phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
18250 commits 1603 branches 645 tags 320 MiB
Commit graph

53 commits

Author SHA1 Message Date
Krish Dholakia
136693cac4
LiteLLM Minor Fixes & Improvements (11/05/2024) (#6590) 
* fix(pattern_matching_router.py): update model name using correct function

* fix(langfuse.py): metadata deepcopy can cause unhandled error (#6563)

Co-authored-by: seva <seva@inita.com>

* fix(stream_chunk_builder_utils.py): correctly set prompt tokens + log correct streaming usage

Closes https://github.com/BerriAI/litellm/issues/6488

* build(deps): bump cookie and express in /docs/my-website (#6566)

Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together.

Updates `cookie` from 0.6.0 to 0.7.1
- [Release notes](https://github.com/jshttp/cookie/releases)
- [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1)

Updates `express` from 4.20.0 to 4.21.1
- [Release notes](https://github.com/expressjs/express/releases)
- [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md)
- [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1)

---
updated-dependencies:
- dependency-name: cookie
  dependency-type: indirect
- dependency-name: express
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* docs(virtual_keys.md): update Dockerfile reference (#6554)

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

* (proxy fix) - call connect on prisma client when running setup (#6534)

* critical fix - call connect on prisma client when running setup

* fix test_proxy_server_prisma_setup

* fix test_proxy_server_prisma_setup

* Add 3.5 haiku (#6588)

* feat: add claude-3-5-haiku-20241022 entries

* feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models

* add missing entries, remove vision

* remove image token costs

* Litellm perf improvements 3 (#6573)

* perf: move writing key to cache, to background task

* perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils

adds 200ms on calls with pgdb connected

* fix(litellm_pre_call_utils.py'): rename call_type to actual call used

* perf(proxy_server.py): remove db logic from _get_config_from_file

was causing db calls to occur on every llm request, if team_id was set on key

* fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db

reduces latency/call by ~100ms

* fix(proxy_server.py): minor fix on existing_settings not incl alerting

* fix(exception_mapping_utils.py): map databricks exception string

* fix(auth_checks.py): fix auth check logic

* test: correctly mark flaky test

* fix(utils.py): handle auth token error for tokenizers.from_pretrained

* build: fix map

* build: fix map

* build: fix json for model map

* fix ImageObject conversion (#6584)

* (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546)

* unit test test_huggingface_text_completion_logprobs

* fix return TextCompletionHandler convert_chat_to_text_completion

* fix hf rest api

* fix test_huggingface_text_completion_logprobs

* fix linting errors

* fix importLiteLLMResponseObjectHandler

* fix test for LiteLLMResponseObjectHandler

* fix test text completion

* fix allow using 15 seconds for premium license check

* testing fix bedrock deprecated cohere.command-text-v14

* (feat) add `Predicted Outputs` for OpenAI  (#6594)

* bump openai to openai==1.54.0

* add 'prediction' param

* testing fix bedrock deprecated cohere.command-text-v14

* test test_openai_prediction_param.py

* test_openai_prediction_param_with_caching

* doc Predicted Outputs

* doc Predicted Output

* (fix) Vertex Improve Performance when using `image_url`  (#6593)

* fix transformation vertex

* test test_process_gemini_image

* test_image_completion_request

* testing fix - bedrock has deprecated cohere.command-text-v14

* fix vertex pdf

* bump: version 1.51.5 → 1.52.0

* fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check (#6577)

* fix(lowest_tpm_rpm_routing.py): fix parallel rate limit check

* fix(lowest_tpm_rpm_v2.py): return headers in correct format

* test: update test

* build(deps): bump cookie and express in /docs/my-website (#6566)

Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together.

Updates `cookie` from 0.6.0 to 0.7.1
- [Release notes](https://github.com/jshttp/cookie/releases)
- [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1)

Updates `express` from 4.20.0 to 4.21.1
- [Release notes](https://github.com/expressjs/express/releases)
- [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md)
- [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1)

---
updated-dependencies:
- dependency-name: cookie
  dependency-type: indirect
- dependency-name: express
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* docs(virtual_keys.md): update Dockerfile reference (#6554)

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

* (proxy fix) - call connect on prisma client when running setup (#6534)

* critical fix - call connect on prisma client when running setup

* fix test_proxy_server_prisma_setup

* fix test_proxy_server_prisma_setup

* Add 3.5 haiku (#6588)

* feat: add claude-3-5-haiku-20241022 entries

* feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models

* add missing entries, remove vision

* remove image token costs

* Litellm perf improvements 3 (#6573)

* perf: move writing key to cache, to background task

* perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils

adds 200ms on calls with pgdb connected

* fix(litellm_pre_call_utils.py'): rename call_type to actual call used

* perf(proxy_server.py): remove db logic from _get_config_from_file

was causing db calls to occur on every llm request, if team_id was set on key

* fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db

reduces latency/call by ~100ms

* fix(proxy_server.py): minor fix on existing_settings not incl alerting

* fix(exception_mapping_utils.py): map databricks exception string

* fix(auth_checks.py): fix auth check logic

* test: correctly mark flaky test

* fix(utils.py): handle auth token error for tokenizers.from_pretrained

* build: fix map

* build: fix map

* build: fix json for model map

* test: remove eol model

* fix(proxy_server.py): fix db config loading logic

* fix(proxy_server.py): fix order of config / db updates, to ensure fields not overwritten

* test: skip test if required env var is missing

* test: fix test

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com>

* test: mark flaky test

* test: handle anthropic api instability

* test(test_proxy_utils.py): add testing for db config update logic

* Update setuptools in docker and fastapi to latest verison, in order to upgrade starlette version (#6597)

* build(deps): bump cookie and express in /docs/my-website (#6566)

Bumps [cookie](https://github.com/jshttp/cookie) and [express](https://github.com/expressjs/express). These dependencies needed to be updated together.

Updates `cookie` from 0.6.0 to 0.7.1
- [Release notes](https://github.com/jshttp/cookie/releases)
- [Commits](https://github.com/jshttp/cookie/compare/v0.6.0...v0.7.1)

Updates `express` from 4.20.0 to 4.21.1
- [Release notes](https://github.com/expressjs/express/releases)
- [Changelog](https://github.com/expressjs/express/blob/4.21.1/History.md)
- [Commits](https://github.com/expressjs/express/compare/4.20.0...4.21.1)

---
updated-dependencies:
- dependency-name: cookie
  dependency-type: indirect
- dependency-name: express
  dependency-type: indirect
...

Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>

* docs(virtual_keys.md): update Dockerfile reference (#6554)

Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>

* (proxy fix) - call connect on prisma client when running setup (#6534)

* critical fix - call connect on prisma client when running setup

* fix test_proxy_server_prisma_setup

* fix test_proxy_server_prisma_setup

* Add 3.5 haiku (#6588)

* feat: add claude-3-5-haiku-20241022 entries

* feat: add claude-3-5-haiku-20241022 and vertex_ai/claude-3-5-haiku@20241022 models

* add missing entries, remove vision

* remove image token costs

* Litellm perf improvements 3 (#6573)

* perf: move writing key to cache, to background task

* perf(litellm_pre_call_utils.py): add otel tracing for pre-call utils

adds 200ms on calls with pgdb connected

* fix(litellm_pre_call_utils.py'): rename call_type to actual call used

* perf(proxy_server.py): remove db logic from _get_config_from_file

was causing db calls to occur on every llm request, if team_id was set on key

* fix(auth_checks.py): add check for reducing db calls if user/team id does not exist in db

reduces latency/call by ~100ms

* fix(proxy_server.py): minor fix on existing_settings not incl alerting

* fix(exception_mapping_utils.py): map databricks exception string

* fix(auth_checks.py): fix auth check logic

* test: correctly mark flaky test

* fix(utils.py): handle auth token error for tokenizers.from_pretrained

* build: fix map

* build: fix map

* build: fix json for model map

* fix ImageObject conversion (#6584)

* (fix) litellm.text_completion raises a non-blocking error on simple usage (#6546)

* unit test test_huggingface_text_completion_logprobs

* fix return TextCompletionHandler convert_chat_to_text_completion

* fix hf rest api

* fix test_huggingface_text_completion_logprobs

* fix linting errors

* fix importLiteLLMResponseObjectHandler

* fix test for LiteLLMResponseObjectHandler

* fix test text completion

* fix allow using 15 seconds for premium license check

* testing fix bedrock deprecated cohere.command-text-v14

* (feat) add `Predicted Outputs` for OpenAI  (#6594)

* bump openai to openai==1.54.0

* add 'prediction' param

* testing fix bedrock deprecated cohere.command-text-v14

* test test_openai_prediction_param.py

* test_openai_prediction_param_with_caching

* doc Predicted Outputs

* doc Predicted Output

* (fix) Vertex Improve Performance when using `image_url`  (#6593)

* fix transformation vertex

* test test_process_gemini_image

* test_image_completion_request

* testing fix - bedrock has deprecated cohere.command-text-v14

* fix vertex pdf

* bump: version 1.51.5 → 1.52.0

* Update setuptools in docker and fastapi to latest verison, in order to upgrade starlette version

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com>
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
Co-authored-by: Jacob Hagstedt <wcgs@novonordisk.com>

* fix(langfuse.py): fix linting errors

* fix: fix linting errors

* fix: fix casting error

* fix: fix typing error

* fix: add more tests

* fix(utils.py): fix return_processed_chunk_logic

* Revert "Update setuptools in docker and fastapi to latest verison, in order t…" (#6615)

This reverts commit 1a7f7bdfb7.

* docs fix clarify team_id on team based logging

* doc fix team based logging with langfuse

* fix flake8 checks

* test: bump sleep time

* refactor: replace claude-instant-1.2 with haiku in testing

* fix(proxy_server.py): move to using sl payload in track_cost_callback

* fix(proxy_server.py): fix linting errors

* fix(proxy_server.py): fallback to kwargs(response_cost) if given

* test: remove claude-instant-1 from tests

* test: fix claude test

* docs fix clarify team_id on team based logging

* doc fix team based logging with langfuse

* build: remove lint.yml

---------

Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: Vsevolod Karvetskiy <56288164+karvetskiy@users.noreply.github.com>
Co-authored-by: seva <seva@inita.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Emmanuel Ferdman <emmanuelferdman@gmail.com>
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: paul-gauthier <69695708+paul-gauthier@users.noreply.github.com>
Co-authored-by: Jacob Hagstedt P Suorra <Jacobh2@users.noreply.github.com>
Co-authored-by: Jacob Hagstedt <wcgs@novonordisk.com>
 2024-11-07 04:17:05 +05:30
Krish Dholakia
d57be47b0f
Litellm ruff linting enforcement (#5992) 
* ci(config.yml): add a 'check_code_quality' step

Addresses https://github.com/BerriAI/litellm/issues/5991

* ci(config.yml): check why circle ci doesn't pick up this test

* ci(config.yml): fix to run 'check_code_quality' tests

* fix(__init__.py): fix unprotected import

* fix(__init__.py): don't remove unused imports

* build(ruff.toml): update ruff.toml to ignore unused imports

* fix: fix: ruff + pyright - fix linting + type-checking errors

* fix: fix linting errors

* fix(lago.py): fix module init error

* fix: fix linting errors

* ci(config.yml): cd into correct dir for checks

* fix(proxy_server.py): fix linting error

* fix(utils.py): fix bare except

causes ruff linting errors

* fix: ruff - fix remaining linting errors

* fix(clickhouse.py): use standard logging object

* fix(__init__.py): fix unprotected import

* fix: ruff - fix linting errors

* fix: fix linting errors

* ci(config.yml): cleanup code qa step (formatting handled in local_testing)

* fix(_health_endpoints.py): fix ruff linting errors

* ci(config.yml): just use ruff in check_code_quality pipeline for now

* build(custom_guardrail.py): include missing file

* style(embedding_handler.py): fix ruff check
 2024-10-01 19:44:20 -04:00
Ishaan Jaff
4b7ceade64 mark test_key_info_spend_values_streaming as flaky 2024-08-29 14:39:53 -07:00
Krrish Dholakia
5703da9b42 fix(user_api_key_auth.py): Fixes https://github.com/BerriAI/litellm/issues/5111 2024-08-08 10:30:15 -07:00
Krrish Dholakia
c27ae34a39 fix(proxy_server.py): use consistent 400-status code error code for exceeded budget errors 
standardizes error code for budget exceeded errors to status code 400
 2024-06-11 16:10:58 -07:00
Ishaan Jaff
6166381579 fix migrate to LitellmUserRoles 2024-05-30 13:57:50 -07:00
Krrish Dholakia
95566dc249 fix(proxy_server.py): fix model list returned for /model/info when team has restricted access 2024-05-25 13:21:33 -07:00
Krrish Dholakia
25a2f00db6 fix(proxy_server.py): fix model check for /v1/models endpoint when team has restricted access 2024-05-25 13:02:03 -07:00
Ishaan Jaff
595a2a5b1b fix test_key_model_list 2024-05-22 20:49:19 -07:00
Krrish Dholakia
f2766fddbf fix(proxy_server.py): fix /v1/models bug where it would return empty list 
handle 'all-team-models' being set for a given key
 2024-05-07 13:43:15 -07:00
Ishaan Jaff
31c4f5f811 (ci/cd) add detailed debugging info 2024-05-06 11:40:16 -07:00
Krrish Dholakia
918367cc7b test: skip hanging test 2024-05-05 00:27:38 -07:00
Krrish Dholakia
b9f5b3c1a0 build(test_keys.py): improve error message for test 2024-05-01 08:22:28 -07:00
Krrish Dholakia
5583197d63 fix(proxy_server.py): fix setting offset-aware datetime 2024-04-25 21:18:32 -07:00
Ishaan Jaff
7b24a74e77 test fix - test_key_delete_ui 2024-04-20 12:30:58 -07:00
Ishaan Jaff
a34f725db7 fix - test keys 2024-04-20 11:43:43 -07:00
Krrish Dholakia
70716b3373 fix(proxy_server.py): fix key create logic + add unit tests 2024-04-16 13:08:34 -07:00
Ishaan Jaff
e20d3f29b0 test - delete keys 2024-04-15 16:37:20 -07:00
Krrish Dholakia
af2eabba91 fix(proxy_server.py): fix /key/update endpoint to update key duration 
also adds a test for this to our ci/cd
 2024-03-29 21:47:10 -07:00
Krrish Dholakia
c81c9c2583 fix(proxy_server.py): fix model info check 2024-03-23 15:59:17 -07:00
Krrish Dholakia
066346b8c8 test: handle flaky tests locally - causing db timeout issues on circle ci 2024-03-19 20:39:53 -07:00
Krrish Dholakia
f588bff69b fix(proxy_server.py): fix spend log update 2024-03-18 20:26:28 -07:00
Krrish Dholakia
b9854a99d2 test: increase time before checking budget reset - avoid deadlocking 2024-03-06 22:16:59 -08:00
Krrish Dholakia
ad55f4dbb5 feat(proxy_server.py): retry if virtual key is rate limited 
currently for chat completions
 2024-03-05 19:00:03 -08:00
Krrish Dholakia
2b595bfdc9 test(test_keys.py): add more duration for test 2024-03-05 15:42:19 -08:00
Krrish Dholakia
4f3d1ee11f test(test_keys.py): extend time for test 2024-03-02 21:19:34 -08:00
Krrish Dholakia
37ad5efc61 fix(proxy/utils.py): fix resetting budget logic 2024-03-02 20:52:54 -08:00
Krrish Dholakia
f7a2d3faef test: skip sagemaker test - aws account suspended 2024-02-28 15:00:53 -08:00
Krrish Dholakia
5265d9042d test: testing fixes 2024-02-27 20:35:42 -08:00
Krrish Dholakia
4a0df3cb4f fix(proxy_cli.py-&&-proxy_server.py): bump reset budget intervals and fix pool limits for prisma connections 2024-02-06 19:39:49 -08:00
Krrish Dholakia
b6adeec347 fix(proxy_server.py): prisma client fixes for high traffic 2024-02-06 17:30:36 -08:00
Krrish Dholakia
ef0171e063 feat(utils.py): support cost tracking for openai/azure image gen models 2024-02-03 17:09:54 -08:00
ishaan-jaff
419bddae93 (fix) show error in test_keys 2024-02-02 19:15:03 -08:00
Krrish Dholakia
bfe2faa454 test(test_keys.py): separate streaming key info test from normal completion key info test 2024-02-02 19:03:47 -08:00
ishaan-jaff
d7d1aa1266 (ci/cd) run again 2024-02-02 18:56:03 -08:00
Krrish Dholakia
92ebe132e8 test(test_keys.py): fix test 2024-01-31 11:26:49 -08:00
Krrish Dholakia
ecc6855e49 build(config.yml): add more logging for docker build and test 2024-01-31 10:58:25 -08:00
Krrish Dholakia
eea4325e60 test(test_keys.py): add more retries for checking if budget updated 2024-01-31 10:44:19 -08:00
Krrish Dholakia
70d5f9ef96 test(test_keys.py): reorder tests 2024-01-31 09:37:37 -08:00
Krrish Dholakia
f9acad87dc feat(proxy_server.py): enable cache controls per key + no-store cache flag 2024-01-30 20:46:50 -08:00
ishaan-jaff
9c4d9c2f58 (test) /key/info 2024-01-26 19:26:55 -08:00
ishaan-jaff
2a60af7164 (test) key crossing budget 2024-01-26 14:43:16 -08:00
ishaan-jaff
55b95e87dd (fix) SpendLogs Table 2024-01-26 13:23:51 -08:00
Krrish Dholakia
554f1a090d test(test_keys.py): add delay for test check 
n
 2024-01-25 18:31:07 -08:00
Krrish Dholakia
09ec6d6458 fix(utils.py): fix sagemaker async logging for sync streaming 
https://github.com/BerriAI/litellm/issues/1592
 2024-01-25 12:49:45 -08:00
Krrish Dholakia
8e1157fc92 test(test_keys.py): reset proxy spend 2024-01-24 21:08:09 -08:00
Krrish Dholakia
bb7705b494 test(test_users.py): test budgets with resets 2024-01-24 15:30:30 -08:00
Krrish Dholakia
e471157d57 test(test_keys.py): add testing to make sure budget resets are working as expected 2024-01-24 15:13:11 -08:00
Krrish Dholakia
f0ada5c950 test(test_spend_logs): new endpoint test for /spend/logs 2024-01-24 11:20:31 -08:00
Krrish Dholakia
d6844f43c8 test(test_keys.py): use correct model name for token counting 2024-01-23 17:46:14 -08:00