Commit graph

1355 commits

Author SHA1 Message Date
Vince Loewe
a9648613dc feat: LLMonitor is now Lunary 2024-02-27 22:07:13 -08:00
ishaan-jaff
7485fa797c (docs) vertex ai litellm proxy 2024-02-27 17:55:05 -08:00
ishaan-jaff
f3144dd9cf (docs) vertex ai 2024-02-27 17:44:35 -08:00
ishaan-jaff
8075746078 (docs) fix clickhouse link 2024-02-26 18:35:33 -08:00
ishaan-jaff
9bb55a0671 add clickhouse docs 2024-02-26 18:31:10 -08:00
ishaan-jaff
c627ce6631 (docs) use azure ai studio + mistral litellm 2024-02-26 14:33:21 -08:00
ishaan-jaff
da4832d5a2 (feat) add mistral-large-latest 2024-02-26 09:25:44 -08:00
Krrish Dholakia
577a0f9440 docs: add gemini-1.5 to docs 2024-02-26 08:01:30 -08:00
Krish Dholakia
61d69b1efa
Merge pull request #2183 from BerriAI/litellm_team_rate_limits
fix(proxy_server.py): allow user to set team tpm/rpm limits/budget/models
2024-02-25 01:12:39 -08:00
ishaan-jaff
7c19783d32 (docs) writing custo add 2024-02-24 18:54:46 -08:00
Ishaan Jaff
c8daf61592
Merge pull request #2188 from BerriAI/litellm_fix_health_checks
[Fix] Fix health check when API base set for OpenAI compatible models
2024-02-24 18:47:13 -08:00
ishaan-jaff
a4d2d1c4e6 (docs) using openai compatible endpoints 2024-02-24 18:46:20 -08:00
ishaan-jaff
bf403dc02e (docs) health 2024-02-24 18:38:39 -08:00
ishaan-jaff
986babfeaa (docs) open router 2024-02-24 18:30:41 -08:00
ishaan-jaff
7c032fcc05 (docs) open router 2024-02-24 18:28:32 -08:00
Krrish Dholakia
0b77420087 docs(users.md): add team budgets to docs 2024-02-24 11:41:42 -08:00
Krrish Dholakia
edaf20b60a docs(enterprise.md): add end user opt out to docs 2024-02-24 09:28:41 -08:00
Krrish Dholakia
308c73fca9 docs(contributing.md): add docs for contributing to litellm ui 2024-02-23 13:01:34 -08:00
ishaan-jaff
602b25972d (docs) add groq ai 2024-02-23 10:40:33 -08:00
Krrish Dholakia
44b8270bf6 docs(enterprise.md): add banned keywords to docs 2024-02-23 10:07:31 -08:00
ishaan-jaff
c2325539e7 (docs) fix athina docs 2024-02-23 09:56:10 -08:00
Ishaan Jaff
9594ceae55
Merge pull request #2164 from BerriAI/litellm_support_extra_headers
[FEAT] Support extra headers - OpenAI / Azure
2024-02-23 09:42:09 -08:00
Ishaan Jaff
5ec3075fb1
Merge pull request #2163 from vivek-athina/feature/athina
Support for Athina logging
2024-02-23 09:39:06 -08:00
ishaan-jaff
c9567c8652 (docs) passing extra_headers to OpenAI 2024-02-23 09:27:48 -08:00
Vivek Aditya
0d3046dcc9 added athina to logging doc 2024-02-23 22:33:09 +05:30
ishaan-jaff
aa9164e2ce (docs) setting extra_headers 2024-02-23 08:56:09 -08:00
Krrish Dholakia
d1a40ecacf docs(load_balancing.md): have proxy routing docs point to sdk routing docs 2024-02-23 08:34:15 -08:00
Vivek Aditya
244fa1c4ab Support for Athina logging 2024-02-23 21:49:40 +05:30
Krish Dholakia
e7cce90c3a
Merge pull request #2144 from BerriAI/litellm_blocked_user_list
feat(proxy_server.py): add support for blocked user lists (enterprise-only)
2024-02-22 21:34:07 -08:00
ishaan-jaff
21e1c2dc21 (docs) admin ui with proxy_base_url 2024-02-22 21:18:26 -08:00
ishaan-jaff
2122a7cf1e (docs) set user tpm/rpm limits 2024-02-22 19:23:16 -08:00
Krrish Dholakia
6ad450396b docs(enterprise.md): add Enable Blocked User Lists for docs 2024-02-22 18:04:29 -08:00
ishaan-jaff
b6886b8714 (docs) set hosted image for custom branding 2024-02-22 15:40:15 -08:00
ishaan-jaff
6a48fa64ce (docs) set generic user attributes 2024-02-22 14:25:07 -08:00
Ishaan Jaff
b603d9784d
Merge pull request #2129 from adrien-f/sso
update generic SSO login
2024-02-22 13:21:53 -08:00
ishaan-jaff
580f9e3097 (docs) setting cache paras on proxy + Openai client 2024-02-22 13:17:32 -08:00
ishaan-jaff
5c888853c7 (docs) litellm proxy server 2024-02-22 07:55:23 -08:00
Adrien Fillon
90f0062fc6
update generic SSO login
During implementation for Okta, noticed a few things:

- Some providers require a state parameter to be sent
- Some providers require that the client_id is not included in the body

Moreover, the OpenID response converter was not implemented which
was returning an empty response.

Finally, there was an order where there's a fetch of user information
but on first usage, it is not created yet.
2024-02-22 14:34:18 +01:00
ishaan-jaff
f04b67c433 (docs) custom ui branding 2024-02-21 22:07:40 -08:00
ishaan-jaff
7419547ba1 (docs) model max budgets 2024-02-20 21:11:17 -08:00
ishaan-jaff
2b2e62477b (docs) use correct base model for cost 2024-02-20 21:00:43 -08:00
Krrish Dholakia
987cb38976 docs(pii_masking.md): docs for ad-hoc recognizers for pii masking 2024-02-20 16:08:34 -08:00
Krrish Dholakia
1227964155 docs(enterprise.md): clarify what's in enterprise 2024-02-20 08:43:28 -08:00
Krrish Dholakia
fde478f70b docs(enterprise.md): add llm guard to docs 2024-02-19 21:05:01 -08:00
Krrish Dholakia
54e9b5b99a docs(enterprise.md): add customizing llama guard prompt to docs 2024-02-19 15:22:09 -08:00
Krrish Dholakia
7348956bf2 docs(enterprise.md): add google text moderations to the docs 2024-02-19 14:17:52 -08:00
Krish Dholakia
6f77a4a31e
Merge pull request #2037 from BerriAI/litellm_request_level_pii_masking
feat(presidio_pii_masking.py): allow request level controls for turning on/off pii masking
2024-02-17 19:05:14 -08:00
Krrish Dholakia
045d84e167 fix(proxy_cli.py): allow user to control db connection pool + timeouts from config 2024-02-17 19:03:43 -08:00
Krish Dholakia
ad81e19282
Merge pull request #2013 from afbarbaro/litellm_gemini_safety_settings
Add safety_settings parameter to gemini generate_content calls
2024-02-17 16:47:29 -08:00
Ishaan Jaff
35af2d666b
Merge pull request #2022 from BerriAI/litellm_budgets_per_llm
[FEAT] Track spend per model (for Key, User and Team)
2024-02-17 15:35:31 -08:00