frob
|
82a4232dce
|
ollama also accepts PNG
|
2024-04-08 03:35:02 +02:00 |
|
frob
|
59ed4fb51e
|
Update ollama.py for image handling
ollama wants plain base64 jpeg images, and some clients send dataURI and/or webp. Remove prefixes and convert all non-jpeg images to jpeg.
|
2024-04-08 03:28:24 +02:00 |
|
frob
|
d5c1ae1cb2
|
Update ollama.py for image handling
Some clients (eg librechat) send images in datauri format, not plain base64. Strip off the prerix when passing images to ollama.
|
2024-04-07 13:05:39 +02:00 |
|
Ishaan Jaff
|
3b6b497672
|
Merge pull request #2882 from BerriAI/litellm_docs_fix
docs fix gpt-3.5-turbo-instruct-0914
|
2024-04-06 20:26:24 -07:00 |
|
Krrish Dholakia
|
c60140a09a
|
bump: version 1.34.32 → 1.34.33
|
2024-04-06 19:44:29 -07:00 |
|
Krrish Dholakia
|
8a8b207fc9
|
refactor(main.py): trigger new build
|
2024-04-06 19:42:54 -07:00 |
|
Krrish Dholakia
|
6773341a08
|
test(test_alerting.py): remove duplicate test
|
2024-04-06 19:33:01 -07:00 |
|
Ishaan Jaff
|
3833c4083c
|
(ci/cd) fix queueing github releases
|
2024-04-06 19:21:58 -07:00 |
|
Krish Dholakia
|
83f608dc5d
|
Merge pull request #2880 from BerriAI/litellm_api_base_alerting
feat(proxy/utils.py): return api base for request hanging alerts
|
2024-04-06 19:17:18 -07:00 |
|
Krrish Dholakia
|
d65efcce99
|
refactor(main.py): trigger new build
|
2024-04-06 18:50:38 -07:00 |
|
Krrish Dholakia
|
6234982fd9
|
test(test_custom_callback_input.py): fix assert
|
2024-04-06 18:48:33 -07:00 |
|
Krrish Dholakia
|
5f910c1811
|
test(test_streaming.py): fix vertex project name
|
2024-04-06 18:45:17 -07:00 |
|
Krrish Dholakia
|
460546956d
|
fix(utils.py): fix import
|
2024-04-06 18:37:38 -07:00 |
|
Krrish Dholakia
|
a410981972
|
fix(utils.py): fix circular import
|
2024-04-06 18:29:51 -07:00 |
|
Krrish Dholakia
|
6f94f3d127
|
fix(router.py): improve pre-call check -> get model group cache one-time
|
2024-04-06 18:24:51 -07:00 |
|
Ishaan Jaff
|
4512510d37
|
Revert "fix test streaming"
This reverts commit f10aba1007.
|
2024-04-06 18:24:00 -07:00 |
|
Ishaan Jaff
|
f10aba1007
|
fix test streaming
|
2024-04-06 18:23:10 -07:00 |
|
Ishaan Jaff
|
187774ef5c
|
bump: version 1.34.31 → 1.34.32
|
2024-04-06 18:20:23 -07:00 |
|
Krrish Dholakia
|
7ae6432f94
|
fix(router.py): check usage based routing cache in pre-call check
allows pre-call rpm check to work across instances
|
2024-04-06 18:19:02 -07:00 |
|
Krrish Dholakia
|
a6f987e065
|
test(test_amazing_vertex_completion.py): fix project name
|
2024-04-06 17:59:49 -07:00 |
|
Krrish Dholakia
|
205ac1496a
|
fix(router.py): store in-memory deployment request count for 60s only
|
2024-04-06 17:53:39 -07:00 |
|
Krrish Dholakia
|
0d1cca9aa0
|
fix(router.py): make router async calls coroutine safe
uses pre-call checks to check if a call is below it's rpm limit, works even if multiple async calls are
made simultaneously
|
2024-04-06 17:31:26 -07:00 |
|
Krish Dholakia
|
a101591f74
|
Update README.md
|
2024-04-06 16:11:33 -07:00 |
|
Krrish Dholakia
|
ead59b7b38
|
fix(utils.py): add gemini api base support to 'get_api_base'
|
2024-04-06 16:08:15 -07:00 |
|
Krrish Dholakia
|
6110d32b1c
|
feat(proxy/utils.py): return api base for request hanging alerts
|
2024-04-06 15:58:53 -07:00 |
|
Ishaan Jaff
|
f09e6ba98d
|
Merge pull request #2878 from BerriAI/litellm_azure_gpt_instruct
re-use Azure OpenAI client for azure text completions
|
2024-04-06 13:35:39 -07:00 |
|
Ishaan Jaff
|
a6bc673ffa
|
feat - re-use OpenAI client for azure text
|
2024-04-06 12:23:58 -07:00 |
|
Ishaan Jaff
|
a2c63075ef
|
Merge pull request #2877 from BerriAI/litellm_fix_text_completion
[Feat] Text-Completion-OpenAI - Re-use OpenAI Client
|
2024-04-06 12:15:52 -07:00 |
|
Krrish Dholakia
|
b49e47b634
|
ci(vertex_key.json): switch gcloud accounts
|
2024-04-06 12:14:46 -07:00 |
|
Ishaan Jaff
|
c2f978fd5a
|
(docs) use text completion with litellm proxy
|
2024-04-06 12:07:20 -07:00 |
|
Ishaan Jaff
|
3b622556be
|
test - setting org for openai text completion
|
2024-04-06 11:53:26 -07:00 |
|
Ishaan Jaff
|
a55f3cdace
|
test - router re-use openai client
|
2024-04-06 11:33:17 -07:00 |
|
Ishaan Jaff
|
01fef1a9f8
|
feat - re-use openai client for text completion
|
2024-04-06 11:28:25 -07:00 |
|
Ishaan Jaff
|
ad7302cdc8
|
feat - re-use openai client for text completion
|
2024-04-06 11:25:33 -07:00 |
|
Krish Dholakia
|
5c2af90ac0
|
Merge pull request #2844 from nicovank/main
[integrations/langfuse] Use packaging over deprecated pkg_resources
|
2024-04-06 10:58:07 -07:00 |
|
Krrish Dholakia
|
e424a294a5
|
build(model_prices_and_context_window.json): add pricing for bedrock mistral paris region
|
2024-04-06 09:23:09 -07:00 |
|
Ishaan Jaff
|
2cc364743c
|
docs fix gpt-3.5-turbo-instruct-0914
|
2024-04-06 09:12:01 -07:00 |
|
Krrish Dholakia
|
90e03399fa
|
bump: version 1.34.30 → 1.34.31
|
2024-04-06 09:07:11 -07:00 |
|
Krrish Dholakia
|
6f1377481e
|
bump: version 1.34.29 → 1.34.30
|
2024-04-06 09:07:06 -07:00 |
|
Krrish Dholakia
|
ef9e29d575
|
refactor(main.py): trigger new build
|
2024-04-06 09:06:53 -07:00 |
|
Krrish Dholakia
|
7b30e5ae38
|
fix(utils.py): fix content check in pre-call rules
|
2024-04-06 09:03:19 -07:00 |
|
Krish Dholakia
|
9119858f4a
|
Merge pull request #2798 from CLARKBENHAM/main
add test for rate limits - Router isn't coroutine safe
|
2024-04-06 08:47:40 -07:00 |
|
Krish Dholakia
|
7495222a8b
|
Merge pull request #2855 from Caixiaopig/fix_update_default_claude3_maxtokens
Updating the default Anthropic Officlal Claude 3 max_tokens to 4096
|
2024-04-06 08:39:55 -07:00 |
|
Krrish Dholakia
|
afa2e2eba9
|
docs(anthropic.md): update anthropic docs to show 'tool' param usage
|
2024-04-06 08:35:43 -07:00 |
|
Krrish Dholakia
|
30f57e7aa5
|
fix(utils.py): move info statement to debug
|
2024-04-05 22:06:46 -07:00 |
|
Krrish Dholakia
|
dce96478c7
|
docs(vertex.md): add claude 3 on vertex ai to docs
|
2024-04-05 21:48:42 -07:00 |
|
Ishaan Jaff
|
3d298fc549
|
(test) completion
|
2024-04-05 21:03:04 -07:00 |
|
Ishaan Jaff
|
83580dc00a
|
(ci/cd) run again
|
2024-04-05 20:44:51 -07:00 |
|
Ishaan Jaff
|
122dff007b
|
fix gemini test
|
2024-04-05 20:38:28 -07:00 |
|
Krish Dholakia
|
1790869739
|
Merge pull request #2870 from BerriAI/litellm_ui_fixes
feat(prisma.schema): UI improvements for tracking spend for users
|
2024-04-05 18:42:41 -07:00 |
|