Ishaan Jaff
9692b2ed73
ui new build
2025-03-11 12:22:12 -07:00
Steve Farthing
ffce48ed3c
Merge branch 'stevefarthing/bing-search-pass-thru' of github.com:sfarthin/litellm into stevefarthing/bing-search-pass-thru
...
# Conflicts:
# litellm/proxy/pass_through_endpoints/pass_through_endpoints.py
2025-03-11 08:15:23 -04:00
Steve Farthing
dbfb7ebdaf
Merge branch 'main' into stevefarthing/bing-search-pass-thru
2025-03-11 08:06:56 -04:00
Steve Farthing
e8a859720b
Feedback
2025-03-11 08:01:31 -04:00
Steve Farthing
75b713974f
Bing Search Pass Thru
2025-03-11 08:01:31 -04:00
Krish Dholakia
9610c844c7
Merge pull request #9109 from BerriAI/litellm_dev_03_10_2025_p1_v2
...
Read Version from pyproject.toml / read-version (push) Successful in 12s
Return `code`, `param` and `type` on openai bad request error
2025-03-10 22:38:16 -07:00
Krish Dholakia
c93a5e2301
Merge pull request #9047 from BerriAI/litellm_dev_03_06_2025_p4
...
feat(handle_jwt.py): support multiple jwt url's
2025-03-10 22:37:35 -07:00
Krrish Dholakia
01aa536716
fix: fix test
2025-03-10 21:46:05 -07:00
Krrish Dholakia
92881ee79e
fix: fix linting error
2025-03-10 21:22:00 -07:00
Ishaan Jaff
3ee6a3eaee
ui new build
2025-03-10 21:05:00 -07:00
Krrish Dholakia
5a5639e81b
feat(credential_endpoints/endpoints.py): don't return credentials on get
...
prevent leakage
2025-03-10 20:11:38 -07:00
Ishaan Jaff
aa5ac6ba3d
can_team_access_model
2025-03-10 20:03:19 -07:00
Krrish Dholakia
f56c5ca380
feat: working e2e credential management - support reusing existing credentials
2025-03-10 19:29:24 -07:00
Ishaan Jaff
0d6df360bf
test_can_team_access_model fix
2025-03-10 19:09:50 -07:00
Ishaan Jaff
9dcc25d63b
Merge branch 'main' into litellm_fix_team_model_access_checks
2025-03-10 19:05:11 -07:00
Krrish Dholakia
2ec7830b66
feat: complete crud endpoints for credential management on proxy
2025-03-10 18:46:35 -07:00
Krish Dholakia
c58941d49c
Merge branch 'main' into litellm_dev_03_06_2025_p4
2025-03-10 18:41:10 -07:00
Krrish Dholakia
507640bc8f
fix(endpoints.py): encrypt credentials before storing in db
2025-03-10 18:37:59 -07:00
Krrish Dholakia
a962a97fcb
feat(endpoints.py): support writing credentials to db
2025-03-10 18:27:43 -07:00
Krrish Dholakia
f1cdc26967
feat(endpoints.py): initial set of crud endpoints for reusable credentials on proxy
2025-03-10 17:48:02 -07:00
Krrish Dholakia
fdd5ba3084
feat(credential_accessor.py): support loading in credentials from credential_list
...
Resolves https://github.com/BerriAI/litellm/issues/9114
2025-03-10 17:15:58 -07:00
Krrish Dholakia
4bd4bb16fd
feat(proxy_server.py): move credential list to being a top-level param
2025-03-10 17:04:05 -07:00
Krrish Dholakia
5458b08425
fix(router.py): comment out azure/openai client init - not necessary
2025-03-10 16:47:43 -07:00
Krrish Dholakia
f688fc8138
feat(proxy_server.py): check code before defaulting to status code
2025-03-10 15:34:06 -07:00
Krish Dholakia
e00d4fb18c
Litellm dev 03 08 2025 p3 ( #9089 )
...
* feat(ollama_chat.py): pass down http client to ollama_chat
enables easier testing
* fix(factory.py): fix passing images to ollama's `/api/generate` endpoint
Fixes https://github.com/BerriAI/litellm/issues/6683
* fix(factory.py): fix ollama pt to handle templating correctly
2025-03-09 18:20:56 -07:00
Ishaan Jaff
b41311bb21
(UI) - Fix show correct count of internal user keys on Users Page ( #9082 )
...
* get_user_key_counts
* fix get_user_key_counts
* fix get_user_key_counts
* test_get_users_filters_dashboard_keys
* remove unused func
2025-03-08 16:13:18 -08:00
Ishaan Jaff
73df319f4e
(Clean up) - Allow switching off storing Error Logs in DB ( #9084 )
...
* fix - cleanup, dont store ErrorLogs in 2 tables
* async_post_call_failure_hook
* docs disable error logs
* disable_error_logs
2025-03-08 16:12:03 -08:00
Krish Dholakia
4330ef8e81
Fix batches api cost tracking + Log batch models in spend logs / standard logging payload ( #9077 )
...
Read Version from pyproject.toml / read-version (push) Successful in 42s
* feat(batches/): fix batch cost calculation - ensure it's accurate
use the correct cost value - prev. defaulting to non-batch cost
* feat(batch_utils.py): log batch models to spend logs + standard logging payload
makes it easy to understand how cost was calculated
* fix: fix stored payload for test
* test: fix test
2025-03-08 11:47:25 -08:00
Krish Dholakia
0e3caf92b9
UI - new API Playground for testing LiteLLM translation ( #9073 )
...
* feat: initial commit - enable dev to see translated request
* feat(utils.py): expose new endpoint - `/utils/transform_request` to see the raw request sent by litellm
* feat(transform_request.tsx): allow user to see their transformed request
* refactor(litellm_logging.py): return raw request in 3 parts - api_base, headers, request body
easier to render each individually on UI vs. extracting from combined string
* feat: transform_request.tsx
working e2e raw request viewing
* fix(litellm_logging.py): fix transform viewing for bedrock models
* fix(litellm_logging.py): don't return sensitive headers in raw request headers
prevent accidental leak
* feat(transform_request.tsx): style improvements
2025-03-07 19:39:31 -08:00
Ishaan Jaff
b5eeafdd72
(Docs) OpenWeb x LiteLLM Docker compose + Instructions on spend tracking + logging ( #9059 )
...
* docs improve open web ui litellm doc
* docs openweb show teams + keys
* docs open web ui litellm
2025-03-07 17:01:39 -08:00
Ishaan Jaff
7f70bdd99b
(Feat) - add pricing for eu.amazon.nova models ( #9056 )
...
* add pricing for eu.amazon.nova models
* fix typo in key management endpoints.py
2025-03-07 07:06:17 -08:00
Krish Dholakia
5591354309
Support master key rotations ( #9041 )
...
* feat(key_management_endpoints.py): adding support for rotating master key
* feat(key_management_endpoints.py): support decryption-re-encryption of models in db, when master key rotated
* fix(user_api_key_auth.py): raise valid token is None error earlier
enables easier debugging with api key hash in error message
* feat(key_management_endpoints.py): rotate any env vars
* fix(key_management_endpoints.py): uncomment check
* fix: fix linting error
2025-03-06 23:13:30 -08:00
Krrish Dholakia
805679becc
feat(handle_jwt.py): support multiple jwt url's
2025-03-06 23:05:54 -08:00
Krish Dholakia
274147bc5e
fix(team_endpoints.py): ensure 404 raised when team not found ( #9038 )
...
* fix(team_endpoints.py): ensure 404 raised when team not found
* fix(key_management_endpoints.py): fix adding tags to key when metadata is empty
* fix(key_management_endpoints.py): refactor set metadata field to use common function across keys + teams
reduces scope for errors + easier testing
* fix: fix linting error
2025-03-06 22:04:36 -08:00
Ishaan Jaff
0fed8bcefd
ui new build
2025-03-06 21:22:58 -08:00
Ishaan Jaff
73448412e1
ui allow ui or eu api base adding model ( #9042 )
2025-03-06 21:22:03 -08:00
Ishaan Jaff
958e71b906
(Docs) connect litellm to open web ui ( #9040 )
...
* init doc
* working thinking tutorial
* docs open web ui with litellm
* minor edits
* docs one tab for tutorials
2025-03-06 21:13:00 -08:00
Ishaan Jaff
04e839d846
(AWS Secret Manager) - Using K/V pairs in 1 AWS Secret ( #9039 )
...
* fixes for primary_secret_kv_pairs
* _parse_primary_secret
* Using K/V pairs in 1 AWS Secret
* test_primary_secret_functionality
2025-03-06 19:30:18 -08:00
Ishaan Jaff
b02af305de
[Feat] - Display thinking tokens on OpenWebUI (Bedrock, Anthropic, Deepseek) ( #9029 )
...
Read Version from pyproject.toml / read-version (push) Successful in 14s
* if merge_reasoning_content_in_choices
* _optional_combine_thinking_block_in_choices
* stash changes
* working merge_reasoning_content_in_choices with bedrock
* fix litellm_params accessor
* fix streaming handler
* merge_reasoning_content_in_choices
* _optional_combine_thinking_block_in_choices
* test_bedrock_stream_thinking_content_openwebui
* merge_reasoning_content_in_choices
* fix for _optional_combine_thinking_block_in_choices
* linting error fix
2025-03-06 18:32:58 -08:00
Ishaan Jaff
f47987e673
(Refactor) /v1/messages to follow simpler logic for Anthropic API spec ( #9013 )
...
* anthropic_messages_handler v0
* fix /messages
* working messages with router methods
* test_anthropic_messages_handler_litellm_router_non_streaming
* test_anthropic_messages_litellm_router_non_streaming_with_logging
* AnthropicMessagesConfig
* _handle_anthropic_messages_response_logging
* working with /v1/messages endpoint
* working /v1/messages endpoint
* refactor to use router factory function
* use aanthropic_messages
* use BaseConfig for Anthropic /v1/messages
* track api key, team on /v1/messages endpoint
* fix get_logging_payload
* BaseAnthropicMessagesTest
* align test config
* test_anthropic_messages_with_thinking
* test_anthropic_streaming_with_thinking
* fix - display anthropic url for debugging
* test_bad_request_error_handling
* test_anthropic_messages_router_streaming_with_bad_request
* fix ProxyException
* test_bad_request_error_handling_streaming
* use provider_specific_header
* test_anthropic_messages_with_extra_headers
* test_anthropic_messages_to_wildcard_model
* fix gcs pub sub test
* standard_logging_payload
* fix unit testing for anthopic /v1/messages support
* fix pass through anthropic messages api
* delete dead code
* fix anthropic pass through response
* revert change to spend tracking utils
* fix get_litellm_metadata_from_kwargs
* fix spend logs payload json
* proxy_pass_through_endpoint_tests
* TestAnthropicPassthroughBasic
* fix pass through tests
* test_async_vertex_proxy_route_api_key_auth
* _handle_anthropic_messages_response_logging
* vertex_credentials
* test_set_default_vertex_config
* test_anthropic_messages_litellm_router_non_streaming_with_logging
* test_ageneric_api_call_with_fallbacks_basic
* test__aadapter_completion
2025-03-06 00:43:08 -08:00
Krrish Dholakia
3be3b802c8
fix: fix linting error
2025-03-05 10:10:53 -08:00
Ishaan Jaff
8d6815ce98
Revert "(UI) - Security Improvement, move to JWT Auth for Admin UI Sessions ( #8995 )"
...
This reverts commit 01a44a4e47
2025-03-05 08:49:20 -08:00
Krrish Dholakia
313b315791
fix: fix linting error
2025-03-05 08:26:26 -08:00
Krish Dholakia
c69ec66dc5
fix(base_aws_llm.py): remove region name before sending in args ( #8998 )
...
Read Version from pyproject.toml / read-version (push) Successful in 12s
* fix(base_aws_llm.py): remove region name before sending in args
* fix(base_aws_llm.py): fix optional param pop position
* fix: fix linting error
2025-03-04 23:05:28 -08:00
Krrish Dholakia
e715c376b9
fix: fix linting error
2025-03-04 22:34:07 -08:00
Krish Dholakia
5e386c28b2
Litellm dev 03 04 2025 p3 ( #8997 )
...
* fix(core_helpers.py): handle litellm_metadata instead of 'metadata'
* feat(batches/): ensure batches logs are written to db
makes batches response dict compatible
* fix(cost_calculator.py): handle batch response being a dictionary
* fix(batches/main.py): modify retrieve endpoints to use @client decorator
enables logging to work on retrieve call
* fix(batches/main.py): fix retrieve batch response type to be 'dict' compatible
* fix(spend_tracking_utils.py): send unique uuid for retrieve batch call type
create batch and retrieve batch share the same id
* fix(spend_tracking_utils.py): prevent duplicate retrieve batch calls from being double counted
* refactor(batches/): refactor cost tracking for batches - do it on retrieve, and within the established litellm_logging pipeline
ensures cost is always logged to db
* fix: fix linting errors
* fix: fix linting error
2025-03-04 21:58:03 -08:00
Ishaan Jaff
01a44a4e47
(UI) - Security Improvement, move to JWT Auth for Admin UI Sessions ( #8995 )
...
* (UI) - Improvements to session handling logic (#8970 )
* add cookieUtils
* use utils for clearing cookies
* on logout use clearTokenCookies
* ui use correct clearTokenCookies
* navbar show userEmail on UserID page
* add timestamp on token cookie
* update generate_authenticated_redirect_response
* use common getAuthToken
* fix clearTokenCookies
* fixes for get auth token
* fix invitation link sign in logic
* Revert "fix invitation link sign in logic"
This reverts commit 30e5308cb3
2025-03-04 21:48:23 -08:00
Krish Dholakia
f1a44d1fdc
fix(common_utils.py): handle $id in response schema when calling vert… ( #8991 )
...
* fix(common_utils.py): handle $id in response schema when calling vertex ai
Fixes issue where `$id` present in response_schema was not accepted by vertex ai
* test(test_vertex.py): add unit test to ensure $id stripped out of vertex schema
2025-03-04 21:19:50 -08:00
Ishaan Jaff
4c8b4fefc9
Revert "(UI) - Improvements to session handling logic ( #8970 )"
...
Read Version from pyproject.toml / read-version (push) Successful in 15s
This reverts commit c015fb34f1
2025-03-04 13:29:08 -08:00
Ishaan Jaff
772c2b1fff
Revert "ui new build"
...
This reverts commit 94563ab1e7
2025-03-04 13:28:54 -08:00
