Commit Graph
17290 Commits
Author SHA1 Message Date
Ishaan Jaff 3c898e23ea refactor secret managers 2024-09-03 10:58:02 -07:00
Ishaan Jaff 150f3c2cfa read from .env for secret manager 2024-09-03 10:53:52 -07:00
Ishaan Jaff b0178a85cf refactor get_secret 2024-09-03 10:42:12 -07:00
Ishaan Jaff 1546a82f18 add sync_construct_request_headers 2024-09-03 10:36:10 -07:00
Krrish Dholakia 36ce43ed95 refactor: ci/cd run again v1.44.15 v1.44.15-stable 2024-09-03 07:17:02 -07:00
Krrish Dholakia eadcc09f44 docs(enterprise.md): clarify how enterprise deployments work 2024-09-03 06:55:14 -07:00
Krrish Dholakia 2d47acad6c test: fix test 2024-09-03 06:40:52 -07:00
Krrish Dholakia 9df0588c2c docs(json_mode.md): update docs 2024-09-02 22:41:17 -07:00
Krish DholakiaandGitHub 6ccff1b13e fix(router.py): fix inherited type (#5485) 2024-09-02 22:03:21 -07:00
Krish DholakiaandGitHub 9f3fa29624 feat(router.py): Support Loadbalancing batch azure api endpoints (#5469)
* feat(router.py): initial commit for loadbalancing azure batch api endpoints

Closes https://github.com/BerriAI/litellm/issues/5396

* fix(router.py): working `router.acreate_file()`

* feat(router.py): working router.acreate_batch endpoint

* feat(router.py): expose router.aretrieve_batch function

Make it easy for user to retrieve the batch information

* feat(router.py): support 'router.alist_batches' endpoint

Adds support for getting all batches across all endpoints

* feat(router.py): working loadbalancing on `/v1/files`

* feat(proxy_server.py): working loadbalancing on `/v1/batches`

* feat(proxy_server.py): working loadbalancing on Retrieve + List batch
2024-09-02 21:32:55 -07:00
Ishaan Jaff 7a22faaba4 bump: version 1.44.14 → 1.44.15 2024-09-02 21:27:23 -07:00
Ishaan JaffandGitHub 38bb8439b0 Merge pull request #5482 from BerriAI/litellm_track_embedding_spendLogs
[Feat] track embedding /predict in spend logs
2024-09-02 21:23:24 -07:00
Ishaan JaffandGitHub 5100b31292 Merge branch 'main' into litellm_track_embedding_spendLogs 2024-09-02 21:23:18 -07:00
Ishaan JaffandGitHub 7aaabb51ef Merge pull request #5481 from BerriAI/litellm_track_imagen_spend_logs
[Feat-Proxy] track imagen /predict in LiteLLM spend logs
2024-09-02 21:21:21 -07:00
Ishaan JaffandGitHub c1adb0b7f2 Merge branch 'main' into litellm_track_imagen_spend_logs 2024-09-02 21:21:15 -07:00
Ishaan Jaff 0b51712aab mark test as flaky 2024-09-02 19:44:28 -07:00
Ishaan Jaff 35c0c07b24 fix success handler typing 2024-09-02 19:42:36 -07:00
Ishaan Jaff bfb39eb0cd fix linting errors 2024-09-02 19:39:10 -07:00
Ishaan Jaff e09db615aa fix linting 2024-09-02 19:29:32 -07:00
Ishaan JaffandGitHub a64f9f4bc0 Merge pull request #5480 from BerriAI/litellm_track_streaming_spendLogs
[Feat] Track Usage for `/streamGenerateContent` endpoint
2024-09-02 19:25:52 -07:00
Ishaan Jaff b0735c9e9f add doc with support imagen models 2024-09-02 18:17:12 -07:00
Ishaan Jaff ad10dcd3c3 fix linting error 2024-09-02 18:14:15 -07:00
Ishaan Jaff 8ede32f91d fix linting error 2024-09-02 18:13:59 -07:00
Ishaan Jaff fa6b09f147 fix linting error 2024-09-02 18:13:32 -07:00
Ishaan Jaff 4a0fdc40f1 add cost tracking for pass through imagen 2024-09-02 18:10:46 -07:00
Ishaan Jaff 9fcab392a4 fix get llm provider for imagen 2024-09-02 17:49:36 -07:00
Ishaan Jaff 80dd2cfc7f fix get_llm_provider for imagegeneration@006 2024-09-02 17:47:29 -07:00
Ishaan Jaff 811aa34a36 track image gen in spend logs 2024-09-02 17:36:25 -07:00
Ishaan Jaff aa13977136 refactor vtx image gen 2024-09-02 17:35:51 -07:00
Ishaan Jaff 6393d2391e refactor vertex to use spearate image gen folder 2024-09-02 17:34:43 -07:00
Ishaan Jaff 296dba8923 fix lining 2024-09-02 17:08:30 -07:00
Ishaan Jaff f89487a496 fix linting error 2024-09-02 17:08:03 -07:00
Ishaan Jaff eb9e4f1787 track /embedding in spendLogs 2024-09-02 17:05:53 -07:00
Ishaan Jaff 42b95c5979 code cleanup 2024-09-02 16:36:19 -07:00
Ishaan JaffandGitHub 666dd6aca2 Merge pull request #5478 from BerriAI/litellm_Add_ai21
[Feat] Add AI21 /chat API
2024-09-02 16:20:37 -07:00
Ishaan Jaff e9427205ef add test for pass through streaming usage tracking 2024-09-02 16:17:49 -07:00
Ishaan Jaff a6d4a27207 pass through track usage for streaming endpoints 2024-09-02 16:11:20 -07:00
Ishaan Jaff 73d0a78444 use chunk_processort 2024-09-02 15:51:52 -07:00
Ishaan Jaff fdecafd347 new streaming handler fn 2024-09-02 15:51:21 -07:00
Krish DholakiaandGitHub f9e6507cd1 LiteLLM Minor Fixes + Improvements (#5474)
* feat(proxy/_types.py): add lago billing to callbacks ui

Closes https://github.com/BerriAI/litellm/issues/5472

* fix(anthropic.py): return anthropic prompt caching information

Fixes https://github.com/BerriAI/litellm/issues/5364

* feat(bedrock/chat.py): support 'json_schema' for bedrock models

Closes https://github.com/BerriAI/litellm/issues/5434

* fix(bedrock/embed/embeddings.py): support async embeddings for amazon titan models

* fix: linting fixes

* fix: handle key errors

* fix(bedrock/chat.py): fix bedrock ai21 streaming object

* feat(bedrock/embed): support bedrock embedding optional params

* fix(databricks.py): fix usage chunk

* fix(internal_user_endpoints.py): apply internal user defaults, if user role updated

Fixes issue where user update wouldn't apply defaults

* feat(slack_alerting.py): provide multiple slack channels for a given alert type

multiple channels might be interested in receiving an alert for a given type

* docs(alerting.md): add multiple channel alerting to docs
2024-09-02 14:29:57 -07:00
02f288a8a3 Azure Service Principal with Secret authentication workflow. (#5131) (#5437)
* Azure Service Principal with Secret authentication workflow. (#5131)

* Implement Azure Service Principal with Secret authentication workflow.

* Use `ClientSecretCredential` instead of `DefaultAzureCredential`.

* Move imports into the function.

* Add type hint for `azure_ad_token_provider`.

* Add unit test for router initialization and sample completion using Azure Service Principal with Secret authentication workflow.

* Add unit test for router initialization with neither API key nor using Azure Service Principal with Secret authentication workflow.

* fix(client_initializtion_utils.py): fix typing + overrides

* test: fix linting errors

* fix(client_initialization_utils.py): fix client init azure ad token logic

* fix(router_client_initialization.py): add flag check for reading azure ad token from environment

* test(test_streaming.py): skip end of life bedrock model

* test(test_router_client_init.py): add correct flag to test

---------

Co-authored-by: kzych-inpost <142029278+kzych-inpost@users.noreply.github.com>
2024-09-02 14:29:00 -07:00
Krrish Dholakia 2797b30a50 build(model_prices_and_context_window.json): fix token information 2024-09-02 13:14:11 -07:00
Kyrylo YefimenkoandGitHub 1a0d8e7260 Add pricing for ft:gpt-3.5-turbo-* (#5471) 2024-09-02 13:12:57 -07:00
Ishaan Jaff c8fc453b75 fix pass through construct_target_url when vertex_proj is None 2024-09-02 12:51:30 -07:00
Ishaan Jaff d4f77832c0 docs add docs on supported params 2024-09-02 12:39:07 -07:00
Ishaan Jaff f28e94827c docs update ai21 doc 2024-09-02 12:26:53 -07:00
Ishaan Jaff 93650db380 fix linting 2024-09-02 12:15:14 -07:00
Ishaan Jaff 263e283126 add ai21 model test 2024-09-02 12:14:13 -07:00
Ishaan Jaff ae25c5695f add streaming test for ai21 2024-09-02 11:58:15 -07:00
Ishaan Jaff 0874885f04 add all ai21 params 2024-09-02 11:54:40 -07:00