Commit Graph

243 Commits

Author SHA1 Message Date
nai-degen c0cd2c7549 adds aws opus maybe, idk cannot test 2024-04-16 11:33:44 -05:00
nai-degen 9445110727 adds gpt-4-turbo stable 2024-04-09 16:31:42 -05:00
nai-degen 34a673a80a adds option to disable multimodal prompts 2024-03-23 14:30:14 -05:00
nai-degen 8cb960e174 fixes incorrect model assignment when requesting Haiku from AWS 2024-03-21 23:21:27 -05:00
nai-degen 32fea30c91 handles Anthropic keys which cannot support multimodal requests 2024-03-20 00:03:10 -05:00
nai-degen 3f9fd25004 exempt 'special' token type from context size limits 2024-03-19 11:14:51 -05:00
nai-degen 7705ee58a0 minor cleanup of error-generator.ts 2024-03-18 15:18:18 -05:00
nai-degen 7c64d9209e minor refactoring of response middleware handlers 2024-03-17 22:20:39 -05:00
nai-degen 59107af3d6 minor fixes for google sheets backend for anthropic-chat 2024-03-17 12:08:11 -05:00
nai-degen 435280fa04 fixes missing system prompt on AWS anthropic-chat schema 2024-03-16 16:00:59 -05:00
nai-degen d9117bf08e fixes AWS debug log 2024-03-14 21:34:07 -05:00
nai-degen 57d9791270 fixes uncounted tokens when Response stream is prematurely closed 2024-03-14 21:32:20 -05:00
nai-degen 367ac3d075 adds ?debug=true query param to have proxy respond with transformed prompt 2024-03-14 08:16:38 -05:00
nai-degen 6cf029112e adds Anthropic's SOTA Haiku model; misc code cleanup 2024-03-13 20:48:05 -05:00
nai-degen 4b86802eb2 adds separate model detection for gpt-4-32k-0314 2024-03-10 19:16:11 -05:00
nai-degen 7610369c6d adds dall-e full history page and metadata downloader 2024-03-10 14:53:11 -05:00
nai-degen cec39328a2 adds azure dall-e support 2024-03-09 13:03:50 -06:00
nai-degen cab346787c fixes regression in anthropic text > anthropic chat api translation 2024-03-08 21:16:25 -06:00
nai-degen fab404b232 refactors api transformers and adds oai->anthropic chat api translation 2024-03-08 20:59:19 -06:00
nai-degen 9ce10b4f6a shows more helpful errors when users' prefills are invalid during AWS streaming 2024-03-07 13:28:23 -06:00
nai-degen 96756d32f3 fixes handling of DALL-E content_policy_violation errors 2024-03-07 12:56:35 -06:00
nai-degen 1fb3eac154 maybe shows clearer AWS ValidationExceptions when users have bad prefills 2024-03-06 05:12:47 -06:00
nai-degen 8f46bd4397 handles 'this organization is disabled' error from anthropic 2024-03-06 00:42:10 -06:00
nai-degen ddf34685df adds Claude 3 Vision support 2024-03-05 18:34:10 -06:00
nai-degen ea3aae5da6 allows selecting compat model via endpoint name and makes errors less confusing 2024-03-05 05:13:22 -06:00
nai-degen 055d650c5d fixes legacy compat endpoint 2024-03-05 01:38:39 -06:00
nai-degen 2643dfea61 improves aws sonnet key detection and no keys available error messaging 2024-03-05 01:04:08 -06:00
nai-degen 434445797a fixes bad handleCompatibilityRequest middleware fallthrough 2024-03-04 23:53:13 -06:00
nai-degen 03c5c473e1 improves error handling for sillytavern 2024-03-04 22:59:32 -06:00
nai-degen 068e7a834f fixes AWS legacy models for non-streaming requests 2024-03-04 21:22:43 -06:00
nai-degen 736803ad92 enables opus by default 2024-03-04 21:11:32 -06:00
nai-degen 51ffca480a adds AWS Claude Chat Completions and Claude 3 Sonnet support 2024-03-04 16:25:06 -06:00
nai-degen 90ddcac55b makes claude3 compat model customizable via environment variable 2024-03-04 14:21:55 -06:00
nai-degen 1edc93dc72 adds claude-opus model family 2024-03-04 14:08:59 -06:00
nai-degen f6c124c1d3 fixes issue with preamble-required claude keys and anthropic chat 2024-03-04 14:00:25 -06:00
nai-degen 90a053d0e0 detects and removes over-quota claude keys from keypool 2024-03-04 13:42:29 -06:00
khanon db318ec237 Implement Anthropic Chat Completions endpoint and Claude 3 (khanon/oai-reverse-proxy!64) 2024-03-04 19:06:46 +00:00
nai-degen b90abbda88 spoofs response for SillyTavern test messages 2024-02-28 15:57:18 -06:00
nai-degen 93cee1db9b removes claude v1 from AWS keychecker as it has been retired 2024-02-27 15:52:09 -06:00
nai-degen bd15728743 uses explicitly set keyprovider rather than inferring via requested model 2024-02-27 10:56:50 -06:00
nai-degen 627559b729 updates mistral modelids 2024-02-26 23:55:03 -06:00
nai-degen 5e19e2756a adds mistral-large model family, untested 2024-02-26 18:12:08 -06:00
nai-degen 59bda40bbc handles google streaming json response format variation 2024-02-19 00:12:09 -06:00
nai-degen 68d829bceb adds Claude over-quota detection 2024-02-17 15:56:22 -06:00
nai-degen 3498584a1f removes forceModel on Google AI endpoint 2024-02-15 11:41:34 -06:00
nai-degen 21d61da62b increases max image payload size for gpt4v 2024-02-12 21:59:48 -06:00
nai-degen 35dc0f4826 fixes 'Premature close' caused by fucked up AWS unmarshaller errors 2024-02-10 14:47:14 -06:00
devvnull 0ce4582f3b Improve "\n\nHuman" prefix requirement detection for Anthropic (khanon/oai-reverse-proxy!63) 2024-02-08 16:28:11 +00:00
nai-degen bbee056114 fixes Force Key Recheck admin function for azure/aws 2024-02-07 19:54:40 -06:00
nai-degen ecc804887b uses EventStreamMarshaller from AWS SDK to hopefully handle split messages 2024-02-05 19:56:41 -06:00