 nai-degen
|
b58e7cb830
|
always applies Mistral prompt fixes on messages input
|
2024-08-14 10:48:55 -05:00 |
|
|
khanon
|
f531272b00
|
Refactor AWS service code and add AWS Mistral support (khanon/oai-reverse-proxy!75)
|
2024-08-14 04:40:41 +00:00 |
|
|
nai-degen
|
b7cd326d2a
|
handles 'invalid subscription' 403 errors from Mistral API
|
2024-08-07 14:14:53 -05:00 |
|
|
nai-degen
|
6c9f302fb9
|
minor gultra fix
|
2024-08-06 18:46:49 -05:00 |
|
|
nai-degen
|
9ab1e7d0ce
|
adds new gpt4o id
|
2024-08-06 13:08:25 -05:00 |
|
|
nai-degen
|
81f8dc2613
|
updates README.md
|
2024-08-05 11:33:16 -05:00 |
|
|
khanon
|
0c936e97fe
|
Merge GCP Vertex AI implementation from cg-dot/oai-reverse-proxy (khanon/oai-reverse-proxy!72)
|
2024-08-05 14:27:51 +00:00 |
|
|
nai-degen
|
29ed07492e
|
fixes info page display for gemini flash/ultra
|
2024-08-03 22:18:05 -05:00 |
|
|
nai-degen
|
2f7315379c
|
adds gemini/makersuite keychecker, native endpoint, and streaming fixes
|
2024-08-03 21:53:32 -05:00 |
|
|
nai-degen
|
e91532f4f7
|
handle dead makersuite keys triggering 400 error instead of 401/403
|
2024-08-03 19:09:50 -05:00 |
|
|
nai-degen
|
9a3cca6b80
|
adds new mistral models and updates older model lists/context limits
|
2024-07-28 13:15:03 -05:00 |
|
|
nai-degen
|
f242777596
|
fixes token index used as msg idx in anthropic chat-to-openai SSE transformer
|
2024-07-07 13:33:33 -05:00 |
|
|
nai-degen
|
edc0d094e2
|
tries to disable quarantined aws keys
|
2024-06-30 05:08:27 -05:00 |
|
|
nai-degen
|
994b30dcce
|
adjusts gemini pro model assignment
|
2024-06-26 13:37:23 -05:00 |
|
|
nai-degen
|
b4fb97ca5c
|
fixes model id typo
|
2024-06-20 10:42:48 -05:00 |
|
|
nai-degen
|
eb700d3da6
|
adds untested claude 3.5 model ids and model assignment
|
2024-06-20 10:34:48 -05:00 |
|
|
nai-degen
|
d706d4c59d
|
adds USER_CONCURRENCY_LIMIT environment variable
|
2024-06-14 22:52:16 -05:00 |
|
|
nai-degen
|
7660ed8b94
|
allows enabling vision prompts on a per-service basis
|
2024-06-07 12:09:43 -05:00 |
|
|
nai-degen
|
57fd17ede0
|
makes it easier for clients to detect proxy errors programatically
|
2024-05-27 15:30:28 -05:00 |
|
|
nai-degen
|
9d00b8a9de
|
adjusts max IP error message wording
|
2024-05-27 08:24:56 -05:00 |
|
|
scrappyanon
|
2d82e55d72
|
Sqlite backend with user event logging (khanon/oai-reverse-proxy!69)
|
2024-05-26 17:31:12 +00:00 |
|
|
nai-degen
|
68b48428de
|
adjusts gatekeeper module to send auth errors as fake chat completions
|
2024-05-21 12:44:43 -05:00 |
|
|
nai-degen
|
6dabc82bcf
|
adds preliminary gpt4o
|
2024-05-13 12:43:39 -05:00 |
|
|
nai-degen
|
d3e7ef3c14
|
prevents leaking headers to upstream API when serving via Tailscale
|
2024-05-01 11:26:15 -05:00 |
|
|
nai-degen
|
32b623d6bc
|
partial googleai fixes; adds jsonl file backend for promptlogger stolen from fiz
|
2024-04-23 03:43:38 -05:00 |
|
|
nai-degen
|
c15f07c0d8
|
adds OpenAI-to-AWS Claude3 compat endpoint
|
2024-04-17 21:23:30 -05:00 |
|
|
nai-degen
|
db28e90c51
|
adds proper Opus model check to aws claude keychecker
|
2024-04-17 21:09:00 -05:00 |
|
|
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 |
|