zack3d/OAI-Proxy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
737 Commits 20 Branches 0 Tags
21294abd8ead9aa403841db67fbc722a53f5d24c
Commit Graph

737 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
penurin 239f95e8a1 Merge branch 'patch-1' into 'main' 
Fix anthropic content schema

See merge request penurin/oai-reverse-proxy!1
 2025-02-12 13:18:21 +00:00
W92k6zuinOCClyWS 17475447a0 Fix anthropic content schema (penurin/oai-reverse-proxy!1) 2025-02-12 13:18:21 +00:00
user d2b37b8455 Fix Gemini key checking: old code didn't properly check for the error message. Swapped the check to use 2.0 Flash because it catches more 429 keys 2025-02-05 17:11:27 +00:00
user cec66cdc44 Newer Gemini 2.0 models in the list 2025-02-05 17:11:27 +00:00
user a5c9e95929 Add all o models to the OpenAI model list 2025-01-31 20:22:06 +00:00
user c5d4fe44e6 Fix for the timeout workaround for o1 2025-01-31 20:22:06 +00:00
user 8ed883eaff o3 mini 2025-01-31 20:22:06 +00:00
user 6de338c6ac Properly separate deepseek keys from the generic ones in service info 2025-01-25 11:06:38 +00:00
user 45576db441 [Deepseek] Properly handle over-quota keys 2025-01-25 11:59:41 +00:00
user bcc83f30d9 Properly count DS reasoning tokens and properly save them per-user 2025-01-25 11:06:38 +00:00
user e5a26215e1 Add native Gemini model list endpoint 2025-01-24 08:34:12 +00:00
user cd6cc76a46 Attempt to improve the o1 timeout hack 2025-01-22 15:23:17 +00:00
faggot 613bb789fb fix error checking o1 deployments 2025-01-22 09:59:11 +00:00
user f1c698388e [Gemini] Support the new thinking config for 2.0 Flash Thinking 2025-01-22 09:59:11 +00:00
user 75605a2bfb Add preliminary deepseek-reasoner support 2025-01-20 07:28:30 +00:00
user 58e67d40e2 Check logging for AWS keys (untested) 2025-01-20 11:28:53 +00:00
user 796b4eee47 Make the OpenAI checker properly clone orgs again, and fix the error with the liveness check 2025-01-06 06:55:41 +00:00
user 0f482e67d2 Fix OpenAI -> Google AI conversion 2025-01-05 14:02:17 +00:00
user 496ec09905 Add v1alpha support (needed for 2.0 flash thinking with the new 'thought' parameter), already used by ST 2025-01-04 19:11:02 +00:00
user f522dba6a3 Fix errors with o1-preview and o1-mini 2025-01-03 04:41:29 +00:00
user 25ba8447d9 And add display names as well 2025-01-03 04:41:29 +00:00
user 91b8c01a9d Do the same for the AWS endpoint 2025-01-03 04:41:29 +00:00
user 82b88764ba Fix Anthropic model list to be actually compatible with Anthropic API (required by some frontends), remove old models 2025-01-03 04:50:55 +00:00
user 6ea9235ff8 Actually camelCase is canon for Gemini, oops 2024-12-31 08:23:45 +00:00
user 372ad85283 Support camelCase Gemini params and validate vision 2024-12-31 10:16:04 +00:00
user c2f5d2fbf3 Add /v1/models to deepseek 2024-12-31 08:23:45 +00:00
user c264413495 Leave a comment about concurrency for "special" user tokens 2024-12-31 08:23:45 +00:00
user 8d27082ad0 Fix formatting changes with upstream 2024-12-31 08:23:45 +00:00
user e2b602fd52 Adjust chunked transfer to send 4KB (CF's buffer size) of data every 49 seconds 2024-12-31 08:23:45 +00:00
user b00fb88cab Don't overwrite the reasoning effort by default 2024-12-31 07:45:11 +00:00
user 1cc281f6fe Add automatic prefill for Deepseek - works the same way as with Claude 2024-12-31 07:45:11 +00:00
user 8f4d00ed26 Init commit, some things: 
- 'Transfer-Encoding: chunked' for o1 requests to prevent CF's 100 second limit
- Better tool/function call support
- Deepseek support
- Handling system as an array for AWS Claude
- Image support for Gemini
- Better o1 support (reasoning effort, developer role, context size)
 2024-12-31 00:00:00 +00:00
nai-degen 36e2430a8f adjusts gemini keychecker to trigger real generation for better rate limit detection 2024-12-07 01:31:10 -06:00
nai-degen 28447d0811 resolves server-side error when a Gemini prompt is blocked due to safety 2024-12-07 00:54:13 -06:00
nai-degen 6d54cbc785 maybe handles gemini daily key block idk 2024-12-05 15:06:29 -06:00
nai-degen 9d7a4f4b51 maybe fixes gemini's fucked error messages idk 2024-12-05 14:54:35 -06:00
nai-degen 3496a2a9bd fixes incorrect 3.5 sonnet v2 model id in gcp model reassignment 2024-12-03 19:53:56 -06:00
nai-degen 5072638ec2 attempt at fixing persistent 'invalid csrf token' error on some browsers 2024-12-03 19:49:47 -06:00
Nopm 8a325a1e0b Add 2 million Google AI context (khanon/oai-reverse-proxy!82) 2024-12-04 01:27:21 +00:00
khanon 5eeb2875b4 adds haiku 3.5 2024-11-04 18:20:19 +00:00
khanon c67dad1617 fixes AWS claude v2 2024-10-25 18:10:26 +00:00
khanon fe61745e24 fixes issue with AWS model assignment when requesting legacy claude (claude-2.1, etc) 2024-10-25 17:49:24 +00:00
nai-degen 251ea6d412 fixes typo in AWS ThrottlingException 2024-10-23 15:36:21 -05:00
nai-degen 55f7337ea4 adjusts AWS keychecker to treat rate limited models as available models 2024-10-23 15:35:32 -05:00
nai-degen f3b876887e fixes issue with AWS model name reassignment 2024-10-23 13:59:10 -05:00
nai-degen 49c578f4dc adds Sonnet 3.5v2 AWS model ID and adjusts AWS model assignment to raise error on no match 2024-10-23 13:39:34 -05:00
khanon 4190d5fef6 fixes missing comma....... 2024-10-22 16:06:39 +00:00
khanon 1644e82f25 adds Sonnet 20241022 snapshot IDs 2024-10-22 15:52:52 +00:00
nai-degen 0bbdc0b841 fixes google ai language filter and updates readme 2024-10-18 23:15:02 -05:00
nai-degen c4a633a5d6 fixes gcp oauth2 token refresh not updating cloned key instance 2024-10-18 22:41:24 -05:00