phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
10692 commits 1603 branches 645 tags 320 MiB
Commit graph

10692 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaff
d6f7fa7f4e v0 prisma schema 2024-04-30 11:42:17 -07:00
Krrish Dholakia
1cd24d8906 bump: version 1.35.32 → 1.35.33 2024-04-30 07:20:50 -07:00
Krrish Dholakia
020b175ef4 fix(lowest_tpm_rpm_v2.py): skip if item_tpm is None 2024-04-29 21:34:25 -07:00
Ishaan Jaff
81df36b298 docs - slack alerting 2024-04-29 21:33:03 -07:00
Ishaan Jaff
b1e888edad docs example logging to langfuse 2024-04-29 21:26:27 -07:00
Ishaan Jaff
0cad58f5c6 docs logging to langfuse on proxy 2024-04-29 21:26:15 -07:00
Ishaan Jaff
0c99ae9451 docs - fix kub.yaml config on docs 2024-04-29 21:20:29 -07:00
Krrish Dholakia
b46db8b891 feat(utils.py): json logs for raw request sent by litellm 
make it easier to view verbose logs in datadog
 2024-04-29 19:21:19 -07:00
Krrish Dholakia
f0e48cdd53 fix(router.py): raise better exception when no deployments are available 
Fixes https://github.com/BerriAI/litellm/issues/3355
 2024-04-29 18:48:04 -07:00
Krrish Dholakia
1e53c06064 test(test_router_caching.py): remove unstable test 
test would fail due to timing issues
 2024-04-29 18:37:31 -07:00
Krrish Dholakia
e7b4882e97 fix(router.py): fix high-traffic bug for usage-based-routing-v2 2024-04-29 16:48:01 -07:00
Krish Dholakia
09bae3d8ad
Merge pull request #3351 from elisalimli/main 
Fix Cohere tool calling
 2024-04-29 16:45:48 -07:00
Krish Dholakia
32534b5e91
Merge pull request #3358 from sumanth13131/usage-based-routing-RPM-fix 
usage based routing RPM count fix
 2024-04-29 16:45:25 -07:00
Krrish Dholakia
bd79e8b516 docs(langfuse_integration.md): add 'existing_trace_id' to langfuse docs 2024-04-29 16:40:38 -07:00
Krrish Dholakia
853b70aba9 fix(langfuse.py): support 'existing_trace_id' param 
allow user to call out a trace as pre-existing, this prevents creating a default trace name, and potentially overwriting past traces
 2024-04-29 16:39:17 -07:00
Krrish Dholakia
2cf069befb fix(langfuse.py): don't set default trace_name if trace_id given 2024-04-29 16:39:17 -07:00
Ishaan Jaff
d58dd2cbeb
Merge pull request #3360 from BerriAI/litellm_random_pick_lowest_latency 
[Fix] Lowest Latency routing - random pick deployments when all latencies=0
 2024-04-29 16:31:32 -07:00
Krrish Dholakia
77f155d158 docs(load_test.md): cleanup docs 2024-04-29 16:27:58 -07:00
Krrish Dholakia
af6a21f27c docs(load_test.md): add multi-instance router load test to docs 2024-04-29 16:25:56 -07:00
Ishaan Jaff
4cb4a7f06d fix - lowest latency routing 2024-04-29 16:02:57 -07:00
Krrish Dholakia
8f830bd948 docs(load_test.md): simplify doc 2024-04-29 16:00:02 -07:00
Krrish Dholakia
fcb83781ec docs(load_test.md): formatting 2024-04-29 15:58:41 -07:00
Krrish Dholakia
5fe0f38558 docs(load_test.md): load test multiple instances of the proxy w/ tpm/rpm limits on deployments 2024-04-29 15:58:14 -07:00
Ishaan Jaff
3b0aa05378 fix lowest latency - routing 2024-04-29 15:51:52 -07:00
Ishaan Jaff
5247d7b6a5 test - lowest latency router 2024-04-29 15:51:01 -07:00
Krrish Dholakia
cef2d95bb4 docs(routing.md): add max parallel requests to router docs 2024-04-29 15:37:48 -07:00
Krrish Dholakia
a978f2d881 fix(lowest_tpm_rpm_v2.py): shuffle deployments with same tpm values 2024-04-29 15:23:47 -07:00
Krrish Dholakia
f10a066d36 fix(lowest_tpm_rpm_v2.py): add more detail to 'No deployments available' error message 2024-04-29 15:04:37 -07:00
Ishaan Jaff
de3e642999
Merge pull request #3359 from BerriAI/litellm_docs_trackin_cost 
docs - update track cost with custom callbacks
 2024-04-29 13:19:25 -07:00
Ishaan Jaff
8d26030b99 docs - track cost custom callbacks 2024-04-29 13:15:08 -07:00
sumanth
89e655c79e usage based routing RPM count fix 2024-04-30 00:29:38 +05:30
Krrish Dholakia
4b04b017df bump: version 1.35.31 → 1.35.32 2024-04-29 09:16:44 -07:00
Krish Dholakia
ec2510029a
Merge pull request #3354 from BerriAI/litellm_replicate_cost_tracking 
fix(utils.py): replicate now also has token based pricing for some models
 2024-04-29 09:13:41 -07:00
Krrish Dholakia
3725732c4d fix(utils.py): default to time-based tracking for unmapped replicate models. fix time-based cost calc for replicate 2024-04-29 08:36:01 -07:00
Krrish Dholakia
a18844b230 fix(utils.py): use llama tokenizer for replicate models 2024-04-29 08:28:31 -07:00
Krrish Dholakia
dc5c175406 build(model_prices_and_context_window.json): add token-based replicate costs to model cost map 2024-04-29 08:20:44 -07:00
Krrish Dholakia
ab954243e8 fix(utils.py): fix watson streaming 2024-04-29 08:09:59 -07:00
Krrish Dholakia
2cfb97141d fix(utils.py): replicate now also has token based pricing for some models 2024-04-29 08:06:15 -07:00
alisalim17
0aa8b94ff5 test: completion with Cohere command-r-plus model 2024-04-29 18:38:12 +04:00
Krrish Dholakia
0a6b6302f1 fix(router.py): fix typing error 2024-04-29 07:25:39 -07:00
Krrish Dholakia
7b617e666d fix(proxy_server.py): return more detailed auth error message. 2024-04-29 07:24:19 -07:00
Krish Dholakia
ffc6af0b22
Merge pull request #3334 from CyanideByte/main 
protected_namespaces warning fixed for model_name & model_info
 2024-04-29 07:16:05 -07:00
alisalim17
0db7fa3fd8 fix: cohere tool results 2024-04-29 14:20:24 +04:00
Krrish Dholakia
f74a43aa78 docs(vllm.md): update docs to tell people to check openai-compatible endpoint docs for vllm 2024-04-28 09:48:03 -07:00
Krrish Dholakia
1f6c342e94 test: fix test 2024-04-28 09:45:01 -07:00
Krish Dholakia
39244cd517
Merge pull request #3331 from BerriAI/litellm_common_auth_params 
feat(utils.py): unify common auth params across azure/vertex_ai/bedrock/watsonx
 2024-04-28 09:27:07 -07:00
Krish Dholakia
1841b74f49
Merge branch 'main' into litellm_common_auth_params 2024-04-28 08:38:06 -07:00
Krrish Dholakia
b9c0b55e7c test: fix test - set num_retries=0 2024-04-27 21:02:19 -07:00
CyanideByte
82be9a7e67
Merge branch 'BerriAI:main' into main 2024-04-27 20:51:33 -07:00
CyanideByte
03a43b99a5 Added _types.py cases from edwinjosegeorge PR#3340 2024-04-27 20:42:54 -07:00