Krrish Dholakia
109add7946
build(model_prices_and_context_window.json): add gemini multimodal embedding cost
2025-03-26 23:04:24 -07:00
Ishaan Jaff
7097ce544e
Merge pull request #9569 from BerriAI/litellm_fix_db_unavailable
...
Read Version from pyproject.toml / read-version (push) Successful in 19s
Helm unit test / unit-test (push) Successful in 21s
Publish Prisma Migrations / publish-migrations (push) Failing after 1m18s
[Reliability Fix] - Allow Pods to startup + passing /health/readiness when `allow_requests_on_db_unavailable: True` and DB is down
2025-03-26 21:18:52 -07:00
Ishaan Jaff
05c38049fe
docs prod.md
2025-03-26 21:04:36 -07:00
Ishaan Jaff
b6506f7bda
test_db_health_readiness_check_with_prisma_error
2025-03-26 20:56:39 -07:00
Ishaan Jaff
87f0201f84
test_handle_db_exception_with_connection_error
2025-03-26 20:44:25 -07:00
Ishaan Jaff
34e58be36d
fix order of _setup_prisma_client
2025-03-26 20:42:01 -07:00
Ishaan Jaff
427580eff5
fix _setup_prisma_client
2025-03-26 20:35:27 -07:00
Ishaan Jaff
15c04da735
refactor tests
2025-03-26 20:00:10 -07:00
Ishaan Jaff
88ef97b9d1
allow proxy to startup on DB unavailable
2025-03-26 19:50:57 -07:00
Ishaan Jaff
497570b2a6
bug fix - allow pods to startup when DB is unavailable
2025-03-26 19:49:51 -07:00
Ishaan Jaff
7142b0b610
refactor PrismaDBExceptionHandler
2025-03-26 19:22:24 -07:00
Ishaan Jaff
0155b0eba2
Merge pull request #9533 from BerriAI/litellm_stability_fixes
...
[Reliability Fixes] - Gracefully handle exceptions when DB is having an outage
2025-03-26 18:57:38 -07:00
Ishaan Jaff
485aa87e65
allow_requests_on_db_unavailable
2025-03-26 18:48:18 -07:00
Ishaan Jaff
763f853a9f
docs fix
2025-03-26 18:32:58 -07:00
Ishaan Jaff
5242c5fbab
test - auth exception handler
2025-03-26 18:28:28 -07:00
Ishaan Jaff
15b1a8afb0
test_is_database_connection_error_prisma_errors
2025-03-26 18:27:39 -07:00
Ishaan Jaff
8499a88e4a
fixes - anthropic messages interface
2025-03-26 17:45:47 -07:00
Ishaan Jaff
9eb9a369bb
working anthropic API tests
2025-03-26 17:34:41 -07:00
Krish Dholakia
4351c77253
Support Gemini audio token cost tracking + fix openai audio input token cost tracking ( #9535 )
...
* fix(vertex_and_google_ai_studio_gemini.py): log gemini audio tokens in usage object
enables accurate cost tracking
* refactor(vertex_ai/cost_calculator.py): refactor 128k+ token cost calculation to only run if model info has it
Google has moved away from this for gemini-2.0 models
* refactor(vertex_ai/cost_calculator.py): migrate to usage object for more flexible data passthrough
* fix(llm_cost_calc/utils.py): support audio token cost tracking in generic cost per token
enables vertex ai cost tracking to work with audio tokens
* fix(llm_cost_calc/utils.py): default to total prompt tokens if text tokens field not set
* refactor(llm_cost_calc/utils.py): move openai cost tracking to generic cost per token
more consistent behaviour across providers
* test: add unit test for gemini audio token cost calculation
* ci: bump ci config
* test: fix test
2025-03-26 17:26:25 -07:00
Ishaan Jaff
8dcdff9280
fix anthropic_messages
2025-03-26 17:21:14 -07:00
Ishaan Jaff
1b085a306a
add clear type hints to litellm.messages.create functions
2025-03-26 17:17:56 -07:00
Ishaan Jaff
3640262dbf
fix anthropic_messages implementation
2025-03-26 17:12:40 -07:00
Krrish Dholakia
04490c99d7
test: fix test
2025-03-26 17:12:09 -07:00
Krrish Dholakia
72c0ad419f
build(migration.sql): add migration file for new dailyusertable
...
documents prisma db changes
2025-03-26 17:11:25 -07:00
Ishaan Jaff
07dce8bed3
allow using litellm.messages.acreate and litellm.messages.create
2025-03-26 17:05:38 -07:00
Krrish Dholakia
d4adc9764b
test(test_db_schema_migration.py): ci/cd test to enforce schema migrations are documented in .sql files
2025-03-26 16:59:50 -07:00
Ishaan Jaff
968ef4a299
fix response typing
2025-03-26 16:56:56 -07:00
Ishaan Jaff
957b7eb82c
define types for response form AnthropicMessagesResponse
2025-03-26 16:54:45 -07:00
Ishaan Jaff
e93f84b347
add type hints for AnthropicMessagesResponse
2025-03-26 16:53:33 -07:00
Krish Dholakia
37265c8b1c
Add Daily User Spend Aggregate view - allows UI Usage tab to work > 1m rows ( #9538 )
...
* ci: update github action
* build(schema.prisma): enable daily user spend table
allows storing aggregate view of user's daily spend
* build(schema.prisma): add new daily user spend table
* feat: working daily user spend tracking
maintains an aggregate view for easier querying in high traffic
* setup_google_dns
* ci: update ci yaml
---------
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
2025-03-26 16:36:36 -07:00
Krrish Dholakia
fb9abd40f3
ci(config.yml): add pytest-postgres to ci/cd
2025-03-26 16:25:08 -07:00
Krish Dholakia
132d3f7baa
feat(prisma-migrations): add baseline db migration file ( #9565 )
...
adds initial baseline db migration file
enables future schema changes to be documented via .sql files
2025-03-26 16:22:56 -07:00
Ishaan Jaff
b7f4abd13a
Merge pull request #9542 from BerriAI/litellm_fix_vertex_ai_ft_models
...
[Feature]: Support for Fine-Tuned Vertex AI LLMs
2025-03-26 16:19:41 -07:00
Ishaan Jaff
23aa7f81b5
fix ProxyException
2025-03-26 15:53:33 -07:00
Ishaan Jaff
ff33ed020c
fix auth checks
2025-03-26 15:45:58 -07:00
Ishaan Jaff
8bd2081dec
fix get_key_object
2025-03-26 15:41:40 -07:00
Ishaan Jaff
f8caebc54b
is_database_connection_error
2025-03-26 14:55:40 -07:00
Ishaan Jaff
4948673e35
fix test changes
2025-03-26 14:51:33 -07:00
Ishaan Jaff
1812ce4a54
undo config.yml changes
2025-03-26 14:43:03 -07:00
Ishaan Jaff
044c56c439
Merge branch 'main' into litellm_stability_fixes
2025-03-26 14:41:43 -07:00
Ishaan Jaff
0aae9aa24a
rename _is_model_gemini_spec_model
2025-03-26 14:28:26 -07:00
Ishaan Jaff
c38b41f65b
test_get_supports_system_message
2025-03-26 14:26:08 -07:00
Ishaan Jaff
72f08bc6ea
unit tests for VertexGeminiConfig
2025-03-26 14:21:35 -07:00
Ishaan Jaff
8eaf4c55c0
test_gemini_fine_tuned_model_request_consistency
2025-03-26 14:18:11 -07:00
Ishaan Jaff
da9d849348
test_gemini_fine_tuned_model_request_consistency
2025-03-26 14:10:32 -07:00
Ishaan Jaff
82faa49668
doc fix Fine-tuned Models
2025-03-26 14:09:27 -07:00
Ishaan Jaff
28ab8fdccc
docs vertex ft model
2025-03-26 14:08:19 -07:00
Ishaan Jaff
e24a601897
docs verte ft models
2025-03-26 14:03:42 -07:00
Ishaan Jaff
82016eba0a
docs vertex ft models
2025-03-26 13:55:38 -07:00
Shixian Sheng
54e83ac8a8
Update all_caches.md
2025-03-26 15:29:58 -04:00
