yuneng-jiang
7e3f3c6f65
Migrate /public/provider/fields to react query
2025-11-26 18:16:52 -08:00
Ishaan Jaffer
5cfcc98d2e
fix img gen
2025-11-26 17:56:59 -08:00
yuneng-jiang
ac1827cbfc
Merge pull request #17168 from BerriAI/litellm_ui_users_loading
...
[Feature] UI - Better Loading State for Internal User Page
2025-11-26 17:28:40 -08:00
yuneng-jiang
9a4d3bc347
Merge pull request #17170 from BerriAI/litellm_key_create_duration_fix
...
[Fix] UI - Create Key Duration Fix
2025-11-26 17:24:30 -08:00
Ishaan Jaffer
0346d1ea23
fix
2025-11-26 17:11:33 -08:00
yuneng-jiang
f0e5921bbd
Add emoji for exact text match
2025-11-26 17:09:07 -08:00
Ishaan Jaff
831694897e
[Feat] RAG API - QA - allow internal user keys to access api, allow using litellm credentials with API, raise clear exception when RAG API fails ( #17169 )
...
* allow using a cred with RAG API
* add /rag/ingest to llm api routes
* add rag endpoints under llm api routes
* raise clear exception when RAG API fails
* use async methods for bedrock ingest
* fix ingestion
* fix _create_opensearch_collection
* fix qa check and linting
2025-11-26 17:07:30 -08:00
yuneng-jiang
4b951c3ced
Removing flaky tests
2025-11-26 17:04:12 -08:00
yuneng-jiang
aad0075366
Change create key duration initial value to null
2025-11-26 17:00:56 -08:00
yuneng-jiang
67f9c6cc08
Adjusting e2e tests for new loading state
2025-11-26 16:47:37 -08:00
yuneng-jiang
87b4e9ebad
User table loading state
2025-11-26 16:24:29 -08:00
AlexsanderHamir
df190d25b8
Add deprecation notice to /spend/logs endpoint
...
- Mark /spend/logs as deprecated in docstring
- Direct users to use /spend/logs/v2 for paginated access
- Warns about performance issues with non-paginated endpoint
2025-11-26 16:16:13 -08:00
AlexsanderHamir
1ad9e014ab
Add endpoint-based date parsing for /spend/logs/v2
...
- Add flexible date parsing for v2 endpoint (supports both YYYY-MM-DD and YYYY-MM-DD HH:MM:SS)
- Keep strict timestamp format for /spend/logs/ui endpoint for backward compatibility
- Parse dates based on which endpoint was called using request path
2025-11-26 16:11:53 -08:00
Ishaan Jaff
379655e16b
[Feat] LiteLLM RAG API - Add support for Vertex RAG engine ( #17117 )
...
* add VertexAIVectorStoreOptions
* Revert "add VertexAIVectorStoreOptions"
This reverts commit b086adf10b
2025-11-26 15:49:04 -08:00
AlexsanderHamir
210560e1e7
Add paginated /spend/logs/v2 endpoint
...
- Add /spend/logs/v2 endpoint that shares implementation with /spend/logs/ui
- Provides paginated access to spend logs with comprehensive filtering
- Replaces non-paginated /spend/logs endpoint to prevent performance issues
- Both v2 and ui endpoints share the same function for consistency
2025-11-26 15:48:43 -08:00
SamAcctX
32617d1e72
Add OpenRouter Opus 4.5 ( #17144 )
2025-11-26 15:45:45 -08:00
yuneng-jiang
1b34312488
Merge pull request #17166 from BerriAI/litellm_ui_mh_server_root
...
[Fix] UI - Change model_hub_table to call getUiConfig before Fetching Public Data
2025-11-26 15:30:16 -08:00
yuneng-jiang
86af4891fa
Change model_hub_table to call getUiConfig before fetching public data
2025-11-26 15:12:40 -08:00
Ishaan Jaffer
8f1be80054
fix code qa check
2025-11-26 14:45:07 -08:00
Alexsander Hamir
c0d9facd96
Merge pull request #17089 from BerriAI/litellm_refactor_01
...
[Refactor#1] `litellm/init` – Lazy-load `cost_calculator` & `logging` to reduce memory + import time
2025-11-26 14:41:46 -08:00
Ishaan Jaffer
ce60453855
test_gemini_get_complete_url
2025-11-26 14:35:03 -08:00
AlexsanderHamir
49f0a86d0c
revert fix
2025-11-26 14:34:29 -08:00
Sameer Kankute
b97ea585b2
Add method for extracting vector store ids from path params ( #16566 )
...
* Add method for extracting vector store ids from path params
* Add vector id handling from path
* Move method to utils
2025-11-26 14:19:30 -08:00
yuneng-jiang
8d72d86cb6
Merge pull request #17163 from BerriAI/litellm_extras_version_bump
...
bump: version 0.4.8 → 0.4.9
2025-11-26 14:17:11 -08:00
Ishaan Jaff
d987593855
[Feat] Add audio transcriptions for WatsonX ( #17160 )
...
* feat: add IBMWatsonXAudioTranscriptionConfig
* init IBMWatsonXAudioTranscriptionConfig
* add inits
* test_watsonx_transcription_url_and_headers
* docs watsox audio
* docs watsonx audi
* docs
2025-11-26 14:15:49 -08:00
yuneng-jiang
21830cb853
Including files for publish_proxy_extras output
2025-11-26 14:15:06 -08:00
yuneng-jiang
f1789a5fa9
bump: version 0.4.8 → 0.4.9
2025-11-26 14:12:15 -08:00
yuneng-jiang
d8e4aaf301
Merge pull request #17161 from BerriAI/litellm_fix_flaky_ui_test_teaminfo
...
[Fix] UI - Fix Flaky Test
2025-11-26 14:02:38 -08:00
yuneng-jiang
1a9b2d2206
Merge pull request #16560 from BerriAI/litellm_org_usage
...
[Feature] Organization Usage
2025-11-26 13:55:58 -08:00
yuneng-jiang
cfdade1a6f
Adding timeout it instead
2025-11-26 13:53:31 -08:00
yuneng-jiang
b93fe4b93e
Add explicit timeout for flaky tests
2025-11-26 13:41:03 -08:00
yuneng-jiang
ce9474a039
Updating spend writer
2025-11-26 13:31:04 -08:00
yuneng-jiang
02e99f22f8
Revert "Revert "Update spend logs writer to add organization_id""
...
This reverts commit b11a803dd3
2025-11-26 13:29:27 -08:00
Ishaan Jaffer
5a60a8ab3b
bump: version 1.80.5 → 1.80.6
2025-11-26 13:20:25 -08:00
Ishaan Jaffer
9aef28fe70
fix get litellm params
2025-11-26 13:20:05 -08:00
Ishaan Jaffer
0437be13d3
bump pyproject extras
2025-11-26 13:10:57 -08:00
Ishaan Jaffer
bb7db67f32
0.4.8 extras bump
2025-11-26 12:42:51 -08:00
Ishaan Jaffer
4e9490b1db
fix fallback handlers
2025-11-26 12:39:17 -08:00
yuneng-jiang
b11a803dd3
Revert "Update spend logs writer to add organization_id"
...
This reverts commit 5b645d5f2f
2025-11-26 12:39:04 -08:00
Ishaan Jaffer
529c56423c
test_opentelemetry_integration
2025-11-26 12:28:47 -08:00
Ishaan Jaffer
44e3133827
test_imagen_get_complete_url
2025-11-26 12:26:49 -08:00
yuneng-jiang
046b5fc27b
Merge remote-tracking branch 'origin' into litellm_org_usage
2025-11-26 12:23:43 -08:00
Ishaan Jaffer
7e0822fb55
fix validate_environment
2025-11-26 12:12:38 -08:00
Ishaan Jaffer
4bf5830106
test fix
2025-11-26 12:07:58 -08:00
Chesars
8c128edb5d
test: add unit tests for BaseModelResponseIterator empty SSE line filtering
...
Tests verify that empty lines between SSE events are properly filtered
and don't produce extra empty chunks in streaming responses.
2025-11-26 17:05:40 -03:00
Ishaan Jaffer
2548c89042
code qa check
2025-11-26 12:04:12 -08:00
Ishaan Jaffer
983ada20c3
mock test fixes
2025-11-26 12:02:35 -08:00
Chesars
16a7e0ce8f
fix: filter empty SSE lines in BaseModelResponseIterator to prevent extra empty chunks
...
When streaming with stream_options={"include_usage": True}, xAI and other
providers using BaseLLMHTTPHandler were returning an extra empty chunk after
the usage chunk. This was caused by empty SSE lines (separators between events)
being processed as empty GenericStreamingChunks.
The fix adds a loop in __next__ and __anext__ to skip empty lines before
processing, ensuring only meaningful SSE data events are converted to chunks.
Fixes #17136
2025-11-26 17:01:23 -03:00
Ishaan Jaffer
2d70aee0c2
test_edit_mcp_server_redacts_credentials
2025-11-26 11:54:11 -08:00
Ishaan Jaffer
a48705bfaf
fix code QA checks
2025-11-26 11:53:58 -08:00
