a61275f6e2
Merge pull request #13796 from 0x-fang/fix_aip_pass_through_08_20
...
Fix(Bedrock): fix application inference profile for pass-through endpoints for bedrock
2025-08-21 19:41:23 -07:00
7c2c1c11d9
Merge pull request #13783 from philipkiely-baseten/main
...
Update Baseten LiteLLM integration
2025-08-21 18:34:36 -07:00
77a5de37b1
[Fix] Ensure Service Account Keys require team_id field on API Endpoints ( #13873 )
...
* fixes for generating service accounts through the API
* fixes for test_update_service_account_works_with_team_id
2025-08-21 14:55:06 -07:00
5fa4a18073
add testing and remove redundant function
2025-08-21 11:25:26 -07:00
0e6e8af1c3
Merge pull request #13795 from TomeHirata/feat/predict/mlflow
...
Include predicted output in MLflow tracing
2025-08-20 22:40:33 -07:00
1f84451925
Merge pull request #13803 from UlookEE/fix_bedrock_epc_acompletion
...
fix : Synchronize cache behavior between acompletion and completion
2025-08-20 22:38:30 -07:00
ff267ab68e
Merge pull request #13820 from kankute-sameer/litellm_rerank_deepinfra_endpoint
...
Add rerank endpoint support for deepinfra
2025-08-20 22:33:25 -07:00
609679ded4
Merge pull request #13835 from 0x-fang/fix_api_key_guardrail_proxy
...
Fix(bedrock): fix the api key support for bedrock guardrail in proxy
2025-08-20 22:31:17 -07:00
07f6235730
[Performance] Improve LiteLLM Python SDK RPS by +200 RPS ( #13839 )
...
* fix _proxy_from_env +100 RPS
* fix: global_braintrust_http_handler
* test_braintrust_logging
2025-08-20 21:46:33 -07:00
91040b6b56
fix the api key support for bedrock guardrail in proxy
2025-08-20 18:46:00 -07:00
55dcaded72
[Feat] Add VertexAI qwen API Service ( #13828 )
...
* add support for vertex AI QWEN API
* streaming QWEN API support
* test_partner_models_httpx
* test_partner_models_httpx_streaming
* add cost tracking for vertex_ai/qwen/qwen3-235b-a22b-instruct-2507-maa
* docs qwen models vertexAI
2025-08-20 15:00:33 -07:00
5b5a2d12a8
remove test
2025-08-21 00:32:16 +05:30
1d1d637ac0
fix automated checks
2025-08-21 00:09:17 +05:30
37b84d1582
Add rerank endpoint support for deepinfra
2025-08-20 23:36:05 +05:30
12bae8fdda
test_partner_models_httpx_streaming
2025-08-20 09:44:47 -07:00
e69a895884
test_apply_default_settings
2025-08-20 08:53:38 -07:00
036b358636
Synchronize cache behavior between acompletion and completion
2025-08-20 18:27:36 +09:00
caad9b3ca7
fix application inference profile for pass-through endpoints for bedrock
2025-08-20 00:40:43 -07:00
5879f6e930
comment
2025-08-20 15:46:53 +09:00
d64b579131
Include predicted output in tracing
...
Signed-off-by: Tomu Hirata <tomu.hirata@gmail.com >
2025-08-20 15:39:32 +09:00
04feaf33c0
Merge pull request #13748 from hakasecurity/migrate-to-aim-new-firewall-api
...
Migrate to aim new firewall api
2025-08-19 22:32:22 -07:00
be30bc68ae
Merge pull request #13759 from kankute-sameer/litellm_feat_correct_cost_calculations
...
Add long context support for claude-4-sonnet
2025-08-19 22:30:25 -07:00
7d09375d52
fix: fix gpt-5-chat mappings
2025-08-19 22:21:00 -07:00
56ac778316
[Bug Fix] Bedrock KB - Using LiteLLM Managed Credentials for Query ( #13787 )
...
* fix: add get_credentials_for_vector_store
* test_search_uses_registry_credentials
* test_bedrock_search_with_credentials_managed_registry
2025-08-19 15:39:36 -07:00
48622a4ee7
add cache above 200k keys in INTENDED_SCHEMA
2025-08-20 01:47:34 +05:30
fa81b6c639
Update test_cost_calculator.py
2025-08-19 23:14:22 +05:30
195ea6515e
[Feat] Datadog LLM Observability - Add support for tracing guardrail input/output ( #13767 )
...
* add guardrail information on DD LLM Obs
* test_guardrail_information_in_metadata
2025-08-19 10:26:25 -07:00
b5f0a7b49b
Merge branch 'main' into litellm_feat_correct_cost_calculations
2025-08-19 18:55:36 +05:30
d39b2e8888
Add test for long context cost calculation
2025-08-19 16:56:13 +05:30
6b78ade918
migrate to use new aim FW API
2025-08-19 12:20:19 +03:00
88e52c55d0
Merge pull request #13675 from colesmcintosh/fix/groq-streaming-encoding
...
Fix Groq streaming ASCII encoding issue
2025-08-18 23:00:00 -07:00
9dadd279a4
Merge pull request #13741 from BerriAI/litellm_dev_08_18_2025_p1
...
Refactor - forward model group headers - reuse same logic as global header forwarding
2025-08-18 22:58:39 -07:00
2c0520635d
test: cleanup old tests
2025-08-18 22:58:29 -07:00
048f22b7ec
Merge pull request #13742 from BerriAI/litellm_dev_08_18_2025_p2
...
Fix - gemini prompt caching cost calculation
2025-08-18 22:54:28 -07:00
3713c926c0
Merge pull request #13704 from michal-otmianowski/use-namespace-as-prefix-for-s3-cache
...
Use namespace as prefix for s3 cache
2025-08-18 22:37:18 -07:00
f7f1a0d0b7
test: add unit test
2025-08-18 22:32:36 -07:00
2e16f2cb13
test: add unit tests
2025-08-18 21:19:43 -07:00
422447b7f1
Responses API - add default api version for openai responses api calls + Openrouter - fix claude-sonnet-4 on openrouter + Azure - Handle openai/v1/responses
...
Responses API - add default api version for openai responses api calls + Openrouter - fix claude-sonnet-4 on openrouter + Azure - Handle `openai/v1/responses`
2025-08-18 18:59:28 -07:00
3b52545db3
Merge pull request #13529 from BerriAI/litellm_dev_08_11_2025_p1
...
[Fix] Cooldowns - don't return raw Azure Exceptions to client
2025-08-18 18:54:19 -07:00
ba0881d728
[Bug Fix] image_edit() function returns APIConnectionError with litellm_proxy - Support for both image edits and image generations ( #13735 )
...
* add image edits litellm proxy on SDK
* add image gen provider
* add IMG Gen support for litellm_proxy provider
2025-08-18 18:26:32 -07:00
76f1064229
[Bug Fix] litellm incompatible with newest release of openAI v1.100.0 ( #13728 )
...
* fix imports OpenAI SDK
* ResponseText fixes
* fixes ResponseText
* fix imports
* catch AttributeError
* fix import
* use openai==1.100.1
* fix build from PIP
* fix lint test
* Print OpenAI version
* fix Install dependencies
2025-08-18 18:26:17 -07:00
ba1d2e8749
[Feat] DD LLM Observability - Add time to first token, litellm overhead, guardrail overhead latency metrics ( #13734 )
...
* fixes for DDLLMObsLatencyMetrics
* use _get_latency_metrics
* DD LLM Obs - track latency metrics
* fixes for bedrock guardrails
* DD unit tests
* test DD
2025-08-18 17:38:04 -07:00
ef08e18c66
[Feat] Datadog LLM Observability - Add support for Failure Logging ( #13726 )
...
* add async_log_failure_event for DD LLM Obs
* update types
* DataDogLLMObsLogger add failure logging support
* test_async_log_failure_event
* dd test failure
2025-08-18 15:19:48 -07:00
169a17400f
fix(vertexai-batch): fix vertexai batch file format ( #13576 )
...
* fix(access group): allow access group on mcp tool retrieval
* fix(test): fix broken tests and add test case for access group
* fix(mypy): fix typing issues
* fix(memory file): add content type to in memory file
2025-08-18 10:19:23 -07:00
405e74ec16
use namespace as prefix in s3
2025-08-18 13:43:51 +02:00
6322aef0e3
fix(streaming_handler.py): fix streaming chunk calculation
2025-08-16 14:25:29 -07:00
eb66daeef7
test: update test
...
we now return correct token usage on clientside
2025-08-16 14:14:35 -07:00
d96df5e9be
Revert "test_stream_token_counting_anthropic_with_include_usage"
...
This reverts commit c3aee1194b
2025-08-16 13:07:00 -07:00
c3aee1194b
test_stream_token_counting_anthropic_with_include_usage
2025-08-16 13:06:31 -07:00
8bb5ee2ba5
test: update unit test
2025-08-16 12:39:03 -07:00
Krish Dholakia