phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
11040 commits 2497 branches 897 tags 550 MiB
Commit graph

32 commits

Author SHA1 Message Date
Krish Dholakia
fd06009199 Merge pull request #3455 from BerriAI/litellm_assistants_support 
feat(openai.py): add support for openai assistants
 2024-05-04 22:21:44 -07:00
Krrish Dholakia
138613616e fix(types/openai.py): fix python3.8 typing issue 2024-05-04 22:04:17 -07:00
Krrish Dholakia
0acd05a3d1 fix(typing/openai.py): fix openai typing error (version-related) 2024-05-04 22:02:43 -07:00
Krrish Dholakia
382000eb76 fix(types/openai.py): fix typing import 2024-05-04 21:53:08 -07:00
Krrish Dholakia
b0845d82cd fix(assistants/main.py): support litellm.create_thread() call 2024-05-04 19:35:37 -07:00
Ishaan Jaff
a72a6b0e9e Merge pull request #3456 from BerriAI/litellm_router_set_retry_policy_errors 
[FEAT] router set custom num retries for ContentPolicyViolationErrorRetries, RateLimitErrorRetries, BadRequestErrorRetries etc
 2024-05-04 18:26:03 -07:00
Ishaan Jaff
18f3de5a2d init router retry policy 2024-05-04 16:59:14 -07:00
Krish Dholakia
bc773aa052 Merge pull request #3448 from BerriAI/litellm_anthropic_fix 
fix(factory.py): support 'function' openai message role for anthropic
 2024-05-04 16:36:05 -07:00
Ishaan Jaff
1a96bbea64 Merge pull request #1530 from TanaroSch/main 
change max_tokens type to int
 2024-05-04 12:47:15 -07:00
Krrish Dholakia
d222dd8f82 fix(factory.py): support 'function' openai message role for anthropic 
Fixes https://github.com/BerriAI/litellm/issues/3446
 2024-05-04 10:03:30 -07:00
Krrish Dholakia
cfb6df4987 fix(main.py): support new 'supports_system_message=False' param 
Fixes https://github.com/BerriAI/litellm/issues/3325
 2024-05-03 21:31:45 -07:00
Krrish Dholakia
aca36d8b79 feat(proxy_server.py): return api base in response headers 
Closes https://github.com/BerriAI/litellm/issues/2631
 2024-05-03 15:27:32 -07:00
Krrish Dholakia
c39f8f3ef1 fix(lowest_tpm_rpm_v2.py): add more detail to 'No deployments available' error message 2024-04-29 15:04:37 -07:00
Krrish Dholakia
940ca0a4c1 fix(router.py): fix typing error 2024-04-29 07:25:39 -07:00
CyanideByte
a6c350e2bb protected_namespaces fixed for model_info 2024-04-27 13:08:45 -07:00
Krish Dholakia
26bacef87b Merge branch 'main' into litellm_default_router_retries 2024-04-27 11:21:57 -07:00
Krrish Dholakia
08e36547d6 fix(router.py): allow passing httpx.timeout to timeout param in router 
Closes https://github.com/BerriAI/litellm/issues/3162
 2024-04-26 14:57:19 -07:00
Krrish Dholakia
f1b2405fe0 fix(router.py): fix default retry logic 2024-04-25 11:57:27 -07:00
Krrish Dholakia
f4bd85a489 fix(proxy_server.py): fix /config/update/ 
allows updating router config via UI and having the change be propogated across all proxy instances by persisting config changes to the db
 2024-04-24 16:42:42 -07:00
Ishaan Jaff
5ff0bad6a4 feat - update deployments 2024-04-24 09:53:42 -07:00
Krrish Dholakia
7f5bcf38b7 feat(prometheus_services.py): emit proxy latency for successful llm api requests 
uses prometheus histogram for this
 2024-04-18 16:04:35 -07:00
Krrish Dholakia
c6ad02b167 fix(proxy_server.py): ensure id used in delete deployment matches id used in litellm Router 2024-04-16 15:17:18 -07:00
Krrish Dholakia
866259f95f feat(prometheus_services.py): monitor health of proxy adjacent services (redis / postgres / etc.) 2024-04-13 18:15:02 -07:00
Krrish Dholakia
c177407f7b test(test_openai_endpoints.py): add concurrency testing for user defined rate limits on proxy 2024-04-12 18:56:13 -07:00
Krrish Dholakia
f5206d592a fix(router.py): generate consistent model id's 
having the same id for a deployment, lets redis usage caching work across multiple instances
 2024-04-10 15:23:57 -07:00
unclecode
3a75c144dc Continue fixing the issue #2832: Add protected_namespaces to another to Config class within the router.py 2024-04-08 12:49:40 +08:00
unclecode
311e801ab4 Fix issue #2832: Add protected_namespaces to Config class within utils.py, router.py and completion.py to avoid the warning message. 2024-04-08 12:43:17 +08:00
Krrish Dholakia
fd67dc7556 fix(utils.py): fix import 2024-04-06 18:37:38 -07:00
TanaroSch
97d27e53db change max_tokens float to int 2024-02-06 11:19:28 +01:00
ishaan-jaff
2adcf8c762 (types) routerConfig 2024-01-02 14:14:29 +05:30
ishaan-jaff
2cbbfa72f1 (feat) add Router init Pydantic Type 2024-01-02 13:30:24 +05:30
ishaan-jaff
f7fc4da850 (feat) litellm add types for completion, embedding request 2024-01-02 12:27:08 +05:30