Commit graph

17527 commits

Author SHA1 Message Date
Krrish Dholakia
0a016d33e6 Revert "fix(router.py): return model alias w/ underlying deployment on router.get_model_list()"
This reverts commit 638896309c.
2024-09-07 18:04:56 -07:00
Krrish Dholakia
638896309c fix(router.py): return model alias w/ underlying deployment on router.get_model_list()
Fixes https://github.com/BerriAI/litellm/issues/5524#issuecomment-2336410666
2024-09-07 18:01:31 -07:00
Krrish Dholakia
8294e8793c docs(deploy.md): add published non-root docker image to docs 2024-09-07 18:01:31 -07:00
Ishaan Jaff
ba41a72f92 High Level architecture 2024-09-07 16:29:22 -07:00
Ishaan Jaff
c574c729cd ui new build 2024-09-07 16:24:06 -07:00
Ishaan Jaff
9eb59e3645
Merge pull request #5585 from BerriAI/litellm_docs_arch_diagram
[Docs] - Add Lifecycle of a request through LiteLLM Gateway
2024-09-07 16:22:02 -07:00
Ishaan Jaff
c2c63e4dbe docs add arch diagram 2024-09-07 16:21:29 -07:00
Ishaan Jaff
54db564529 add arch diagram 2024-09-07 15:49:51 -07:00
Ishaan Jaff
e88482e6cf
Merge pull request #5582 from BerriAI/litellm_ui
[Feat UI] allow setting input / output cost per M tokens
2024-09-07 12:32:42 -07:00
Ishaan Jaff
64e830ac21
Merge pull request #5581 from BerriAI/litellm_allow_setting_spend_report_frequency
[Feat] Slack Alerting - Allow setting custom spend report frequency
2024-09-07 12:32:18 -07:00
Ishaan Jaff
57d3d59aaf ui allow setting input / output cost per M tokens 2024-09-07 12:07:14 -07:00
Ishaan Jaff
ecb774c3e8 add doc on spend report frequency 2024-09-07 11:54:33 -07:00
Ishaan Jaff
805e4c5754 add spend_report_frequency as a general setting 2024-09-07 11:44:58 -07:00
Ishaan Jaff
1b732c485d fix slack alerting allow setting custom spend report frequency 2024-09-07 11:42:16 -07:00
Ishaan Jaff
009a1f7f86
Merge pull request #5579 from BerriAI/litellm_set_redis_cluster_env
[Feat] Allow setting up Redis Cluster using .env vars
2024-09-07 11:31:38 -07:00
Ishaan Jaff
05505903b2 docs better sidebar 2024-09-07 11:31:07 -07:00
Ishaan Jaff
3984b9080c docs cleanup 2024-09-07 11:23:44 -07:00
Ishaan Jaff
2cf0714b0d docs organize sidebar 2024-09-07 11:23:06 -07:00
Ishaan Jaff
808ba36b55 ui cleanup 2024-09-07 11:20:07 -07:00
Ishaan Jaff
66eba43f29 mark test_langfuse_masked_input_output 2024-09-07 11:15:29 -07:00
Ishaan Jaff
3bf2c06e06 add config for setting up redis cluster 2024-09-07 09:37:23 -07:00
Ishaan Jaff
9a9c0e42eb allow setting password for redis cluster 2024-09-07 09:25:13 -07:00
Ishaan Jaff
eaab0e761d add test_redis_cache_cluster_init_with_env_vars_unit_test 2024-09-07 08:56:00 -07:00
Ishaan Jaff
5c4f3a9a34 fix allow using .env vars for redis cluster 2024-09-07 08:54:40 -07:00
Peter Laß
72ea6f2ea8
litellm-helm: fix missing resource definitions in initContainer and missing DBname value for envVars in deployment.yaml (#5562)
* fix missing resource definitions in initContainer and missing DBname value in envVars in deployment.yaml

* fix missing resource definitions in initContainer and missing DBname value in envVars in deployment.yaml

---------

Co-authored-by: Peter Laß <peter.lass@maibornwolff.de>
2024-09-07 08:23:05 -07:00
Pradyumna Singh Rathore
a4f5fb3c30
fix missing class object instantiation in custom_llm_server provider documentation's quick start (#5578)
Co-authored-by: Pradyumna Singh Rathore <pradyumna.singhrathore@halliburton.com>
2024-09-07 08:22:18 -07:00
Ishaan Jaff
9225d31776 allow setting REDIS_CLUSTER_NODES in .env 2024-09-07 07:41:49 -07:00
Krish Dholakia
4371aa1995
fix(langsmith.py): support sampling langsmith traces (#5577) 2024-09-06 22:14:44 -07:00
Krish Dholakia
32d0277f03
Allow client-side credentials to be sent to proxy (accept only if complete credentials are given) (#5575)
* feat: initial commit

* fix(proxy/auth/auth_utils.py): Allow client-side credentials to be given to the proxy (accept only if complete credentials are given)
2024-09-06 19:21:54 -07:00
Ishaan Jaff
a1f0169fc1 bump: version 1.44.20 → 1.44.21 2024-09-06 18:15:00 -07:00
Ishaan Jaff
afffd1f461 bump: version 1.44.19 → 1.44.20 2024-09-06 18:14:47 -07:00
Ishaan Jaff
64a828b455
Merge pull request #5573 from BerriAI/litellm_add_rerank_spend_tracking
[Feat] Add cost tracking for cohere rerank
2024-09-06 18:11:30 -07:00
Ishaan Jaff
516a6b63e1 ui new build 2024-09-06 18:10:46 -07:00
Ishaan Jaff
ff9aafe05d
Merge pull request #5566 from BerriAI/litellm_ui_regen_keys
[Feat] Allow setting duration time when regenerating key
2024-09-06 18:05:51 -07:00
Ishaan Jaff
09a4568172
Merge pull request #5574 from BerriAI/litellm_tags_use_views
[Feat-Proxy] Use DB Views to Get spend per Tag (Usage endpoints)
2024-09-06 17:33:06 -07:00
Krish Dholakia
72e961af3c
LiteLLM Minor Fixes and Improvements (08/06/2024) (#5567)
* fix(utils.py): return citations for perplexity streaming

Fixes https://github.com/BerriAI/litellm/issues/5535

* fix(anthropic/chat.py): support fallbacks for anthropic streaming (#5542)

* fix(anthropic/chat.py): support fallbacks for anthropic streaming

Fixes https://github.com/BerriAI/litellm/issues/5512

* fix(anthropic/chat.py): use module level http client if none given (prevents early client closure)

* fix: fix linting errors

* fix(http_handler.py): fix raise_for_status error handling

* test: retry flaky test

* fix otel type

* fix(bedrock/embed): fix error raising

* test(test_openai_batches_and_files.py): skip azure batches test (for now) quota exceeded

* fix(test_router.py): skip azure batch route test (for now) - hit batch quota limits

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>

* All `model_group_alias` should show up in `/models`, `/model/info` , `/model_group/info` (#5539)

* fix(router.py): support returning model_alias model names in `/v1/models`

* fix(proxy_server.py): support returning model alias'es on `/model/info`

* feat(router.py): support returning model group alias for `/model_group/info`

* fix(proxy_server.py): fix linting errors

* fix(proxy_server.py): fix linting errors

* build(model_prices_and_context_window.json): add amazon titan text premier pricing information

Closes https://github.com/BerriAI/litellm/issues/5560

* feat(litellm_logging.py): log standard logging response object for pass through endpoints. Allows bedrock /invoke agent calls to be correctly logged to langfuse + s3

* fix(success_handler.py): fix linting error

* fix(success_handler.py): fix linting errors

* fix(team_endpoints.py): Allows admin to update team member budgets

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
2024-09-06 17:16:24 -07:00
Krish Dholakia
e4dcd6f745
fix(navbar.tsx): only show 'get enterprise license' if user is not already a premium user (#5568) 2024-09-06 17:14:30 -07:00
Ishaan Jaff
b345db5011 fix ui type 2024-09-06 17:04:03 -07:00
Ishaan Jaff
7f461dbf68 fix linting 2024-09-06 16:54:43 -07:00
Ishaan Jaff
c5aa422847 Merge branch 'main' into litellm_ui_regen_keys 2024-09-06 16:48:18 -07:00
Ishaan Jaff
d5914cf958 Merge branch 'main' into litellm_tags_use_views 2024-09-06 16:46:23 -07:00
Ishaan Jaff
292e87f572 Merge branch 'main' into litellm_add_rerank_spend_tracking 2024-09-06 16:46:07 -07:00
Ishaan Jaff
e0ac27c00c fix azure batches test - don't have more quota 2024-09-06 16:44:16 -07:00
Ishaan Jaff
3c16fcff1b fix linting errors 2024-09-06 16:41:47 -07:00
Ishaan Jaff
42f56e4287
Merge pull request #5570 from BerriAI/litellm_fix_datadog
[Fix-Datdog Logger] Log exceptions when callbacks faces an error
2024-09-06 16:32:16 -07:00
Ishaan Jaff
67751d0ecc fix use view for getting tag usage 2024-09-06 16:28:24 -07:00
Ishaan Jaff
43acf6d08f use view for getting tag usage on ui 2024-09-06 16:28:05 -07:00
Ishaan Jaff
bf1325e898
Merge pull request #5411 from gary149/huggingface-update
Update Hugging Face Doc
2024-09-06 16:18:31 -07:00
Ishaan Jaff
b659095f71 add cost tracking for rerank+ test 2024-09-06 16:06:19 -07:00
Ishaan Jaff
d1342c5991 fix RerankResponse type 2024-09-06 16:05:19 -07:00