.py with multimodal API support (#2025) 2023-05-12 14:37:49 -03:00
oobabooga
146a9cb393 Allow superbooga to download URLs in parallel 2023-05-12 14:19:55 -03:00
matatonic
f98fd01dcd
is_chat=False for /edits (#2011) 2023-05-11 19:15:11 -03:00
oobabooga
0d36c18f5d Always return only the new tokens in generation functions 2023-05-11 17:07:20 -03:00
matatonic
c4f0e6d740
is_chat changes fix for openai extension (#2008) 2023-05-11 16:32:25 -03:00
oobabooga
638c6a65a2
Refactor chat functions (#2003) 2023-05-11 15:37:04 -03:00
matatonic
309b72e549
[extension/openai] add edits & image endpoints & fix prompt return in non --chat modes (#1935) 2023-05-11 11:06:39 -03:00
oobabooga
943b5e5f80 Minor bug fix 2023-05-10 23:54:25 -03:00
oobabooga
9695bfe117 Add an option for cleaning up html in superbooga 2023-05-10 23:51:52 -03:00
oobabooga
f1d10edcb7
Update README.md 2023-05-10 12:13:14 -03:00
oobabooga
c35860ff2f Add a link to silero samples 2023-05-10 01:39:35 -03:00
oobabooga
3913155c1f
Style improvements (#1957) 2023-05-09 22:49:39 -03:00
missionfloyd
fe4dfc647d
SileroTTS preview (#1934) 2023-05-09 20:28:59 -03:00
oobabooga
8fa5f651d6 Style changes 2023-05-09 20:20:35 -03:00
Wojtab
e9e75a9ec7
Generalize multimodality (llava/minigpt4 7b and 13b now supported) (#1741) 2023-05-09 20:18:02 -03:00
Jeffrey Lin
791a38bad1
[extensions/openai] Support undocumented base64 'encoding_format' param for compatibility with official OpenAI client (#1876) 2023-05-08 22:31:34 -03:00
kaiokendev
0e27b660e8
Fix issue where n_results/k > index size (#1929) 2023-05-08 21:16:00 -03:00
oobabooga
b5260b24f1
Add support for custom chat styles (#1917) 2023-05-08 12:35:03 -03:00
oobabooga
82eb284a3f Fix a bug in silero tts 2023-05-07 23:59:43 -03:00
oobabooga
b3bbda22d1 Exception handling 2023-05-07 16:50:45 -03:00
oobabooga
8515f19078 Fix typing error 2023-05-07 16:25:39 -03:00
oobabooga
6b67cb6611 Generalize superbooga to chat mode 2023-05-07 15:05:26 -03:00
oobabooga
ec1cda0e1f Rename superbig to superbooga 2023-05-07 13:29:49 -03:00
oobabooga
8216c8f732 Handle multiline inputs 2023-05-07 11:54:26 -03:00
oobabooga
a35a2fab02 Reorganize superbig ui 2023-05-07 11:30:16 -03:00
oobabooga
befa307c42 Add support for loading multiple URLs into superbig 2023-05-07 11:08:02 -03:00
oobabooga
04eca9b65b Make chunk length/count customizable 2023-05-07 05:02:04 -03:00
oobabooga
8c06eeaf84 Add requirement 2023-05-07 04:50:12 -03:00
oobabooga
58f9a30be1 Add support for input file/url in superbig 2023-05-07 04:49:02 -03:00
oobabooga
6afba065a1 Only update the chroma database when necessary 2023-05-07 04:03:17 -03:00
kaiokendev
5a4bd3918c
Add SuperBIG extension (alpha) (#1548) 
---------

Co-authored-by: kaiokendev <>
Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-05-07 03:50:12 -03:00
oobabooga
85238de421 Remove unused variable 2023-05-06 11:03:12 -03:00
oobabooga
de9c4e260e
Minor fixes to elevenlabs_tts 2023-05-06 10:57:34 -03:00
Steve Randall
b03a2ac512
Elevenlabs Extension Improvement and migration to official API (#1830) 2023-05-06 10:56:31 -03:00
oobabooga
8aafb1f796
Refactor text_generation.py, add support for custom generation functions (#1817) 2023-05-05 18:53:03 -03:00
oobabooga
4bf7253ec5 Fix typing bug in api 2023-05-03 19:27:20 -03:00
Thireus ☠
4883e20fa7
Fix openai extension script.py - TypeError: '_Environ' object is not callable (#1753) 2023-05-03 09:51:49 -03:00
Wojtab
80c2f25131
LLaVA: small fixes (#1664) 
* change multimodal projector to the correct one

* remove reference to custom stopping strings from readme

* fix stopping strings if tokenizer extension adds/removes tokens

* add API example

* LLaVA 7B just dropped, add to readme that there is no support for it currently
 2023-05-02 23:12:22 -03:00
oobabooga
c31b0f15a7 Remove some spaces 2023-05-02 23:07:07 -03:00
oobabooga
320fcfde4e Style/pep8 improvements 2023-05-02 23:05:38 -03:00
matatonic
7ac41b87df
add openai compatible api (#1475) 2023-05-02 22:49:53 -03:00
oobabooga
88cdf6ed3d Prevent websocket from disconnecting 2023-05-02 19:03:19 -03:00
oobabooga
d87ca8f2af LLaVA fixes 2023-04-26 03:47:34 -03:00
oobabooga
68ed73dd89 Make API extension print its exceptions 2023-04-25 23:23:47 -03:00
Wojtab
65beb51b0b
fix returned dtypes for LLaVA (#1547) 2023-04-25 21:25:34 -03:00
MajdajkD
c86e9a3372
fix websocket batching (#1511) 2023-04-24 03:51:32 -03:00
Wojtab
04b98a8485
Fix Continue for LLaVA (#1507) 2023-04-23 22:58:15 -03:00
Wojtab
12212cf6be
LLaVA support (#1487) 2023-04-23 20:32:22 -03:00
Andy Salerno
654933c634
New universal API with streaming/blocking endpoints (#990) 
Previous title: Add api_streaming extension and update api-example-stream to use it

* Merge with latest main

* Add parameter capturing encoder_repetition_penalty

* Change some defaults, minor fixes

* Add --api, --public-api flags

* remove unneeded/broken comment from blocking API startup. The comment is already correctly emitted in try_start_cloudflared by calling the lambda we pass in.

* Update on_start message for blocking_api, it should say 'non-streaming' and not 'streaming'

* Update the API examples

* Change a comment

* Update README

* Remove the gradio API

* Remove unused import

* Minor change

* Remove unused import

---------

Co-authored-by: oobabooga <112222186+oobabooga@users.noreply.github.com>
 2023-04-23 15:52:43 -03:00
oobabooga
7ff645899e Fix bug in api extension 2023-04-22 17:33:36 -03:00
AICatgirls
b992c9236a
Prevent API extension responses from getting cut off with --chat enabled (#1467) 2023-04-22 16:06:43 -03:00
Φφ
143e88694d
SD_api_pictures: Modefix, +hires options, UI layout change (#1400) 2023-04-21 17:49:18 -03:00
oobabooga
ff0d0ac552 Api extension bug fix 2023-04-20 13:26:58 -03:00
oobabooga
96ba55501c Rename custom_stopping_strings in the api extension 2023-04-20 00:15:32 -03:00
oobabooga
b0c762ceba
Revert a change 
I think that this may be needed for some clients
 2023-04-18 04:10:45 -03:00
oobabooga
163ea295e7 Fix but in API extension 2023-04-17 13:54:15 -03:00
oobabooga
19e3a59997 Remove unused extension 2023-04-17 11:06:08 -03:00
GuizzyQC
5011f94659
Improved compatibility between silero and sd_api_pictures (#1196) 2023-04-16 21:18:52 -03:00
oobabooga
b937c9d8c2
Add skip_special_tokens checkbox for Dolly model (#1218) 2023-04-16 14:24:49 -03:00
Lou Bernardi
4d13cc0a1f
Suppress whisper_stt pip warning (#1215) 2023-04-15 01:15:59 -03:00
oobabooga
7a0ef1c941 Reorganize whisper extension 2023-04-13 10:40:27 -03:00
Φφ
1d8526849b
SD_api_pictures: Fix for metadata (#1082) 2023-04-12 11:42:30 -03:00
oobabooga
4f7e88c043 Simplify send_pictures 2023-04-12 10:30:12 -03:00
oobabooga
80f4eabb2a Fix send_pictures extension 2023-04-12 10:27:06 -03:00
oobabooga
49ce866c99 Fix silero_tts 2023-04-12 00:58:11 -03:00
Tymec
832ee4323d
API: add endpoint for counting tokens (#1051) 2023-04-11 23:08:42 -03:00
Alexander01998
61641a4551
Add missing new parameters to API extension 2023-04-11 22:41:13 -03:00
oobabooga
dc3c9d00a0 Update the API extension 2023-04-11 13:07:45 -03:00
oobabooga
64f5c90ee7 Fix the API extension 2023-04-10 20:14:38 -03:00
BlueprintCoding
8178fde2cb
Added dropdown to character bias. (#986) 2023-04-09 23:44:31 -03:00
Φφ
c97c270040
Send_pictures small fix (#546) 2023-04-08 01:55:16 -03:00
Φφ
ffd102e5c0
SD Api Pics extension, v.1.1 (#596) 2023-04-07 21:36:04 -03:00
oobabooga
5543a5089d Auto-submit the whisper extension transcription 2023-04-07 15:57:51 -03:00
oobabooga
1dc464dcb0 Sort imports 2023-04-07 14:42:03 -03:00
Φφ
e563b015d8
Silero TTS offline cache (#628) 2023-04-07 12:15:57 -03:00
oobabooga
1c413ed593 Remove torch from silero 2023-04-07 11:51:50 -03:00
da3dsoul
3f922d4bfb
Extract the Preprocessing for Silero into a file and Improve it (#757) 2023-04-07 11:46:29 -03:00
oobabooga
46c4654226 More PEP8 stuff 2023-04-07 00:52:02 -03:00
oobabooga
ea6e77df72
Make the code more like PEP8 for readability (#862) 2023-04-07 00:15:45 -03:00
oobabooga
3f3e42e26c
Refactor several function calls and the API 2023-04-06 01:22:15 -03:00
oobabooga
e722c240af Add Instruct mode 2023-04-05 13:54:50 -03:00
oobabooga
ca8bb38949 Simplify gallery 2023-04-05 00:34:17 -03:00
oobabooga
80dfba05f3 Better crop/resize cached images 2023-04-04 22:52:15 -03:00
oobabooga
65d8a24a6d Show profile pictures in the Character tab 2023-04-04 22:28:49 -03:00
Niels Mündler
7aab88bcc6
Give API extension access to all generate_reply parameters (#744) 
* Make every parameter of the generate_reply function parameterizable

* Add stopping strings as parameterizable
 2023-04-03 13:31:12 -03:00
TheTerrasque
2157bb4319
New yaml character format (#337 from TheTerrasque/feature/yaml-characters) 
This doesn't break backward compatibility with JSON characters.
 2023-04-02 20:34:25 -03:00
oobabooga
b0890a7925 Add shared.is_chat() function 2023-04-01 20:15:00 -03:00
oobabooga
3b90d604d7 Sort the imports 2023-03-31 02:01:48 -03:00
ye7iaserag
ec093a5af7
Fix div alignment for long strings 2023-03-31 06:54:24 +02:00
oobabooga
3737eafeaa Remove a border and allow more characters per pagination page 2023-03-31 00:48:50 -03:00
ye7iaserag
f9940b79dc
Implement character gallery using Dataset 2023-03-31 04:56:49 +02:00
Maya Eary
d1377c37af Fixes for api server - chat mode and integer temperature 2023-03-28 20:57:16 +03:00
Φφ
1a1e420e65 Silero_tts streaming fix 
Temporarily suppress the streaming during the audio response as it would interfere with the audio (making it stutter and play anew)
 2023-03-25 21:33:30 +03:00
oobabooga
bfe960731f
Merge branch 'main' into fix/api-reload 2023-03-24 16:54:41 -03:00
oobabooga
4a724ed22f
Reorder imports 2023-03-24 16:53:56 -03:00
oobabooga
d5fc1bead7
Merge pull request #489 from Brawlence/ext-fixes 
Extensions performance & memory optimisations
 2023-03-22 16:10:59 -03:00
oobabooga
bfb1be2820
Minor fix 2023-03-22 16:09:48 -03:00
oobabooga
0abff499e2
Use image.thumbnail 2023-03-22 16:03:05 -03:00
oobabooga
104212529f
Minor changes 2023-03-22 15:55:03 -03:00
wywywywy
61346b88ea
Add "seed" menu in the Parameters tab 2023-03-22 15:40:20 -03:00
Φφ
5389fce8e1 Extensions performance & memory optimisations 
Reworked remove_surrounded_chars() to use regular expression ( https://regexr.com/7alb5 ) instead of repeated string concatenations for elevenlab_tts, silero_tts, sd_api_pictures. This should be both faster and more robust in handling asterisks.

Reduced the memory footprint of send_pictures and sd_api_pictures by scaling the images in the chat to 300 pixels max-side wise. (The user already has the original in case of the sent picture and there's an option to save the SD generation).
This should fix history growing annoyingly large with multiple pictures present
 2023-03-22 11:51:00 +03:00
oobabooga
536d0a4d93
Add an import 2023-03-20 14:00:40 -03:00
oobabooga
a90f507abe
Exit elevenlabs_tts if streaming is enabled 2023-03-20 11:49:42 -03:00
oobabooga
31ab2be8ef Remove redundant requirements #309 2023-03-19 22:10:55 -03:00
oobabooga
b552d2b58a Remove unused imports 
o
 2023-03-19 19:24:41 -03:00
oobabooga
eab8de0d4a Merge branch 'main' into Brawlence-main 2023-03-19 13:09:59 -03:00
Maya
099d7a844b Add setup method to extensions 2023-03-19 13:22:24 +00:00
Maya
bd27353a08 Fix duplicating server on ui reload 2023-03-19 12:51:27 +00:00
oobabooga
7da742e149
Merge pull request #207 from EliasVincent/stt-extension 
Extension: Whisper Speech-To-Text Input
 2023-03-17 12:37:23 -03:00
oobabooga
1c378965e1 Remove unused imports 2023-03-16 10:18:34 -03:00
awoo
0552ab2e9f flask_cloudflared for shared tunnels 2023-03-16 02:00:16 +03:00
awoo
30281122a5 KoboldAI api 2023-03-15 23:52:46 +03:00
oobabooga
1413931705 Add a header bar and redesign the interface (#293) 2023-03-15 12:01:32 -03:00
Φφ
d537b28d02 Extension: Stable Diffusion Api integration 
Lets the bot answer you with a picture!
 2023-03-14 06:49:10 +03:00
oobabooga
3fb8196e16 Implement "*Is recording a voice message...*" for TTS #303 2023-03-13 22:28:00 -03:00
EliasVincent
02e1113d95 add auto-transcribe option 2023-03-13 21:41:19 +01:00
stefanhamburger
91c2a8e88d
Fix: tuple object does not support item assignment 2023-03-13 07:42:09 +01:00
oobabooga
77294b27dd Use str(Path) instead of os.path.abspath(Path) 2023-03-13 00:08:01 -03:00
oobabooga
1ddcd4d0ba Clean up silero_tts 
This should only be used with --no-stream.

The shared.still_streaming implementation was faulty by design:
output_modifier should never be called when streaming is already over.
 2023-03-12 23:42:49 -03:00
EliasVincent
48aa52849b use Gradio microphone input instead 2023-03-12 21:03:07 +01:00
Elias Vincent Simon
3b4145966d
Merge branch 'oobabooga:main' into stt-extension 2023-03-12 19:19:43 +01:00
oobabooga
d8bea766d7
Merge pull request #192 from xanthousm/main 
Add text generation stream status to shared module, use for better TTS with auto-play
 2023-03-12 13:40:16 -03:00
oobabooga
4066ab4c0c Reorder the imports 2023-03-12 13:36:18 -03:00
Phuoc-Hieu Le
781c09235c
Fix typo error in script.py 2023-03-12 15:21:50 +07:00
Xan
b3e10e47c0 Fix merge conflict in text_generation 
- Need to update `shared.still_streaming = False` before the final `yield formatted_outputs`, shifted the position of some yields.
 2023-03-12 18:56:35 +11:00
Xan
d4afed4e44 Fixes and polish 
- Change wav naming to be completely unique using timestamp instead of message ID, stops browser using cached audio when new audio is made with the same file name (eg after regenerate or clear history).
- Make the autoplay setting actually disable autoplay.
- Make Settings panel a bit more compact.
- Hide html errors when audio file of chat history is missing.
- Add button to permanently convert TTS history to normal text messages
- Changed the "show message text" toggle to affect the chat history.
 2023-03-12 17:56:57 +11:00
oobabooga
195e99d0b6 Add llama_prompts extension 2023-03-11 16:11:15 -03:00
oobabooga
8f8da6707d Minor style changes to silero_tts 2023-03-11 11:17:13 -03:00
Xan
0dfac4b777 Working html autoplay, clean up, improve wav naming 
- New autoplay using html tag, removed from old message when new input provided
- Add voice pitch and speed control
- Group settings together
- Use name + conversation history to match wavs to messages, minimize problems when changing characters

Current minor bugs:
- Gradio seems to cache the audio files, so using "clear history" and generating new messages will play the old audio (the new messages are saving correctly). Gradio will clear cache and use correct audio after a few messages or after a page refresh.
- Switching characters does not immediately update the message ID used for the audio. ID is updated after the first new message, but that message will use the wrong ID
 2023-03-11 16:34:59 +11:00
EliasVincent
1c0bda33fb added installation instructions 2023-03-10 11:47:16 +01:00
EliasVincent
a24fa781f1 tweaked Whisper parameters 2023-03-09 21:18:46 +01:00
EliasVincent
00359ba054 interactive preview window 2023-03-09 21:03:49 +01:00
EliasVincent
7a03d0bda3 cleanup 2023-03-09 20:33:00 +01:00
EliasVincent
4c72e43bcf first implementation 2023-03-09 12:46:50 +01:00
Xan
a2b5383398 Merge in audio generation only on text stream finish., postpone audioblock autoplay 
- Keeping simpleaudio until audio block "autoplay" doesn't play previous messages
- Only generate audio for finished messages
- Better name for autoplay, clean up comments
- set default to unlimited wav files. Still a few bugs when wav id resets

Co-Authored-By: Christoph Hess <9931495+ChristophHess@users.noreply.github.com>
 2023-03-09 10:48:44 +11:00
Xan
738be6dd59 Fix merge errors and unlimited wav bug 2023-03-08 22:25:55 +11:00
Xan
5648a41a27 Merge branch 'main' of https://github.com/xanthousm/text-generation-webui 2023-03-08 22:08:54 +11:00
Xan
ad6b699503 Better TTS with autoplay 
- Adds "still_streaming" to shared module for extensions to know if generation is complete
- Changed TTS extension with new options:
   - Show text under the audio widget
   - Automatically play the audio once text generation finishes
   - manage the generated wav files (only keep files for finished generations, optional max file limit)
   - [wip] ability to change voice pitch and speed
- added 'tensorboard' to requirements, since python sent "tensorboard not found" errors after a fresh installation.
 2023-03-08 22:02:17 +11:00
oobabooga
44e6d82185 Remove unused imports 2023-03-07 22:56:15 -03:00