nai-degen
|
86772ab32a
|
adds 503 as a 'successful' AWS keychecker response to deal with temporary outages
|
2024-09-11 02:42:59 -05:00 |
honeytree
|
bd87ca60f7
|
Implement priority queue by tokens (khanon/oai-reverse-proxy!79)
|
2024-09-09 16:48:46 +00:00 |
nai-degen
|
ac1897fd17
|
returns more clear proxy_note hint on AWS 503 error
|
2024-09-09 09:56:18 -05:00 |
nai-degen
|
2a6f85e2e2
|
Revert "handles AWS HTTP 503 ServiceUnavailableException similarly to 429s"
This reverts commit ffcaa23511 .
|
2024-09-09 09:43:59 -05:00 |
nai-degen
|
ffcaa23511
|
handles AWS HTTP 503 ServiceUnavailableException similarly to 429s
|
2024-09-09 08:07:53 -05:00 |
nai-degen
|
1d5b8efa23
|
reduces key lockout period to more quickly drain queue after AWS rate limit resolves
|
2024-09-08 17:17:22 -05:00 |
nai-degen
|
905273abf2
|
fixes aws mistral token cost estimation
|
2024-09-08 17:15:59 -05:00 |
nai-degen
|
ac92a19946
|
improves reliability of inference profile detection for AWS keychecker
|
2024-09-07 17:36:29 -05:00 |
khanon
|
96fe974ad0
|
Use AWS Inference Profiles for higher rate limits (khanon/oai-reverse-proxy!78)
|
2024-09-01 22:55:07 +00:00 |
nai-degen
|
578615fbd2
|
fixes typo in new Claude system prompt schema
|
2024-08-30 10:23:57 -05:00 |
nai-degen
|
5dc4050e52
|
disable periodic GCP key rechecks to workaround keychecker bug
|
2024-08-29 15:25:37 -05:00 |
nai-degen
|
cf615ee62c
|
applies prettier to GCP checker
|
2024-08-29 15:15:56 -05:00 |
nai-degen
|
ee61f9be2b
|
removes unnecessary log from last commit
|
2024-08-27 23:58:32 -05:00 |
nai-degen
|
0c448cb59d
|
fixes azure dalle using wrong rate limit and out-of-spec Retry-After header
|
2024-08-27 23:53:28 -05:00 |
nai-degen
|
51a9ccceb2
|
supports alternate claude system prompt format
|
2024-08-27 23:27:20 -05:00 |
nai-degen
|
ce490efd7d
|
minor adjustments to HMAC signing
|
2024-08-22 19:54:02 -05:00 |
nai-degen
|
5000e59a61
|
fix for google makersuite prompt validation/transformation
|
2024-08-22 14:19:48 -05:00 |
nai-degen
|
d54acad6ad
|
adds support for sonnet 8192 output tokens on anthropic api
|
2024-08-15 11:55:13 -05:00 |
nai-degen
|
5e1fffe07d
|
adds chatgpt-4o-latest
|
2024-08-15 11:54:42 -05:00 |
nai-degen
|
f7fd5f00f2
|
fixes
esponse_format schema for mistral la plateforme
|
2024-08-14 14:41:47 -05:00 |
nai-degen
|
6d323f6ea1
|
do not transform mistral chat prompts to text when using la plateforme
|
2024-08-14 12:26:27 -05:00 |
nai-degen
|
2959ed3f7f
|
fixes aws keychecker not detecting claude 2.1
|
2024-08-14 10:49:02 -05:00 |
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
|
6c45c92ea0
|
updates dependencies
|
2024-08-12 19:10:15 -05:00 |
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
|
ca58770458
|
fixes issue with PROXY_KEY when used together with proof-of-work captcha
|
2024-07-29 19:41:57 -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
|
584bb3fbc7
|
addresses minor issue with quota refresh UI
|
2024-07-28 11:54:38 -05:00 |
nai-degen
|
2aa19e5b09
|
adds user-specific overrides for daily quota refresh
|
2024-07-27 14:25:53 -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
|
e3d1ab51d1
|
improves handling of AWS regions with Sonnet 3.5 enabled but Sonnet 3.0 disabled
|
2024-06-20 12:20:38 -05:00 |
nai-degen
|
ff38eda066
|
improves model detection for AWS Sydney region
|
2024-06-20 12:19:44 -05:00 |
nai-degen
|
84b917f726
|
fixes AWS Sonnet 3.5 key assignment bug
|
2024-06-20 12:00:11 -05:00 |
nai-degen
|
5871025245
|
fixes AWS keychecker failure caused by Sonnet 3.5 gradual rollout
|
2024-06-20 11:24:47 -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
|
0ea43f61c2
|
fixes incorrect variable name in .env.example docs
|
2024-06-09 11:36:20 -05:00 |
nai-degen
|
ca4321b4cb
|
adjusts openai schema validation to allow
ull stop sequence
|
2024-06-07 14:29:18 -05:00 |
nai-degen
|
7660ed8b94
|
allows enabling vision prompts on a per-service basis
|
2024-06-07 12:09:43 -05:00 |