Commit Graph
11302 Commits
Author SHA1 Message Date
Paul Gauthier 9162f9c2c5 Added costs & context json 2024-05-07 11:44:55 -07:00
Paul Gauthier 90eb0ea022 Added support for the deepseek api 2024-05-07 11:44:03 -07:00
Krish DholakiaandGitHub 93e5fb49d3 Merge pull request #3500 from ghaemisr/main
Added support for JWT auth with PEM cert public keys
2024-05-07 11:07:30 -07:00
phact 7c5c9a8152 looks like cohere does support function calling 2024-05-07 13:41:05 -04:00
Sara Ghaemi 86e0dd68c3 updated tests 2024-05-07 13:28:57 -04:00
phact 1b811cd152 unit test and list fix 2024-05-07 13:24:28 -04:00
Sara Ghaemi 7017899d37 updated tests to also check for audience if found 2024-05-07 12:10:47 -04:00
Ishaan JaffandGitHub cf638d54c4 Merge pull request #3494 from Manouchehri/devcontainer-1
Add devcontainer
2024-05-07 08:57:37 -07:00
Ishaan JaffandGitHub ee1b1fe4f8 Merge pull request #3464 from sepiatone/main
update langchain documentation to reflect refactor
2024-05-07 08:42:23 -07:00
Ishaan JaffandGitHub 8b15507add Merge pull request #3471 from paneru-rajan/Issue-3466-update-doc
Synced the doc with the Mistral
2024-05-07 08:41:18 -07:00
Sara Ghaemi 66b2b5fab9 made audience optional and updated docs 2024-05-07 11:37:04 -04:00
Sara GhaemiandGitHub 0ca5af8ae8 Merge branch 'BerriAI:main' into main 2024-05-07 11:23:00 -04:00
Sara Ghaemi 1580f993fe Updated JWT handler to support PEM public key 2024-05-07 11:22:17 -04:00
Ishaan Jaff e91f0382d7 feat - update gemini-1.5-pro pricing 2024-05-07 07:56:52 -07:00
nkvch 06d1aec49e * fix(factory.py): fix conditional statement for merging messages with previous ones 2024-05-07 13:42:42 +02:00
David Manouchehri a9cae01cf5 Add devcontainer. 2024-05-07 11:33:04 +00:00
sepiatone 1518a7b42d update langchain documentation to reflect refactor 2024-05-07 17:01:55 +05:30
nkvch 389530efb4 * chore(.gitignore): add 'venv' to the list of ignored files/directories
* fix(test_completion.py): fix import order and remove unused imports
* feat(test_completion.py): add test for empty assistant message in completion_claude_3_empty_message()
2024-05-07 12:51:30 +02:00
nkvch 7d7b59ff78 * feat(factory.py): add support for merging consecutive messages of one role when separated with empty message of another role 2024-05-07 12:51:30 +02:00
Krish DholakiaandGitHub 30003afbf8 Merge pull request #3459 from alexanderepstein/langfuse_improvements
Update support for langfuse metadata
2024-05-06 21:56:29 -07:00
Ishaan Jaff bfef424b39 fix don't let slack alert block /model/new v1.36.1 2024-05-06 20:47:29 -07:00
Ishaan Jaff eb84c69ec6 fix - /model/new 2024-05-06 20:45:17 -07:00
Mehmet Bektas 8e9a4fa9eb comment out test method calls, following the pattern 2024-05-06 20:13:11 -07:00
Mehmet Bektas 157d7a7c28 add ollama embeddings unit tests 2024-05-06 20:11:45 -07:00
Krish DholakiaandGitHub 57b3eaf136 Merge pull request #3491 from BerriAI/litellm_slack_daily_reports
feat(slack_alerting.py): support sending daily reports on deployments
2024-05-06 19:31:56 -07:00
Krish DholakiaandGitHub aa62d891a0 Merge branch 'main' into litellm_slack_daily_reports 2024-05-06 19:31:20 -07:00
Krrish Dholakia 69bcde6f6b test(test_router_fallbacks.py): fix test - making it easier to debug 2024-05-06 18:49:36 -07:00
Krrish Dholakia 26c0ed0f2d refactor(proxy_server.py): show ttl's on a top-level enum
Addresses - https://github.com/BerriAI/litellm/issues/2649#issuecomment-2097203372
2024-05-06 18:43:42 -07:00
Krrish Dholakia 72299a6894 fix(slack_alerting.py): allow internal cache to be an optional param 2024-05-06 18:34:09 -07:00
Krrish Dholakia 3a8876b0d5 refactor(slack_alerting.py): trigger new build 2024-05-06 18:29:55 -07:00
Krrish Dholakia 6b9b4f05ba feat(proxy_server.py): schedule slack daily report if enabled
if user enabled daily_reports, send them a slack report every 12 hours
2024-05-06 18:25:48 -07:00
Ishaan Jaff d94065ca43 fix - num active callbacks 2024-05-06 18:20:27 -07:00
Ishaan JaffandGitHub dd14714b94 Merge pull request #3487 from BerriAI/dependabot/pip/jinja2-3.1.4
build(deps): bump jinja2 from 3.1.3 to 3.1.4
2024-05-06 18:15:50 -07:00
Ishaan Jaff 15b264bd4e fix num callbacks test 2024-05-06 18:13:15 -07:00
Ishaan Jaff 5368382c03 fix num callbacks test 2024-05-06 18:12:45 -07:00
Ishaan Jaff 22347f2f56 bump: version 1.36.0 → 1.36.1 2024-05-06 18:08:40 -07:00
Ishaan Jaff a382517992 fix - test alerting 2024-05-06 18:07:58 -07:00
Ishaan Jaff 791ec2e26a ui - new build 2024-05-06 18:06:25 -07:00
Ishaan JaffandGitHub 0012463a9b Merge pull request #3489 from BerriAI/litellm_send_slack_alerts_model_new
Feat - send slack alerts on `model/new`
2024-05-06 18:01:08 -07:00
Ishaan JaffandGitHub 7c789fe0af Merge pull request #3492 from BerriAI/litellm_fixes_retry_policy
[UI] Fixes for getting/setting Retry Policy by Model Group
2024-05-06 18:00:21 -07:00
Ishaan Jaff 6a056c0c17 fix support InternalServerErrorRetries 2024-05-06 17:59:38 -07:00
Ishaan Jaff f04f45a80d ui - fix show num retries for 500 error 2024-05-06 17:58:56 -07:00
Ishaan Jaff eb5dc38fc9 fix - set retry policy on ui 2024-05-06 17:57:07 -07:00
Ishaan Jaff 4fdf1147d3 ui - get/set model retry policy 2024-05-06 17:44:55 -07:00
Ishaan Jaff 116e555a03 fix - setting model_group_retry_policy in db 2024-05-06 17:43:43 -07:00
Ishaan Jaff 57a7870348 ui - show retry policy per model group 2024-05-06 17:23:51 -07:00
Krrish Dholakia 718f423d7d feat(slack_alerting.py): support sending daily reports on deployments
allow admin to easily know slow + failing deployments

Closes  https://github.com/BerriAI/litellm/issues/3483
2024-05-06 17:18:42 -07:00
Ishaan Jaff 040dc1f23e fix retry policy 2024-05-06 16:43:42 -07:00
Ishaan Jaff 1de50d62f7 fix test router debug logs 2024-05-06 16:38:16 -07:00
Ishaan JaffandGitHub 1725b7a9e1 Merge pull request #3461 from BerriAI/litellm_set_router_retry_policy_ui
[UI] Set Router Retry Policy
2024-05-06 16:36:09 -07:00