Commit graph

2623 commits

Author SHA1 Message Date
Krrish Dholakia
4c5398b556 test(test_timeout.py): fix test 2024-04-25 19:35:30 -07:00
Krrish Dholakia
885de2e3c6 fix(proxy/utils.py): log rejected proxy requests to langfuse 2024-04-25 19:26:27 -07:00
Krish Dholakia
69280177a3
Merge pull request #3308 from BerriAI/litellm_fix_streaming_n
fix(utils.py): fix the response object returned when n>1 for stream=true
2024-04-25 18:36:54 -07:00
Krrish Dholakia
1985231022 test(test_timeout.py): explicitly set num retries = 0 2024-04-25 18:06:25 -07:00
Krrish Dholakia
9f5ba67f5d fix(utils.py): return logprobs as an object not dict 2024-04-25 17:55:18 -07:00
Krrish Dholakia
54241f2551 test(test_router_fallbacks.py): fix testing 2024-04-25 17:43:40 -07:00
Ishaan Jaff
de6e03f410
Merge pull request #3307 from BerriAI/litellm_set_alerts_per_channel
[Backend-Alerting] Separate alerting for different channels
2024-04-25 16:35:16 -07:00
Krrish Dholakia
caf1e28ba3 test(test_completion.py): fix test 2024-04-25 14:07:07 -07:00
Krrish Dholakia
5f8d88d363 fix(vertex_ai.py): handle stream=false
also adds unit testing for vertex ai calls with langchain
2024-04-25 13:59:37 -07:00
Krrish Dholakia
a819454647 test(test_completion.py): fix test to not raise exception if it works 2024-04-25 13:31:19 -07:00
Krrish Dholakia
6c5c7cca3d fix(utils.py): fix the response object returned when n>1 for stream=true
Fixes https://github.com/BerriAI/litellm/issues/3276
2024-04-25 13:27:29 -07:00
Ishaan Jaff
2aa849b7ae fix test alerting 2024-04-25 13:06:17 -07:00
Krrish Dholakia
160acc085a fix(router.py): fix default retry logic 2024-04-25 11:57:27 -07:00
Krrish Dholakia
4f46b4c397 fix(factory.py): add replicate meta llama prompt templating support 2024-04-25 08:25:00 -07:00
Ishaan Jaff
74817c560e (ci/cd) run again 2024-04-24 23:23:14 -07:00
Ishaan Jaff
4e707af592 Revert "fix(router.py): fix max retries on set_client"
This reverts commit 821844c1a3.
2024-04-24 23:19:14 -07:00
Ishaan Jaff
13e0ac64ef (fix) updating router settings 2024-04-24 23:09:25 -07:00
Krrish Dholakia
821844c1a3 fix(router.py): fix max retries on set_client 2024-04-24 22:03:01 -07:00
Ishaan Jaff
242830108c (ci/cd) run again 2024-04-24 21:09:49 -07:00
Krish Dholakia
435a4b5ed4
Merge pull request #3267 from BerriAI/litellm_openai_streaming_fix
fix(utils.py): fix streaming to not return usage dict
2024-04-24 21:08:33 -07:00
Ishaan Jaff
2c7f4695d9
Merge pull request #3283 from BerriAI/litellm_debug_lowest_latency
[Fix] Add better observability for debugging lowest latency routing
2024-04-24 20:42:52 -07:00
Krrish Dholakia
df7db2b870 fix(factory.py): support llama3 instuct chat template
allows automatic templating for llama3 instruct requests
2024-04-24 20:35:10 -07:00
Krrish Dholakia
495aebb582 fix(utils.py): fix setattr error 2024-04-24 20:19:27 -07:00
Ishaan Jaff
2e6fc91a75 test - lowest latency logger 2024-04-24 16:35:43 -07:00
Ishaan Jaff
36f8431bf0 (ci/cd) testing 2024-04-24 13:25:18 -07:00
Ishaan Jaff
efbf85a5ad /model/update endpoint 2024-04-24 10:39:20 -07:00
Krrish Dholakia
48c2c3d78a fix(utils.py): fix streaming to not return usage dict
Fixes https://github.com/BerriAI/litellm/issues/3237
2024-04-24 08:06:07 -07:00
Simon Sanchez Viloria
9fc30e8b31 (test) Added completion and embedding tests for watsonx provider 2024-04-24 12:52:29 +02:00
Krish Dholakia
4acdde988f
Merge pull request #3250 from BerriAI/litellm_caching_no_cache_fix
fix(utils.py): fix 'no-cache': true when caching is turned on
2024-04-23 19:57:07 -07:00
Ishaan Jaff
3b860a7f20
Merge pull request #3255 from BerriAI/litellm_refactor_slack_alerting
[Fix] Refactor slack alerting, use one httpx client
2024-04-23 19:45:52 -07:00
Ishaan Jaff
c1ea3597bc fix test alerting 2024-04-23 19:10:06 -07:00
Krish Dholakia
8d2e411df6
Merge pull request #3124 from elisalimli/bugfix/add-missing-tool-calls-mistral-messages
Add missing tool_calls and name to messages
2024-04-23 17:25:12 -07:00
Krrish Dholakia
72ac0d26e3 test: fix test 2024-04-23 16:56:48 -07:00
Krrish Dholakia
d67e47d7fd fix(test_caching.py): add longer delay for async test 2024-04-23 16:13:03 -07:00
Krrish Dholakia
161e836427 fix(utils.py): fix 'no-cache': true when caching is turned on 2024-04-23 12:58:30 -07:00
Krrish Dholakia
9d2726c2ac fix(proxy_server.py): handle router being initialized without a model list 2024-04-23 10:52:28 -07:00
Krrish Dholakia
a520e1bd6f fix(router.py): add random shuffle and tpm-based shuffle for async shuffle logic 2024-04-22 12:58:59 -07:00
Ishaan Jaff
1fea2b0397 (ci/cd) run again 2024-04-21 16:50:11 -07:00
alisalim17
e404dd7569 test: add test forfunction calling with mistral large latest to test_streaming.py 2024-04-21 11:27:42 +04:00
alisalim17
319e006d13 test: add test for function calling with mistral large latest to test_completion.py 2024-04-21 11:27:21 +04:00
Ishaan Jaff
a909af3fc0 (ci/cd) fix test_master_key_hashing 2024-04-20 14:50:34 -07:00
Krish Dholakia
fcde3ba213
Merge pull request #3192 from BerriAI/litellm_calculate_max_parallel_requests
fix(router.py): Make TPM limits concurrency-safe
2024-04-20 13:24:29 -07:00
Krish Dholakia
3faada32d5
Merge pull request #3118 from n1lanjan/2833-anthropic-tool-call-fix
Fix tool call errors using anthropic
2024-04-20 13:14:29 -07:00
Krrish Dholakia
c96ca1f85e fix(router.py): improve debug logsd 2024-04-20 13:12:12 -07:00
Krrish Dholakia
0f69f0b44e test(test_router_max_parallel_requests.py): more extensive testing for setting max parallel requests 2024-04-20 12:56:54 -07:00
Ishaan Jaff
f89f8a4157
Merge pull request #3184 from BerriAI/litellm_ui_non_admins_flow
[UI] - non admin flow - only Create + Test Key available
2024-04-20 12:40:43 -07:00
Krrish Dholakia
e56dc2817b test(test_router_max_parallel_requests.py): add unit tests for different scenarios 2024-04-20 12:29:38 -07:00
Ishaan Jaff
7ebf2ca4d9 (ci/cd) testing with team_id and /user/new 2024-04-20 11:09:34 -07:00
Ishaan Jaff
81e4d59357 test - gemini-1.5-pro-latest 2024-04-19 21:22:19 -07:00
Krrish Dholakia
fa14d3c8dc test: remove duplicate test file 2024-04-19 19:56:36 -07:00