Commit graph

16623 commits

Author SHA1 Message Date
Ishaan Jaff
54102a660d pass cache_control in tool call 2024-08-14 15:18:11 -07:00
Ishaan Jaff
96f9655a02 test test_anthropic_api_prompt_caching_basic 2024-08-14 15:06:10 -07:00
Krish Dholakia
75ed22d391
Merge pull request #5192 from BerriAI/litellm_fix_pass_through_endpoints
feat(user_api_key_auth.py): support calling langfuse with litellm user_api_key_auth
2024-08-14 14:59:46 -07:00
Ishaan Jaff
69a640e9c4 test amnthropic prompt caching 2024-08-14 14:59:46 -07:00
Krish Dholakia
aa2267bddb
Merge branch 'main' into litellm_fix_pass_through_endpoints 2024-08-14 14:59:38 -07:00
Ishaan Jaff
b0651bd481 add anthropic cache controls 2024-08-14 14:56:49 -07:00
Krrish Dholakia
179dd7b893 docs(model_management.md): add section on adding additional model information to proxy config 2024-08-14 14:39:48 -07:00
Krrish Dholakia
9b46ec05b0 fix(factory.py): support assistant messages as a list of dictionaries - cohere messages api
Fixes https://github.com/BerriAI/litellm/pull/5121
2024-08-14 14:19:59 -07:00
Krrish Dholakia
10f27bb1b5 test(test_pass_through_endpoints.py): fix langfuse base 2024-08-14 14:13:21 -07:00
Krish Dholakia
eb5f0a8da2
Merge pull request #5148 from fabceolin/main
Enable follow redirects in ollama_chat
2024-08-14 14:08:45 -07:00
Krrish Dholakia
1faa931f26 build(model_prices_and_context_window.json): add 'supports_assistant_prefill' to all vertex ai anthropic models 2024-08-14 14:08:12 -07:00
Ishaan Jaff
9791352dc6 add testing for test_anthropic_cache_controls_pt 2024-08-14 14:07:48 -07:00
Krish Dholakia
4c6b14c301
Merge pull request #5203 from paul-gauthier/main
vertex_ai/claude-3-5-sonnet@20240620 support prefill
2024-08-14 14:06:20 -07:00
Krrish Dholakia
1e78b3bf54 fix(utils.py): fix is_azure_openai_model helper function 2024-08-14 14:04:39 -07:00
Ishaan Jaff
68e24fbf14 test passing cache controls through anthropic msg 2024-08-14 13:49:07 -07:00
Krrish Dholakia
583a3b330d fix(utils.py): support calling openai models via azure_ai/ 2024-08-14 13:41:04 -07:00
Ishaan Jaff
209c91ac03 feat - anthropic api context caching v0 2024-08-14 13:08:03 -07:00
Krish Dholakia
22243c6571
Merge pull request #5176 from BerriAI/litellm_key_logging
Allow specifying langfuse project for logging in key metadata
2024-08-14 12:55:07 -07:00
Krish Dholakia
1766b61616
Merge pull request #5206 from bachya/bachya/perplexity-cost-updates
Update prices/context windows for Perplexity Llama 3.1 models
2024-08-14 12:53:40 -07:00
Aaron Bach
9d42dfb417 Update prices/context windows for Perplexity Llama 3.1 models 2024-08-14 13:20:22 -06:00
Krrish Dholakia
5af9794b9d test(test_pass_through_endpoints.py): correctly reset test 2024-08-14 10:48:42 -07:00
Ishaan Jaff
066ed20eb0 bump: version 1.43.11 → 1.43.12 2024-08-14 10:42:08 -07:00
Ishaan Jaff
f0ea00d4ab bump: version 1.43.10 → 1.43.11 2024-08-14 10:42:06 -07:00
Paul Gauthier
6a32b05bb1 vertex_ai/claude-3-5-sonnet@20240620 support prefill 2024-08-14 10:14:19 -07:00
Krrish Dholakia
edbe9e0741 test(test_function_call_parsing.py): fix test 2024-08-14 09:59:13 -07:00
Krrish Dholakia
6bcfa90ba8 test(test_pass_through_endpoints.py): fix test 2024-08-14 09:53:19 -07:00
Ishaan Jaff
98ea24aab0
Merge pull request #5202 from BerriAI/litellm_prom_prefix_litellm
[Fix] Prometheus use 'litellm_' prefix for new deployment metrics
2024-08-14 09:50:36 -07:00
Ishaan Jaff
38b6196413
Merge pull request #5200 from BerriAI/litellm_gcs_failure_callback
[Feat-Proxy] Add failure logging for GCS bucket
2024-08-14 09:50:29 -07:00
Ishaan Jaff
69f6952597
Merge pull request #5186 from BerriAI/litellm_prisma_issues
[Fix-Proxy] Fix prisma non-root user issues
2024-08-14 09:29:57 -07:00
Ishaan Jaff
47afbfcbaa allow running as non-root user 2024-08-14 09:26:47 -07:00
Ishaan Jaff
6f06da7d46 fix use normal prisma 2024-08-14 09:24:22 -07:00
Ishaan Jaff
acadabe6c9 use litellm_ prefix for new deployment metrics 2024-08-14 09:08:14 -07:00
Krrish Dholakia
4cef6df4cf docs(sidebar.js): cleanup docs 2024-08-14 09:04:52 -07:00
Ishaan Jaff
326d797111 log failure calls on gcs + testing 2024-08-14 08:55:51 -07:00
Ishaan Jaff
bb877f6ead fix test for gcs bucket 2024-08-14 08:40:02 -07:00
Ishaan Jaff
63af2942ab feat log fail events on gcs 2024-08-14 08:39:16 -07:00
Krish Dholakia
5b46c88eb6
Merge pull request #5199 from zby/calendar_example
Mismatch in example fixed
2024-08-14 08:37:07 -07:00
Krish Dholakia
a6bf763dd9
Merge pull request #5116 from thiswillbeyourgithub/fix_ollama_argument_order
fix: wrong order of arguments for ollama
2024-08-14 08:36:14 -07:00
Zbigniew Łukasiak
963c921c5a
Mismatch in example fixed 2024-08-14 15:07:10 +02:00
Krrish Dholakia
5fdbfcee44 fix(user_api_key_auth.py): more precisely expand scope to handle 'basic' tokens 2024-08-13 22:00:33 -07:00
Krrish Dholakia
2b7a64ee28 test(test_proxy_server.py): skip local test 2024-08-13 21:36:16 -07:00
Ishaan Jaff
e0978378c1 return detailed error message on check_valid_ip 2024-08-13 21:29:21 -07:00
Krrish Dholakia
0d0a793e20 test(test_proxy_server.py): refactor test to work on ci/cd 2024-08-13 21:27:59 -07:00
Ishaan Jaff
05725b8341 bump: version 1.43.9 → 1.43.10 2024-08-13 21:20:11 -07:00
Ishaan Jaff
4d2cedfdb6
Merge pull request #5191 from BerriAI/litellm_load_config_from_s3
[Feat] Allow loading LiteLLM config from s3 buckets
2024-08-13 21:19:16 -07:00
Ishaan Jaff
09535b25f4 fix use s3 get_credentials to get boto3 creds 2024-08-13 21:18:06 -07:00
Krish Dholakia
c8f4cd373d
Merge pull request #5189 from ArtyomZemlyak/patch-1
Fix not sended json_data_for_triton
2024-08-13 20:44:26 -07:00
Krrish Dholakia
c1279ed809 fix(bedrock_httpx.py): fix error code for not found provider/model combo to be 404 2024-08-13 20:36:12 -07:00
Krish Dholakia
d6125ca257
Merge pull request #5190 from Manouchehri/chatgpt-4o-latest-pricing
(models): Add chatgpt-4o-latest
2024-08-13 20:34:54 -07:00
Ishaan Jaff
a37f087b62 fix ci/cd pipeline 2024-08-13 20:33:33 -07:00