Krrish Dholakia
|
9aa05c19d1
|
fix(bedrock_httpx.py): fix bedrock logging
|
2024-05-16 23:53:54 -07:00 |
|
Krrish Dholakia
|
0258351c61
|
fix(main.py): fix async stream handling during bedrock error
|
2024-05-16 23:37:59 -07:00 |
|
Krrish Dholakia
|
21f2ba6f1f
|
fix(bedrock_httpx.py): logging fixes
|
2024-05-16 23:20:51 -07:00 |
|
Krrish Dholakia
|
92c2e2af6a
|
fix(bedrock_httpx.py): add async support for bedrock amazon, meta, mistral models
|
2024-05-16 22:39:25 -07:00 |
|
Krrish Dholakia
|
0293f7766a
|
fix(bedrock_httpx.py): move bedrock ai21 calls to being async
|
2024-05-16 22:21:30 -07:00 |
|
Krrish Dholakia
|
180bc46ca4
|
fix(bedrock_httpx.py): move anthropic bedrock calls to httpx
Fixing https://github.com/BerriAI/litellm/issues/2921
|
2024-05-16 21:51:55 -07:00 |
|
Krrish Dholakia
|
10a672634d
|
fix(proxy_server.py): fix invalid header string
v1.37.13
|
2024-05-16 21:05:40 -07:00 |
|
Ishaan Jaff
|
ee98074273
|
ci/cd run again
|
2024-05-16 18:35:43 -07:00 |
|
Ishaan Jaff
|
729e34ffea
|
(ci/cd) fix - assert len(completed_str)
|
2024-05-16 18:06:48 -07:00 |
|
Krrish Dholakia
|
c5f0918682
|
docs(billing.md): update billing tutorial to show how to bill internal teams
|
2024-05-16 17:49:06 -07:00 |
|
 Ishaan JaffandGitHub
|
fdc9690537
|
Merge pull request #3706 from Manouchehri/fix-azure-openai-3695
Fix(router.py): Kill a bug that forced Azure OpenAI to have an API ke…
|
2024-05-16 17:44:48 -07:00 |
|
 Krish DholakiaandGitHub
|
7502e15295
|
Merge pull request #3701 from paneru-rajan/Issue-3675-remove-empty-valued-header
Exclude custom headers from response if the value is None or empty string
|
2024-05-16 17:42:07 -07:00 |
|
David Manouchehri
|
50accc327c
|
Fix(router.py): Kill a bug that forced Azure OpenAI to have an API key, even though we can use OIDC instead.
|
2024-05-17 00:37:56 +00:00 |
|
 Ishaan JaffandGitHub
|
4952e244d9
|
Merge pull request #3705 from BerriAI/litellm_add_cost_tracking_for_ft_models
[FEAT] add cost tracking for Fine Tuned OpenAI `ft:davinci-002` and `ft:babbage-002`
|
2024-05-16 17:37:35 -07:00 |
|
Rajan Paneru
|
e4ce10038a
|
use default empty str if the allowed_model_region attribute is not present
|
2024-05-17 10:05:18 +09:30 |
|
Ishaan Jaff
|
28ae8284df
|
fix add cost tracking for OpenAI ft models
|
2024-05-16 17:31:19 -07:00 |
|
 Krish DholakiaandGitHub
|
f68eb6f74e
|
Merge pull request #3704 from BerriAI/litellm_replicate_async_fxi
fix(replicate.py): move replicate calls to being async
|
2024-05-16 17:27:12 -07:00 |
|
Rajan Paneru
|
54f8d06057
|
handle exception and logged it
|
2024-05-17 09:55:13 +09:30 |
|
Ishaan Jaff
|
7b60fae6f9
|
feat - add cost tracking for OpenAI Fine tuned models
|
2024-05-16 17:24:15 -07:00 |
|
Krrish Dholakia
|
709373b15c
|
fix(replicate.py): move replicate calls to being completely async
Closes https://github.com/BerriAI/litellm/issues/3128
|
2024-05-16 17:24:08 -07:00 |
|
Ishaan Jaff
|
40bb675156
|
bump: version 1.37.12 → 1.37.13
|
2024-05-16 17:08:47 -07:00 |
|
Ishaan Jaff
|
bd63af395f
|
ui - new build
|
2024-05-16 17:08:36 -07:00 |
|
 Ishaan JaffandGitHub
|
a2ac6a672e
|
Merge pull request #3702 from BerriAI/litellm_separate_slack_alerts_channel
[Fix] allow users to opt into specific alert types + Introduce `spend_report` alert type
|
2024-05-16 17:05:36 -07:00 |
|
Ishaan Jaff
|
7d4f2aaca3
|
docs - alerting
|
2024-05-16 16:59:01 -07:00 |
|
Ishaan Jaff
|
53ae4654c4
|
docs - setting alert types
|
2024-05-16 16:57:54 -07:00 |
|
Ishaan Jaff
|
a292583ff1
|
fix - allow users to opt into specific alert types
|
2024-05-16 16:52:44 -07:00 |
|
Rajan Paneru
|
85679470c2
|
Exclude custom headers from response if the value is None or empty string
This will return clean header, sending a header with empty value is not standard which
is being avoided from this fix.
|
2024-05-17 09:06:58 +09:30 |
|
 Ishaan JaffandGitHub
|
f3d340bd3a
|
Merge pull request #3700 from BerriAI/litellm_ui_round_team_spend
[UI] Fix Round Team Spend, and Show Key Alias on Top API Keys
|
2024-05-16 16:30:33 -07:00 |
|
Ishaan Jaff
|
20dc9e74af
|
ui - show key alias on Top Keys instead of key_name
|
2024-05-16 16:27:35 -07:00 |
|
Krrish Dholakia
|
a2a5884df1
|
fix(utils.py): allow passing in custom pricing to completion_cost as params
|
2024-05-16 16:24:44 -07:00 |
|
Ishaan Jaff
|
57d1efec1b
|
fix round team spend to 2 decimals
|
2024-05-16 16:21:21 -07:00 |
|
 Ishaan JaffandGitHub
|
a0c5c402ae
|
Merge pull request #3698 from BerriAI/litellm_ui_fix_bug_default_selected_model
[Fix] Polish Models Page - set max width per column, fix bug with selecting models
|
2024-05-16 16:13:01 -07:00 |
|
Ishaan Jaff
|
a65c1f8340
|
fix models page
|
2024-05-16 16:10:53 -07:00 |
|
 Ishaan JaffandGitHub
|
907ee2acbd
|
Merge pull request #3699 from msabramo/msabramo/add_commented_out_set_verbose_line_to_proxy_server_config
Add commented `set_verbose` line to proxy_config
|
2024-05-16 16:08:28 -07:00 |
|
Marc Abramowitz
|
83c242bbb3
|
Add commented set_verbose line to proxy_config
because I've wanted to do this a couple of times and couldn't remember
the exact syntax.
|
2024-05-16 15:59:37 -07:00 |
|
 Ishaan JaffandGitHub
|
b170259a88
|
Merge pull request #3696 from BerriAI/litellm_ui_clean_up_models_page
[Feat] Admin UI - show model prices as Per 1M tokens
|
2024-05-16 15:48:37 -07:00 |
|
 Ishaan JaffandGitHub
|
97324800ec
|
Merge pull request #3694 from BerriAI/litellm_allow_setting_anthropic_beta
[Feat] Support Anthropic `tools-2024-05-16` - Set Custom Anthropic Custom Headers
|
2024-05-16 15:48:26 -07:00 |
|
Krrish Dholakia
|
bc23365acc
|
fix(utils.py): update completion_cost docstring
|
2024-05-16 15:47:40 -07:00 |
|
Krrish Dholakia
|
ce4dffb7cb
|
fix(utils.py): fix logging level of error message
|
2024-05-16 15:44:08 -07:00 |
|
 Krish DholakiaandGitHub
|
acf95e978d
|
Merge pull request #3575 from BerriAI/litellm_end_user_obj
fix(proxy_server.py): check + get end-user obj even for master key calls
|
2024-05-16 15:34:06 -07:00 |
|
Ishaan Jaff
|
a1eff57ded
|
ui - fix bug with defaul selected model
|
2024-05-16 15:31:27 -07:00 |
|
Krrish Dholakia
|
b696d47442
|
docs(billing.md): update lago screenshot
|
2024-05-16 15:30:33 -07:00 |
|
Krrish Dholakia
|
53ddc9fdbe
|
docs(billing.md): improve proxy billing tutorial
|
2024-05-16 15:27:23 -07:00 |
|
Ishaan Jaff
|
1dabf424f3
|
ui - show model prices as /1M tokens
|
2024-05-16 15:10:39 -07:00 |
|
Krrish Dholakia
|
48714805bd
|
fix(proxy_server.py): fix code
|
2024-05-16 15:02:39 -07:00 |
|
Ishaan Jaff
|
aa0863dd76
|
docs - Setting anthropic-beta Header in Requests
|
2024-05-16 14:55:29 -07:00 |
|
Ishaan Jaff
|
e19e475c9f
|
test - setting extra headers for anthropic tool use
|
2024-05-16 14:41:26 -07:00 |
|
Ishaan Jaff
|
23bcd03904
|
feat: Anthropic allow users to set anthropic-beta in headers
|
2024-05-16 14:40:31 -07:00 |
|
Ishaan Jaff
|
1fc9bcb184
|
feat use OpenAI extra_headers param
|
2024-05-16 14:38:17 -07:00 |
|
 Ishaan JaffandGitHub
|
2179598d1d
|
Merge pull request #3693 from BerriAI/litellm_fix_gemini_responses
[Fix] AI Studio (Gemini API) returns invalid 1 index instead of 0 when "stream": false
|
2024-05-16 14:21:55 -07:00 |
|