 Ishaan Jaff
|
6fa421ed8e
|
test_llm_guard_triggered
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
9f927e0e4e
|
add testing for aporia guardrails
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
c9d9c6444e
|
fix aporia typo
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
902c3a8f8f
|
docs aporia
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
eb9da06033
|
feat - guardrails v2
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
cc31058451
|
docs fix typo
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
6b651be2f9
|
doc update typo
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
c0bd9edaba
|
docs updates based on feedback
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
49a27320dc
|
doc aporia_w_litellm
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
507fab06f8
|
run during_call_hook
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
b0f546d551
|
feat - return applied guardrails in response headers
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
edf0507399
|
feat - allow accessing data post success call
|
2024-08-19 21:03:37 -07:00 |
|
|
Ishaan Jaff
|
1998809f18
|
feat run aporia as post call success hook
|
2024-08-19 21:03:37 -07:00 |
|
|
Krrish Dholakia
|
2aba1f17cc
|
feat(langfuse_endpoints.py): support team based logging for langfuse pass-through endpoints
|
2024-08-19 21:03:37 -07:00 |
|
|
Krrish Dholakia
|
c1a3d86fe4
|
feat(langfuse_endpoints.py): support langfuse pass through endpoints by default
|
2024-08-19 21:03:37 -07:00 |
|
|
Krrish Dholakia
|
b850edffc5
|
test(test_custom_callback.py): add test for message redaction to standard logging object
|
2024-08-19 21:03:37 -07:00 |
|
|
Krrish Dholakia
|
5bde7b0c70
|
fix(proxy_cli.py): support database_host, database_username, database_password, database_name
|
2024-08-19 21:03:37 -07:00 |
|
|
Krrish Dholakia
|
09fb4ce24d
|
docs: add docs on bedrock + cohere pass through endpoints
|
2024-08-19 21:03:37 -07:00 |
|
|
Krrish Dholakia
|
49416e121c
|
feat(azure.py): support dynamic api versions
Closes https://github.com/BerriAI/litellm/issues/5228
|
2024-08-19 12:17:43 -07:00 |
|
|
Krrish Dholakia
|
417547b6f9
|
fix(user_api_key_auth.py): log requester ip address to logs on request rejection
Closes https://github.com/BerriAI/litellm/issues/5220
|
2024-08-19 11:03:58 -07:00 |
|
|
Krrish Dholakia
|
3cafebbc65
|
test(test_caching.py): re-introduce testing for s3 cache w/ streaming
Closes https://github.com/BerriAI/litellm/issues/3268
|
2024-08-19 10:56:48 -07:00 |
|
|
Ishaan Jaff
|
601be5cb44
|
Merge pull request #5280 from lowjiansheng/js/litellm-help-0.2.3
Update helm repo to v0.2.3
|
2024-08-19 10:01:31 -07:00 |
|
|
lowjiansheng
|
f1c39510cb
|
add 0.2.3 helm
|
2024-08-19 23:59:58 +08:00 |
|
|
Krrish Dholakia
|
04d69464e2
|
fix(ollama.py): fix ollama embeddings - pass optional params
Fixes https://github.com/BerriAI/litellm/issues/5267
|
2024-08-19 08:45:26 -07:00 |
|
|
Krrish Dholakia
|
cc42f96d6a
|
fix(ollama_chat.py): fix sync tool calling
Fixes https://github.com/BerriAI/litellm/issues/5245
|
2024-08-19 08:31:46 -07:00 |
|
|
Krrish Dholakia
|
b8e4ef0abf
|
docs(json_mode.md): add azure openai models to doc
|
2024-08-19 07:19:23 -07:00 |
|
|
Ishaan Jaff
|
398295116f
|
inly write model tpm/rpm tracking when user set it
|
2024-08-18 09:58:09 -07:00 |
|
|
Krish Dholakia
|
f42ac2c9d8
|
Merge pull request #5264 from BerriAI/litellm_bedrock_pass_through
feat: Bedrock pass-through endpoint support (All endpoints)
|
2024-08-18 09:55:22 -07:00 |
|
|
Ishaan Jaff
|
69afb07dea
|
sleep before checi g
v1.43.18-stable
v1.43.18
|
2024-08-17 19:50:37 -07:00 |
|
|
Krrish Dholakia
|
663a0c1b83
|
feat(Support-pass-through-for-bedrock-endpoints): Allows pass-through support for bedrock endpoints
|
2024-08-17 17:57:43 -07:00 |
|
|
Ishaan Jaff
|
5adb7e29b9
|
fix test pass through
|
2024-08-17 17:42:51 -07:00 |
|
|
Ishaan Jaff
|
0bc67761dc
|
docs access groups
|
2024-08-17 17:38:28 -07:00 |
|
|
Ishaan Jaff
|
3cba235109
|
docs virtual key access groups
|
2024-08-17 17:37:23 -07:00 |
|
|
Ishaan Jaff
|
83515e88ce
|
Merge pull request #5263 from BerriAI/litellm_support_access_groups
[Feat-Proxy] Use model access groups for teams
|
2024-08-17 17:11:11 -07:00 |
|
|
Ishaan Jaff
|
6fee350938
|
feat add model access groups for teams
|
2024-08-17 17:10:10 -07:00 |
|
|
Krrish Dholakia
|
f7a2e04426
|
feat(pass_through_endpoints.py): add pass-through support for all cohere endpoints
|
2024-08-17 16:57:55 -07:00 |
|
|
Ishaan Jaff
|
9b239111f4
|
fix test update tpm / rpm limits for a key
|
2024-08-17 16:57:23 -07:00 |
|
|
Ishaan Jaff
|
08db691dec
|
use model access groups for teams
|
2024-08-17 16:45:53 -07:00 |
|
|
Ishaan Jaff
|
d9c91838ce
|
docs cleanup
|
2024-08-17 15:59:23 -07:00 |
|
|
Ishaan Jaff
|
eff874bf05
|
fix proxy all models test
|
2024-08-17 15:54:51 -07:00 |
|
|
Ishaan Jaff
|
78d30990a3
|
docs clean up virtual key access
|
2024-08-17 15:39:50 -07:00 |
|
|
Ishaan Jaff
|
2a18a65f9e
|
bump: version 1.43.17 → 1.43.18
|
2024-08-17 15:27:50 -07:00 |
|
|
Ishaan Jaff
|
b83fa87880
|
update tpm / rpm limit per model
|
2024-08-17 15:26:12 -07:00 |
|
|
Krrish Dholakia
|
db54b66457
|
style(vertex_httpx.py): make vertex error string more helpful
|
2024-08-17 15:09:55 -07:00 |
|
|
Ishaan Jaff
|
671663abe6
|
docs rate limits per model per api key
|
2024-08-17 14:50:17 -07:00 |
|
|
Krish Dholakia
|
be37310e94
|
Merge pull request #5232 from Penagwin/fix_anthropic_tool_streaming_index
Fixes the `tool_use` indexes not being correctly mapped
|
2024-08-17 14:33:50 -07:00 |
|
|
Ishaan Jaff
|
a60fc3ad70
|
Merge pull request #5261 from BerriAI/litellm_set_model_rpm_tpm_limit
[Feat-Proxy] set rpm/tpm limits per api key per model
|
2024-08-17 14:30:54 -07:00 |
|
|
Ishaan Jaff
|
653d2e6ce0
|
fix parallel request limiter tests
|
2024-08-17 14:21:59 -07:00 |
|
|
Ishaan Jaff
|
221e5b829b
|
fix parallel request limiter
|
2024-08-17 14:14:12 -07:00 |
|
|
Krish Dholakia
|
5731287f1b
|
Merge pull request #5221 from kiriloman/adjust-pricing-file
[PRICING] Use specific llama2 and llama3 model names in Ollama
|
2024-08-17 14:03:20 -07:00 |
|