Rajan Paneru
65b07bcb8c
Preserving the Pydantic Message Object
...
Following statement replaces the Pydantic Message Object and initialize it with the dict
model_response["choices"][0]["message"] = response_json["message"]
We need to make sure message is always litellm.Message object
As a fix, based on the code of ollama.py file, i am updating just the content intead of entire object for both sync and async functions
2024-05-10 22:12:32 +09:30
Rajan Paneru
8eb842dcf5
revered the patch so that the fix can be applied in the main place
2024-05-10 22:04:44 +09:30
Rajan Paneru
c45085b728
Based on the data-type using json
...
The value of response_obj["choices"][0]["message"] is Message object and dict
Added a conditional to use .json only iff it is Message Object
2024-05-10 10:06:50 +09:30
Krish Dholakia
8ad979cdfe
Merge branch 'main' into litellm_region_based_routing
2024-05-08 22:19:51 -07:00
Krish Dholakia
3f13251241
Merge pull request #3479 from simonsanvil/feature/watsonx-integration
...
Add support for async streaming to watsonx provider
2024-05-08 22:19:05 -07:00
Krrish Dholakia
3d18897d69
feat(router.py): enable filtering model group by 'allowed_model_region'
2024-05-08 22:10:17 -07:00
Krrish Dholakia
db666b01e5
feat(proxy_server.py): add CRUD endpoints for 'end_user' management
...
allow admin to specify region + default models for end users
2024-05-08 18:50:36 -07:00
Ishaan Jaff
dea4a081c7
ui - new build
2024-05-08 18:45:54 -07:00
Ishaan Jaff
6d955ef457
Merge branch 'main' into ui_show_spend_end_user
2024-05-08 18:29:25 -07:00
Ishaan Jaff
a38d9e35fd
feat - get price by end_user
2024-05-08 18:19:27 -07:00
Ishaan Jaff
b99a6717af
fix - startTime, endTime in GlobalEndUsersSpend
2024-05-08 17:05:09 -07:00
Ishaan Jaff
1eea4d1c90
fix /global/spend/end_users
2024-05-08 17:03:38 -07:00
Ishaan Jaff
faab704d28
update global/spend/end_users
2024-05-08 17:03:09 -07:00
Ishaan Jaff
41a4a06389
Merge pull request #3534 from BerriAI/litellm_fix_cost_calc_bedrock
...
[Fix] `litellm.completion_cost(model="bedrock/anthropic.claude-instant-v1"..)`
2024-05-08 16:59:46 -07:00
Krrish Dholakia
6575143460
feat(proxy_server.py): return litellm version in response headers
2024-05-08 16:00:08 -07:00
Ishaan Jaff
33d6caa889
fix completion cost test
2024-05-08 15:51:30 -07:00
Ishaan Jaff
282b8d0ae4
test bedrock pricing
2024-05-08 15:26:53 -07:00
Ishaan Jaff
8348c671a9
fix - cost tracking - looking up bedrock pricing
2024-05-08 15:25:52 -07:00
Krish Dholakia
91bb7cd261
Merge pull request #3437 from msabramo/add-engines-model-chat-completions-endpoint
...
Add `/engines/{model}/chat/completions` endpoint
2024-05-08 14:30:39 -07:00
Ishaan Jaff
597b09598c
feat - send alert on cooling down a deploymeny
2024-05-08 14:14:14 -07:00
Ishaan Jaff
aef3d89f0c
fix add cooldown_deployment alert_type
2024-05-08 14:13:51 -07:00
Krrish Dholakia
51b6c3bdbc
test(test_function_call_parsing.py): add test for function call parsing
...
Closes https://github.com/BerriAI/litellm/issues/2654
2024-05-08 10:54:26 -07:00
Krrish Dholakia
6ce13ab364
refactor(main.py): trigger new build
2024-05-08 09:24:01 -07:00
Krrish Dholakia
a854824c02
fix(main.py): fix together ai text completion call
2024-05-08 09:10:45 -07:00
CyanideByte
b7c60031ca
Pydantic warning snuck in here
2024-05-07 23:59:18 -07:00
Krish Dholakia
0e709fdc21
Merge branch 'main' into litellm_ui_fixes_6
2024-05-07 22:01:04 -07:00
Krish Dholakia
303e0c6226
Revert "* feat(factory.py): add support for merging consecutive messages of one role when separated with empty message of another role"
2024-05-07 21:42:18 -07:00
Krrish Dholakia
fbcda918de
feat(ui/model_dashboard.tsx): show if model is config or db model
2024-05-07 21:34:18 -07:00
Krrish Dholakia
f45954d154
test(test_config.py): fix test
2024-05-07 21:31:03 -07:00
Krish Dholakia
a325bf2fb8
Merge pull request #3478 from nkvch/Issue-#3474-anthropic-roles-alternation-issue
...
* feat(factory.py): add support for merging consecutive messages of one role when separated with empty message of another role
2024-05-07 21:24:47 -07:00
Krrish Dholakia
8d04f4686f
test: fix test
2024-05-07 21:14:33 -07:00
Krrish Dholakia
dc8239ecc6
feat(model_dashboard.tsx): allow adding output cost per token on ui
2024-05-07 21:09:49 -07:00
Krrish Dholakia
5a16bec6a1
feat(model_dashboard.tsx): allow user to edit input cost per token for model on ui
...
also contains fixes for `/model/update`
2024-05-07 20:57:21 -07:00
Ishaan Jaff
21d3407b95
fix replicate test
2024-05-07 19:48:46 -07:00
Ishaan Jaff
4e7b5aa9d7
Merge pull request #3439 from phact/patch-3
...
add_function_to_prompt bug fix
2024-05-07 19:31:19 -07:00
Ishaan Jaff
2725a55e7a
Merge pull request #3470 from mbektas/fix-ollama-embeddings
...
support sync ollama embeddings
2024-05-07 19:21:37 -07:00
Ishaan Jaff
6e72857cf7
fix model cost map
2024-05-07 19:15:58 -07:00
Ishaan Jaff
223e386737
Merge pull request #3511 from BerriAI/litellm_router_send_exceptions_slack
...
[Feat] litellm.Router / litellm.completion - send llm exceptions to slack
2024-05-07 19:09:44 -07:00
Ishaan Jaff
596adf6e2f
test - slack alerting on litellm router
2024-05-07 19:04:25 -07:00
Krrish Dholakia
312249ca44
feat(ui/model_dashboard.tsx): show if model is config or db model
2024-05-07 18:29:14 -07:00
Ishaan Jaff
dc74204427
fix typo
2024-05-07 18:27:49 -07:00
Ishaan Jaff
e8053c3d0b
fix slack alerting
2024-05-07 18:17:12 -07:00
Ishaan Jaff
c08352a0ce
router- initialize alerting
2024-05-07 18:03:04 -07:00
Ishaan Jaff
5fd3b12d34
add router alerting type
2024-05-07 17:46:18 -07:00
Ishaan Jaff
17787db973
Merge pull request #3503 from paul-gauthier/deepseek
...
Added "deepseek/" as a supported provider (openai compatible)
2024-05-07 15:15:47 -07:00
Ishaan Jaff
b1230dd919
test - slack alerts on router
2024-05-07 15:12:21 -07:00
Ishaan Jaff
32f3e032e9
feat - send slack alerts litellm.router
2024-05-07 15:10:47 -07:00
Krish Dholakia
2aaaa5e1b4
Merge pull request #3506 from BerriAI/litellm_reintegrate_langfuse_url_slack_alert
...
feat(slack_alerting.py): reintegrate langfuse trace url for slack alerts
2024-05-07 15:03:29 -07:00
Ishaan Jaff
84055c0546
Merge pull request #3510 from BerriAI/litellm_make_lowest_cost_async
...
[Feat] Make lowest cost routing Async
2024-05-07 14:14:04 -07:00
Ishaan Jaff
8644aec8d3
test - lowest cost router
2024-05-07 13:52:34 -07:00
