 Ishaan Jaff
|
129c2e0c4f
|
init guardrails on proxy
|
2024-07-03 14:18:12 -07:00 |
|
|
Ishaan Jaff
|
a2b6baab16
|
add new GuardrailItem type
|
2024-07-03 14:03:34 -07:00 |
|
|
Ishaan Jaff
|
50443d3d48
|
fix checks on litellm license
|
2024-07-03 14:02:07 -07:00 |
|
|
Krish DholakiaandGitHub
|
2116dbcdc1
|
Merge pull request #4089 from paneru-rajan/ollama-func-calls
Fix: Output Structure of Ollama chat
|
2024-07-03 08:57:31 -07:00 |
|
|
Krrish Dholakia
|
67433a04a2
|
test: fix test
v1.41.4
|
2024-07-02 22:13:41 -07:00 |
|
|
Ishaan Jaff
|
3da8ce6a75
|
ci/cd run again
|
2024-07-02 18:39:53 -07:00 |
|
|
Krrish Dholakia
|
ac00639301
|
fix(azure.py): fix httpx call for dall e 3
|
2024-07-02 18:30:21 -07:00 |
|
|
Ishaan Jaff
|
540db53ccb
|
docs switch guardrails on / off
|
2024-07-02 18:13:36 -07:00 |
|
|
Ishaan Jaff
|
b288835b47
|
doc secret detection
|
2024-07-02 18:10:41 -07:00 |
|
|
Ishaan Jaff
|
c30061fd09
|
bump: version 1.41.3 → 1.41.4
|
2024-07-02 18:03:04 -07:00 |
|
|
Ishaan JaffandGitHub
|
2dcf06ce7d
|
Merge pull request #4525 from BerriAI/litellm_control_lakera_per_llm_call
[Feat] Control Lakera AI per Request
|
2024-07-02 18:02:43 -07:00 |
|
|
Ishaan JaffandGitHub
|
0d852d7011
|
Merge pull request #4524 from BerriAI/litellm_allow_controlling_guardrails_per_key
[Enterprise] Check if Key should run secret_detection callback
|
2024-07-02 18:02:34 -07:00 |
|
|
Ishaan Jaff
|
62ebcc0bb5
|
doc controlling guardrail per api key
|
2024-07-02 18:01:21 -07:00 |
|
|
Krish DholakiaandGitHub
|
2d6b6662d4
|
Merge pull request #4502 from BerriAI/litellm_support_dynamic_rpm_limiting
feat(dynamic_rate_limiter.py): support dynamic rate limiting on rpm
|
2024-07-02 17:51:23 -07:00 |
|
|
Krish DholakiaandGitHub
|
21d3a28e51
|
Merge branch 'main' into litellm_support_dynamic_rpm_limiting
|
2024-07-02 17:51:18 -07:00 |
|
|
Ishaan Jaff
|
23f8d23acb
|
correct guardrail name
|
2024-07-02 17:50:23 -07:00 |
|
|
Ishaan Jaff
|
11d1f4e430
|
doc - control guradrail per api key
|
2024-07-02 17:50:09 -07:00 |
|
|
Ishaan Jaff
|
f61eb8dfa1
|
docs control lakera ai per request
|
2024-07-02 17:38:07 -07:00 |
|
|
Ishaan Jaff
|
64e86c3305
|
docs control lakera ai per call
|
2024-07-02 17:34:48 -07:00 |
|
|
Ishaan Jaff
|
b6af67344c
|
feat - control lakera per call
|
2024-07-02 17:34:05 -07:00 |
|
|
Krish DholakiaandGitHub
|
f87535140c
|
Merge pull request #4523 from BerriAI/litellm_azure_img_gen_refactor
refactor(azure.py): move azure dall-e calls to httpx client
|
2024-07-02 17:15:41 -07:00 |
|
|
Krrish Dholakia
|
cf5334fe8a
|
refactor(azure.py): refactor sync azure calls to httpx
|
2024-07-02 17:06:48 -07:00 |
|
|
Ishaan Jaff
|
9f8572e427
|
check if key does not want secret detection to run
|
2024-07-02 17:05:53 -07:00 |
|
|
Ishaan JaffandGitHub
|
174b2b69df
|
Merge pull request #4518 from BerriAI/litellm_fix_background_health_checks
[Fix-Proxy] Background health checks use deep copy of model list for _run_background_health_check
|
2024-07-02 16:42:34 -07:00 |
|
|
Ishaan JaffandGitHub
|
90a0db5618
|
Merge pull request #4519 from BerriAI/litellm_re_use_openai_azure_clients_whisper
[Fix+Test] /audio/transcriptions - use initialized OpenAI / Azure OpenAI clients
|
2024-07-02 16:42:22 -07:00 |
|
|
Krrish Dholakia
|
589c1c6280
|
refactor(azure.py): replaces the custom transport logic for just using our httpx client
Done to fix all the http/https proxy issues people are facing with proxy.
|
2024-07-02 15:32:53 -07:00 |
|
|
Krish DholakiaandGitHub
|
612af8f5be
|
Merge pull request #4492 from Manouchehri/gemini-context-caching-1
feat(vertex_httpx.py): Support cachedContent.
|
2024-07-02 14:09:25 -07:00 |
|
|
Krish DholakiaandGitHub
|
c4e11e03d7
|
Merge pull request #4520 from BerriAI/litellm_fix_request_hanging_alert
fix(slack_alerting.py): use in-memory cache for checking request status
|
2024-07-02 13:48:19 -07:00 |
|
|
Krrish Dholakia
|
66c6992f8a
|
fix(slack_alerting.py): use in-memory cache for checking request status
|
2024-07-02 13:01:59 -07:00 |
|
|
Ishaan Jaff
|
ce7fade15e
|
test whisper re-using openai/azure clients
|
2024-07-02 12:35:15 -07:00 |
|
|
Ishaan Jaff
|
2b5f3c6105
|
fix use router level client for OpenAI / Azure transcription calls
|
2024-07-02 12:33:31 -07:00 |
|
|
Krrish Dholakia
|
3d3f725ef5
|
docs(user_keys.md): add langchain js example to docs
|
2024-07-02 12:06:48 -07:00 |
|
|
Ishaan Jaff
|
cd6b121642
|
use deep copy of router for _run_background_health_check
|
2024-07-02 11:29:24 -07:00 |
|
|
Krrish Dholakia
|
79670ab82e
|
fix(main.py): get the region name from boto3 client if dynamic var not set
|
2024-07-02 09:24:07 -07:00 |
|
|
Krrish Dholakia
|
5aae2313f3
|
fix(aws_secret_manager.py): fix string replace
v1.41.3.dev2
|
2024-07-02 00:42:12 -07:00 |
|
|
Krrish Dholakia
|
196b94455e
|
fix(dynamic_rate_limiter.py): add rpm allocation, priority + quota reservation to docs
|
2024-07-01 23:35:42 -07:00 |
|
|
Krish DholakiaandGitHub
|
4ab83f0f46
|
Merge pull request #4497 from BerriAI/litellm_disable_cooldowns
fix(router.py): disable cooldowns
|
2024-07-01 23:10:18 -07:00 |
|
|
Krish DholakiaandGitHub
|
011e14eb08
|
Merge branch 'main' into litellm_disable_cooldowns
|
2024-07-01 23:10:10 -07:00 |
|
|
Krrish Dholakia
|
6b529d4e0e
|
fix(dynamic_rate_limiter.py): support setting priority + reserving tpm/rpm
|
2024-07-01 23:08:54 -07:00 |
|
|
Ishaan Jaff
|
38770da2f6
|
docs prometheus tracking x-remaining tokens
|
2024-07-01 22:45:33 -07:00 |
|
|
Ishaan Jaff
|
5f04ef14a6
|
doc prometheus tracking
|
2024-07-01 22:41:52 -07:00 |
|
|
Ishaan Jaff
|
e2a2c2bde1
|
ci/cd run again
v1.41.3
|
2024-07-01 21:36:30 -07:00 |
|
|
Ishaan Jaff
|
4cb098661a
|
bump: version 1.41.2 → 1.41.3
|
2024-07-01 21:35:52 -07:00 |
|
|
Ishaan JaffandGitHub
|
4bb418acf3
|
Merge pull request #4504 from BerriAI/litellm_fix_exception_provider_not_known
fix exception provider not known
|
2024-07-01 21:22:20 -07:00 |
|
|
Ishaan Jaff
|
665d8fb250
|
test - test_azure_embedding_exceptions
|
2024-07-01 21:19:47 -07:00 |
|
|
Ishaan JaffandGitHub
|
402799c8db
|
Merge pull request #4503 from BerriAI/litellm_log_remaining_rate_limit_prometheus
[Feat-Enterprise] log `"x-ratelimit-remaining-tokens"` and `"x-ratelimit-remaining-requests"` on prometheus
|
2024-07-01 21:11:42 -07:00 |
|
|
Ishaan JaffandGitHub
|
1c194f0275
|
Merge pull request #4501 from BerriAI/litellm_return_Response_headers
[Feat] Return Response headers for OpenAI / Azure OpenAI when `litellm.return_response_headers=True`
|
2024-07-01 21:11:10 -07:00 |
|
|
Ishaan Jaff
|
fcf65d5215
|
fix exception provider not known
|
2024-07-01 21:05:37 -07:00 |
|
|
Ishaan Jaff
|
4033302656
|
feat - return headers for openai audio transcriptions
|
2024-07-01 20:27:27 -07:00 |
|
|
Krrish Dholakia
|
460c33f70f
|
test(test_dynamic_rate_limit_handler.py): add unit tests for dynamic rpm limits
|
2024-07-01 20:20:24 -07:00 |
|