Commit graph

12 commits

Author SHA1 Message Date
Ishaan Jaff
f77bf49772
feat - allow sending tags on vertex pass through requests (#6876)
* feat - allow tagging vertex JS SDK request

* add unit testing for passing headers for pass through endpoints

* fix allow using vertex_ai as the primary way for pass through vertex endpoints

* docs on vertex js pass tags

* add e2e test for vertex pass through with spend tags

* add e2e tests for streaming vertex JS with tags

* fix vertex ai testing
2024-11-25 12:12:09 -08:00
Ishaan Jaff
b8af46e1a2
(feat) Add usage tracking for streaming /anthropic passthrough routes (#6842)
* use 1 file for AnthropicPassthroughLoggingHandler

* add support for anthropic streaming usage tracking

* ci/cd run again

* fix - add real streaming for anthropic pass through

* remove unused function stream_response

* working anthropic streaming logging

* fix code quality

* fix use 1 file for vertex success handler

* use helper for _handle_logging_vertex_collected_chunks

* enforce vertex streaming to use sse for streaming

* test test_basic_vertex_ai_pass_through_streaming_with_spendlog

* fix type hints

* add comment

* fix linting

* add pass through logging unit testing
2024-11-21 19:36:03 -08:00
Krrish Dholakia
24a0d26eb1 test(skip-flaky-google-context-caching-test): google is not reliable. their sample code is also not working 2024-10-22 12:06:30 -07:00
Krish Dholakia
3933fba41f
LiteLLM Minor Fixes & Improvements (09/19/2024) (#5793)
* fix(model_prices_and_context_window.json): add cost tracking for more vertex llama3.1 model

8b and 70b models

* fix(proxy/utils.py): handle data being none on pre-call hooks

* fix(proxy/): create views on initial proxy startup

fixes base case, where user starts proxy for first time

 Fixes https://github.com/BerriAI/litellm/issues/5756

* build(config.yml): fix vertex version for test

* feat(ui/): support enabling/disabling slack alerting

Allows admin to turn on/off slack alerting through ui

* feat(rerank/main.py): support langfuse logging

* fix(proxy/utils.py): fix linting errors

* fix(langfuse.py): log clean metadata

* test(tests): replace deprecated openai model
2024-09-20 08:19:52 -07:00
Ishaan Jaff
e9427205ef add test for pass through streaming usage tracking 2024-09-02 16:17:49 -07:00
Ishaan Jaff
9e557ed072 fix test 2024-08-31 08:39:52 -07:00
Ishaan Jaff
b35bfb0302 fix cost tracking for vertex ai native 2024-08-31 08:22:27 -07:00
Ishaan Jaff
06857d108d fix /spend logs call 2024-08-30 17:02:24 -07:00
Ishaan Jaff
2c86a62474 fix vertex ai test 2024-08-30 16:50:23 -07:00
Ishaan Jaff
f43060e8df mark as async 2024-08-30 16:40:41 -07:00
Ishaan Jaff
414d2dcb52 call spend logs endpoint 2024-08-30 16:35:07 -07:00
Ishaan Jaff
f3f85f6141 add test for vertex basic pass throgh 2024-08-30 16:26:00 -07:00