Commit graph

9045 commits

Author SHA1 Message Date
Krrish Dholakia
9e1e97528d fix(utils.py): ensure last chunk is always empty delta w/ finish reason
makes sure we're openai-compatible with our streaming. Adds stricter tests for this as well
2024-03-25 16:33:41 -07:00
Krrish Dholakia
f153889738 fix(utils.py): allow user to disable streaming logging
fixes event loop issue for litellm.disable_streaming_logging
2024-03-25 14:28:46 -07:00
Krrish Dholakia
16ade7e556 docs(proxy/caching.md): add ttl param to proxy/caching.md 2024-03-25 13:46:52 -07:00
Krrish Dholakia
591a0a376e fix(caching.py): support default ttl for caching 2024-03-25 13:40:17 -07:00
Krrish Dholakia
e1c75c009f bump: version 1.34.1 → 1.34.2 2024-03-25 13:28:25 -07:00
Krish Dholakia
f15ba10170
Merge pull request #2687 from BerriAI/litellm_jwt_auth_fixes_2
Litellm jwt auth fixes
2024-03-25 13:27:19 -07:00
Krrish Dholakia
2e4e97a48f test(test_jwt.py): add unit tests for jwt auth integration 2024-03-25 13:24:39 -07:00
Krrish Dholakia
03b8444d3c docs(token_auth.md): add renaming jwt scope string to docs 2024-03-25 12:49:44 -07:00
Krish Dholakia
e5be002adc
Merge pull request #2660 from dragosMC91/fix-pip-install-extra-proxy
Fix pip install 'litellm[extra_proxy]'
2024-03-25 12:42:13 -07:00
Krrish Dholakia
c2ffb83c71 fix(handle_jwt.py): cache public keys
caches jwt public keys - reducing need for making http calls on every request
2024-03-25 12:36:32 -07:00
Ishaan Jaff
71c3484b93
Merge pull request #2683 from BerriAI/litellm_f_string
(feat) Perf Improvement - stop eagerly evaluating fstring
2024-03-25 12:35:30 -07:00
Krrish Dholakia
f1b1640a31 fix(handle_jwt.py): support scopes being a list
allow scopes in jwt to be a list, not just a space-separated string
2024-03-25 12:30:40 -07:00
Krrish Dholakia
5aa1c10929 fix(handle_jwt.py): don't require kid to be set 2024-03-25 12:28:16 -07:00
Krrish Dholakia
93959ab5aa fix(handle_jwt.py): allow setting proxy admin role string for jwt auth 2024-03-25 12:20:14 -07:00
Krrish Dholakia
edd00af6f2 fix(handle_jwt.py): enable user to set jwt admin scope string in config 2024-03-25 11:34:49 -07:00
Dragos Campean
4549a20333 Merge remote-tracking branch 'upstream/main' into fix-pip-install-extra-proxy 2024-03-25 20:22:17 +02:00
Ishaan Jaff
734a51c049 (fix) stop using f strings in verbose logger 2024-03-25 10:55:30 -07:00
Krish Dholakia
123e012dc0
Merge pull request #2672 from RoniGurvich/main
`cryptography` and `python-multipart` version bump
2024-03-25 10:54:43 -07:00
Krish Dholakia
0804d74d13
Merge pull request #2685 from maxdeichmann/log-langfuse-instantiation
add langfuse logging
2024-03-25 10:48:16 -07:00
Ishaan Jaff
5d121a9f3c (fix) stop using f strings with logger 2024-03-25 10:47:18 -07:00
Max Deichmann
efb43ccd02 push 2024-03-25 17:43:55 +01:00
Ishaan Jaff
dad4bd58bc (feat) stop eagerly evaluating fstring 2024-03-25 09:01:42 -07:00
Krrish Dholakia
85ee29ade2 bump: version 1.34.0 → 1.34.1 2024-03-25 08:37:01 -07:00
Krrish Dholakia
53695943e3 docs(instructor.md): tutorial on using litellm with instructor 2024-03-25 08:35:11 -07:00
Krrish Dholakia
f98aead602 feat(main.py): support router.chat.completions.create
allows using router with instructor

https://github.com/BerriAI/litellm/issues/2673
2024-03-25 08:26:28 -07:00
Krrish Dholakia
9e9de7f6e2 docs(routing.md): add fallbacks being done in order 2024-03-24 12:13:19 -07:00
Roni Gurvich
384882115e cryptography and python-multipart version bump 2024-03-24 08:49:36 +00:00
Roni Gurvich
644632ba3b cryptography and python-multipart version bump 2024-03-24 08:44:36 +00:00
Dragos Campean
4c2274125e Merge remote-tracking branch 'upstream/main' into fix-pip-install-extra-proxy 2024-03-24 08:53:54 +02:00
Dragos Campean
c807a21442 Remove dependency which was removed on main 2024-03-24 08:53:43 +02:00
Krrish Dholakia
63f6a9deff bump: version 1.33.9 → 1.34.0 2024-03-23 22:35:18 -07:00
Krrish Dholakia
1c60fd0e78 docs(routing.md): add url 2024-03-23 20:03:42 -07:00
Krrish Dholakia
7c74ea8b77 docs(routing.md): add proxy example to pre-call checks in routing docs 2024-03-23 20:00:50 -07:00
Krish Dholakia
8f966cd78f
Merge pull request #2666 from BerriAI/litellm_model_fix_v_3
fix(proxy_server.py): fix model info check
2024-03-23 19:39:03 -07:00
Ishaan Jaff
92759ef055
Merge pull request #2670 from BerriAI/litellm_docs_best_practices_prod
(docs) best prod practices
2024-03-23 19:38:22 -07:00
Krish Dholakia
c92fa1af7c
Merge pull request #2669 from BerriAI/litellm_router_pre_call_checks
feat(router.py): enable pre-call checks
2024-03-23 19:38:09 -07:00
Ishaan Jaff
09992a6122 (docs) prod best perf 2024-03-23 19:36:26 -07:00
Ishaan Jaff
d04b4dea3e (docs) best prod practices 2024-03-23 19:29:21 -07:00
Krrish Dholakia
e8e7964025 docs(routing.md): add pre-call checks to docs 2024-03-23 19:10:34 -07:00
Krrish Dholakia
b7321ae4ee fix(router.py): fix pre call check logic 2024-03-23 18:56:08 -07:00
Ishaan Jaff
2ae489c506 (docs) update config set_verbose 2024-03-23 18:54:31 -07:00
Ishaan Jaff
04a09830de
Merge pull request #2668 from BerriAI/litellm_update_deploy_docs
[Docs] Add Docs on deploying to EKS Cluster + K8
2024-03-23 18:42:36 -07:00
Krrish Dholakia
9f83cf95c6 bump: version 1.33.8 → 1.33.9 2024-03-23 18:26:52 -07:00
Krrish Dholakia
eb3ca85d7e feat(router.py): enable pre-call checks
filter models outside of context window limits of a given message for a model group

 https://github.com/BerriAI/litellm/issues/872
2024-03-23 18:03:30 -07:00
Ishaan Jaff
925e785a6a (fix) update locustfile 2024-03-23 17:59:54 -07:00
Ishaan Jaff
0c17fe9a32 (feat) update config.yaml 2024-03-23 17:59:16 -07:00
Ishaan Jaff
b0c75d405c (feat) update kub.yaml 2024-03-23 17:58:39 -07:00
Ishaan Jaff
30ae52c21e (docs) using litellm on EKS 2024-03-23 17:49:00 -07:00
Ishaan Jaff
f646a4612b
Merge pull request #2667 from BerriAI/litellm_update_gunicorn_instructions
[Docs] update gunicorn instructions - Uvicorn perf is significantly better on K8s
2024-03-23 17:43:09 -07:00
Ishaan Jaff
19a1d999ec (feat) update docs to not include gunicorn usage 2024-03-23 17:40:22 -07:00