Lunik
|
21552620ed
|
📝 Clarify GENERIC_SCOPE usage
Signed-off-by: Lunik <lunik@tiwabbit.fr>
|
2024-02-16 23:40:59 +01:00 |
|
ishaan-jaff
|
5857b02bfc
|
(feat) generic sso, set generic_user_id_attribute_name
|
2024-02-16 14:40:27 -08:00 |
|
Lunik
|
af4537e421
|
✨ Allow to configure scopes in generic SSO
Signed-off-by: Lunik <lunik@tiwabbit.fr>
|
2024-02-16 23:24:58 +01:00 |
|
Ishaan Jaff
|
a137680895
|
Update README.md
|
2024-02-16 14:17:24 -08:00 |
|
Ishaan Jaff
|
d46ff8aa40
|
Update README.md
|
2024-02-16 14:15:53 -08:00 |
|
Ishaan Jaff
|
b91f1786c0
|
Merge pull request #2019 from BerriAI/litellm_use_litellm_ghcr_as_base_image
[Docs] Show how to use litellm GHCR as a base image
|
2024-02-16 14:06:58 -08:00 |
|
ishaan-jaff
|
6e1708f595
|
(docs) use litellm ghcr as base image
|
2024-02-16 14:02:46 -08:00 |
|
ishaan-jaff
|
8d3897592e
|
(fix) docker compose
|
2024-02-16 14:01:27 -08:00 |
|
Lunik
|
880213d4a6
|
✨ Refresh Helm chart structure
Signed-off-by: Lunik <lunik@tiwabbit.fr>
|
2024-02-16 22:59:14 +01:00 |
|
Krrish Dholakia
|
5f9e141d1e
|
fix(huggingface_restapi.py): return streamed response correctly
|
2024-02-16 13:25:13 -08:00 |
|
Krrish Dholakia
|
86886de9d8
|
test(test_completion.py): handle azure gpt-4 vision internal error
|
2024-02-16 13:16:46 -08:00 |
|
Ishaan Jaff
|
900ebb6871
|
Merge pull request #2012 from BerriAI/litellm_view_spend_per_tag
[FEAT] View spend per tag
|
2024-02-16 13:08:03 -08:00 |
|
Alexandre Sorokine
|
3c919cbbe7
|
fix for importllib compatibility issue for python 3.8
was tested for python versions 3.8, 3.9, 3.10, 3.11, 3.12
|
2024-02-16 15:52:39 -05:00 |
|
Krrish Dholakia
|
cab8a3c2f5
|
bump: version 1.24.4 → 1.24.5
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
0d54887149
|
test(test_amazing_vertex_completion.py): handle rate limit errors
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
01077b20b9
|
fix(proxy_server.py): restrict model access for /v1/completions endpoint
|
2024-02-16 11:54:12 -08:00 |
|
ishaan-jaff
|
936e460a30
|
(chore) fix spend tracking request tags
|
2024-02-16 11:54:12 -08:00 |
|
ishaan-jaff
|
02a5c105ac
|
(docs) view spend per tag
|
2024-02-16 11:54:12 -08:00 |
|
Toni Engelhardt
|
4067082f47
|
Update NLP Cloud max_tokens
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
b3d48da640
|
fix(main.py): map list input to ollama prompt input format
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
3fffe96f97
|
refactor(test_team.py): trigger new devrelease
|
2024-02-16 11:54:12 -08:00 |
|
Toni Engelhardt
|
51dc3c64df
|
Update NLP Cloude model pricing
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
21d493d3f2
|
bump: version 1.24.3 → 1.24.4
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
9267361683
|
test(test_team.py): trigger new build
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
08ce7a08d3
|
test(test_team.py): adding testing for team endpoints
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
e9b27d9811
|
fix(proxy_server.py): re-add /team/info endpoint (fixing merge issue)
|
2024-02-16 11:54:12 -08:00 |
|
Krrish Dholakia
|
b96330c5dd
|
bump: version 1.24.4 → 1.24.5
|
2024-02-16 11:52:59 -08:00 |
|
Krrish Dholakia
|
8f55e86527
|
test(test_amazing_vertex_completion.py): handle rate limit errors
|
2024-02-16 11:51:41 -08:00 |
|
Krrish Dholakia
|
d97369dcbe
|
fix(proxy_server.py): restrict model access for /v1/completions endpoint
|
2024-02-16 11:50:07 -08:00 |
|
Ishaan Jaff
|
691542ddf0
|
Merge pull request #2004 from BerriAI/litellm_track_spend_per_tag
[FEAT] Track spend per tag
|
2024-02-16 10:55:02 -08:00 |
|
ishaan-jaff
|
55bd08847c
|
(chore) fix spend tracking request tags
|
2024-02-16 10:53:33 -08:00 |
|
ishaan-jaff
|
d574bfc297
|
(docs) view spend per tag
|
2024-02-16 10:47:33 -08:00 |
|
Andres Barbaro
|
1f054203bf
|
Add safety_settings parameter to gemini generate_content calls
|
2024-02-16 12:22:18 -06:00 |
|
ishaan-jaff
|
138f5ceb1e
|
(feat) view spend per tag
|
2024-02-16 10:16:48 -08:00 |
|
Krish Dholakia
|
65e1d5a9e7
|
Merge pull request #2009 from promptmetheus/update-nlpcloud-tokenlimit
Update NLP Cloud max_tokens
|
2024-02-16 10:13:43 -08:00 |
|
Toni Engelhardt
|
db58a2412d
|
Update NLP Cloud max_tokens
|
2024-02-16 18:04:37 +00:00 |
|
Krrish Dholakia
|
944afcb5d1
|
fix(main.py): map list input to ollama prompt input format
|
2024-02-16 09:57:51 -08:00 |
|
Krrish Dholakia
|
dca9103b09
|
refactor(test_team.py): trigger new devrelease
|
2024-02-16 09:57:51 -08:00 |
|
Krish Dholakia
|
563a0436ef
|
Merge pull request #2007 from promptmetheus/update-nlpcloud-pricing
chore: update NLP Cloud model pricing
|
2024-02-16 09:55:43 -08:00 |
|
ishaan-jaff
|
23589a398a
|
(feat) log request_tags in SpendLogs
|
2024-02-16 09:52:25 -08:00 |
|
Toni Engelhardt
|
5430163094
|
Update NLP Cloude model pricing
|
2024-02-16 17:42:19 +00:00 |
|
Krrish Dholakia
|
63731abee4
|
bump: version 1.24.3 → 1.24.4
|
2024-02-16 08:56:13 -08:00 |
|
Krrish Dholakia
|
faa7892b4c
|
test(test_team.py): trigger new build
|
2024-02-16 08:56:08 -08:00 |
|
Krrish Dholakia
|
3af2fb25be
|
test(test_team.py): adding testing for team endpoints
|
2024-02-16 08:55:21 -08:00 |
|
ishaan-jaff
|
097b46d948
|
(feat) view spend per tag
|
2024-02-16 08:51:23 -08:00 |
|
Krrish Dholakia
|
8640989a80
|
fix(proxy_server.py): re-add /team/info endpoint (fixing merge issue)
|
2024-02-16 08:49:37 -08:00 |
|
Krrish Dholakia
|
a938b296a3
|
docs(pii_masking.md): allow keys to turn off pii masking
|
2024-02-16 00:04:24 -08:00 |
|
Krish Dholakia
|
70146c1d37
|
Merge pull request #1995 from BerriAI/litellm_langfuse_prompts
feat(langfuse.py): support langfuse prompt management
|
2024-02-15 23:57:00 -08:00 |
|
Krish Dholakia
|
b96c0e5ec4
|
Merge pull request #1991 from BerriAI/litellm_moderations_improvements
feat(proxy_server.py): support key-level permissions for pii masking
|
2024-02-15 23:08:33 -08:00 |
|
Krish Dholakia
|
999fab82f7
|
Merge branch 'main' into litellm_moderations_improvements
|
2024-02-15 23:08:25 -08:00 |
|