Krrish Dholakia
|
c0ef2e9dd0
|
fix(main.py): fix linting error for python3.8
|
2024-08-07 13:21:35 -07:00 |
|
Krrish Dholakia
|
37dc359efb
|
fix(utils.py): fix linting error for python3.8
|
2024-08-07 13:14:29 -07:00 |
|
Krrish Dholakia
|
a2e792d32e
|
test: update build requirements
|
2024-08-07 13:09:49 -07:00 |
|
 Krish DholakiaandGitHub
|
3605e873a1
|
Merge branch 'main' into litellm_add_pydantic_model_support
|
2024-08-07 13:07:46 -07:00 |
|
Krrish Dholakia
|
f0f900d69e
|
fix(router.py): add reason for fallback failure to client-side exception string
make it easier to debug why a fallback failed to occur
|
2024-08-07 13:02:47 -07:00 |
|
Ishaan Jaff
|
1bf36cd7a4
|
docs prom metrics
|
2024-08-07 12:50:03 -07:00 |
|
Ishaan Jaff
|
61ccd5354b
|
docs prometheus
|
2024-08-07 12:47:06 -07:00 |
|
Ishaan Jaff
|
958e0fdfab
|
show warning about prometheus moving to enterprise
|
2024-08-07 12:46:26 -07:00 |
|
 Ishaan JaffandGitHub
|
80acc7ecfe
|
Merge pull request #5088 from BerriAI/litellm_init_prom_svc_logger
[Fix] Init Prometheus Service Logger when it's None
|
2024-08-07 12:40:08 -07:00 |
|
 Ishaan JaffandGitHub
|
3f9d37c596
|
Merge pull request #5092 from BerriAI/litellm_prom_metrics_llms
[Feat] - Prometheus Metrics to monitor a model health
|
2024-08-07 12:39:38 -07:00 |
|
Ishaan Jaff
|
72aebe5e59
|
docs link to enteprise pricing
|
2024-08-07 12:10:47 -07:00 |
|
Ishaan Jaff
|
8d1f051d8c
|
docs prometheus
|
2024-08-07 11:37:05 -07:00 |
|
Ishaan Jaff
|
579f09b334
|
fix logging cool down deployment
|
2024-08-07 11:27:05 -07:00 |
|
Krrish Dholakia
|
ff386f6b60
|
fix(utils.py): support deepseek tool calling
Fixes https://github.com/BerriAI/litellm/issues/5081
|
2024-08-07 11:14:05 -07:00 |
|
Krrish Dholakia
|
2f402b1cdd
|
fix(vertex_ai_partner.py): default vertex ai llama3.1 api to use all openai params
Poor vertex docs - not clear what can/can't work
Fixes https://github.com/BerriAI/litellm/issues/5090
|
2024-08-07 11:08:54 -07:00 |
|
Ishaan Jaff
|
d1e519afd1
|
use router_cooldown_handler
|
2024-08-07 10:40:55 -07:00 |
|
Ishaan Jaff
|
99ecde7744
|
allow setting outage metrics
|
2024-08-07 10:36:18 -07:00 |
|
Ishaan Jaff
|
9a8fa9f047
|
emit deployment_partial_outage on prometheus
|
2024-08-07 09:56:01 -07:00 |
|
Ishaan Jaff
|
0304513b67
|
rename to set_llm_deployment_success_metrics
|
2024-08-07 09:46:08 -07:00 |
|
Ishaan Jaff
|
13d1caf94a
|
add set_remaining_tokens_requests_metric
|
2024-08-07 09:43:35 -07:00 |
|
Ishaan Jaff
|
315bba34e6
|
prom svc logger init if it's None
|
2024-08-07 09:02:03 -07:00 |
|
 Ishaan JaffandGitHub
|
7e0cd39de7
|
Merge pull request #5086 from BerriAI/litellm_or_headers
[Fix-Bug]: Using extra_headers removes the OpenRouter HTTP-Referer/X-Title headers
|
2024-08-07 08:27:07 -07:00 |
|
Ishaan Jaff
|
dc3cdf3ed8
|
fix use extra headers for open router
|
2024-08-07 08:15:05 -07:00 |
|
Krrish Dholakia
|
1008f24b16
|
build(requirements.txt): bump openai version
v1.43.1-dev1
|
2024-08-07 08:08:37 -07:00 |
|
 Ishaan JaffandGitHub
|
975eec8777
|
Merge pull request #5084 from BerriAI/litellm_add_gpt4o
add ft:gpt-4o-mini-2024-07-18 to model prices
|
2024-08-07 08:05:14 -07:00 |
|
 Ishaan JaffandGitHub
|
2e6ba1c27c
|
Merge pull request #5085 from BerriAI/revert-4640-main
Revert "Fix: Add prisma binary_cache_dir specification to pyproject.toml"
|
2024-08-07 07:54:15 -07:00 |
|
 Ishaan JaffandGitHub
|
64df195fe8
|
Revert "Fix: Add prisma binary_cache_dir specification to pyproject.toml"
|
2024-08-07 07:50:05 -07:00 |
|
Ishaan Jaff
|
5743640250
|
feat add ft:gpt-4o-mini-2024-07-18
|
2024-08-07 07:46:23 -07:00 |
|
Krrish Dholakia
|
a0bb89a372
|
docs(ui.md): add restrict email subdomains w/ sso
|
2024-08-06 22:54:33 -07:00 |
|
Krrish Dholakia
|
bc8857ca23
|
build(model_prices_and_context_window.json): remove duplicate entries
|
2024-08-06 22:50:41 -07:00 |
|
 Krish DholakiaandGitHub
|
405f496962
|
Merge pull request #5076 from BerriAI/litellm_support_lakera_config_thresholds
LLM Guardrails - Support lakera config thresholds + custom api base
|
2024-08-06 22:47:22 -07:00 |
|
 Krish DholakiaandGitHub
|
c82fc0cac2
|
Merge branch 'main' into litellm_support_lakera_config_thresholds
|
2024-08-06 22:47:13 -07:00 |
|
Ishaan Jaff
|
3e84014a69
|
run ci / cd again
|
2024-08-06 21:35:46 -07:00 |
|
Ishaan Jaff
|
f579aef740
|
ci/cd run again
v1.43.1
|
2024-08-06 21:28:22 -07:00 |
|
Ishaan Jaff
|
0d76f49ea6
|
docs run ui on custom server root path
|
2024-08-06 21:27:47 -07:00 |
|
Ishaan Jaff
|
56f110cd04
|
test test_basic_passthrough
|
2024-08-06 21:17:07 -07:00 |
|
Ishaan Jaff
|
ab920ab461
|
fix pass through endpoint tests
|
2024-08-06 21:16:07 -07:00 |
|
 Ishaan JaffandGitHub
|
d6db6f3ee6
|
Merge pull request #5078 from BerriAI/litellm_fwd_server_root_path
UI - fwd UI requests from server root path
|
2024-08-06 20:59:21 -07:00 |
|
Ishaan Jaff
|
7173cef822
|
clean up unused func
|
2024-08-06 20:58:51 -07:00 |
|
Krrish Dholakia
|
2dd27a4e12
|
feat(utils.py): support validating json schema client-side if user opts in
|
2024-08-06 19:35:33 -07:00 |
|
Krrish Dholakia
|
5dfde2ee0b
|
feat: Translate openai 'response_format' json_schema to 'response_schema' for vertex ai + google ai studio
Closes https://github.com/BerriAI/litellm/issues/5074
|
2024-08-06 19:06:14 -07:00 |
|
Ishaan Jaff
|
671d8ac496
|
explain ui base path
|
2024-08-06 18:42:08 -07:00 |
|
Krrish Dholakia
|
0c88cc4153
|
docs(json_mode.md): add example of calling openai with pydantic model via litellm
|
2024-08-06 18:27:06 -07:00 |
|
Krrish Dholakia
|
cf44d1e069
|
docs(sidebars.js): cleanup sidebar title
|
2024-08-06 18:24:54 -07:00 |
|
Krrish Dholakia
|
9cf3d5f568
|
feat(utils.py): support passing response_format as pydantic model
Related issue - https://github.com/BerriAI/litellm/issues/5074
|
2024-08-06 18:16:07 -07:00 |
|
Ishaan Jaff
|
a1c1ad60d2
|
fix forward ui requests when base url set
v1.40.3.dev4
|
2024-08-06 18:10:34 -07:00 |
|
Ishaan Jaff
|
d08f59ae09
|
add redirect_ui_middleware
|
2024-08-06 18:01:23 -07:00 |
|
Ishaan Jaff
|
98758fb59f
|
build custom ui path docker
|
2024-08-06 17:50:07 -07:00 |
|
Krrish Dholakia
|
f3a0eb8eb9
|
docs(json_mode.md): update json mode docs to show structured output responses
Relevant issue - https://github.com/BerriAI/litellm/issues/5074
|
2024-08-06 17:01:41 -07:00 |
|
 Ishaan JaffandGitHub
|
c11f575029
|
Merge pull request #5075 from BerriAI/litelm_use_file_checksum
[Feat] /audio/transcription use file checksum for cache key
|
2024-08-06 16:48:31 -07:00 |
|