Krish Dholakia
ef42461c1e
Litellm fix GitHub action testing ( #11163 )
...
* test: add __init__.py files
* refactor: rename test folder to avoid naming conflict
* test: update workflows
* test: update tests
* test: update imports
* test: update tests
* test: remove unused import
* ci(test-litellm.yml): add pytest retry to github workflow
* test: fix test
2025-05-26 14:41:42 -07:00
k10
9a35c41462
added logprobs ( #11161 )
2025-05-26 11:21:47 -07:00
Ishaan Jaff
1876b3ae35
[Fix] Rollback to httpx==0.27.0 ( #11146 )
...
* fix - fix - use old httpx version
* fix - fix - use old httpx version
* fix: test
* fix: comment
2025-05-26 10:44:11 -07:00
Kyrylo Yefimenko
f37a1a5854
Fix deprecation_date value for llama groq models ( #11151 )
2025-05-26 10:43:35 -07:00
Ishaan Jaff
1009defbdc
[Feat] Add /image/edits support for Azure ( #11160 )
...
* feat: add image edits on litellm router
* feat: add image edits endpoint
* fix: use pure async for image edits
* fix: base_process_llm_request
* fix: get_image_content_type
* feat: add image edits endpoint
* add image edits on UI
* test: image edits support
* fix: linting errors
* fix: linting errors
* test fix img gen
* feat: azure image edits
* fix: fix url construction of azure image edits
* fix: mock endpoints for azure images
2025-05-26 10:37:48 -07:00
Andy Gajdosik
828f9491dd
Fix #9295 docker-compose healthcheck test uses curl but curl is not in the image ( #9737 )
...
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
2025-05-26 10:19:59 -07:00
Adam Holmberg
c93a78cd6c
feat: Make gemini accept the openai parameter parallel_tool_calls ( #11125 )
...
* feat: Make gemini accept the openai parameter parallel_tool_calls
When mapping, allow the parameter: True because that is the
intrinsic behavior of Gemini. Allow False, but reject if there
are multiple tools because there's no actual equivalent in Gemini.
fixes #9686
ref: issues/9686
* chore: cleanup and move test_vertex.py down to tests/litellm
as suggested in https://github.com/BerriAI/litellm/pull/11125#discussion_r2105905871
2025-05-26 07:51:27 -07:00
Ishaan Jaff
77d2615185
docs release notes
2025-05-24 21:24:44 -07:00
Ishaan Jaff
66c44bb9f3
docs notes
2025-05-24 21:00:01 -07:00
Ishaan Jaff
c0239a0a79
feat - add code_execution tool to anthropic
2025-05-24 20:50:09 -07:00
Ishaan Jaff
39c85c22de
docs document all config settings
2025-05-24 20:48:09 -07:00
Krish Dholakia
a78d121ef4
Litellm fix multi instance checks on teams ( #11137 )
...
* fix(auth_checks.py): set ttl on in-memory team objects
ensures objects expire
* fix(in_memory_cache.py): allow ttl override if existing ttl expired (no 'get_cache' ever called)
2025-05-24 20:33:06 -07:00
Krrish Dholakia
bfbec06214
docs(index.md): cleanup
2025-05-24 19:53:59 -07:00
Ishaan Jaff
95b59cbf4d
docs image edits
2025-05-24 19:46:10 -07:00
Ishaan Jaff
7fae80b4c6
docs image edits
2025-05-24 19:44:54 -07:00
Ishaan Jaff
cadd86af95
docs image edit
2025-05-24 19:44:20 -07:00
Ishaan Jaff
1637413677
docs image edits
2025-05-24 19:43:48 -07:00
Ishaan Jaff
cd3e01ea4a
test fixes
2025-05-24 19:27:30 -07:00
Ishaan Jaff
59fd3d5fd9
test test fixes
2025-05-24 19:17:39 -07:00
Krrish Dholakia
cb58fc7f6d
docs: doc improvements
2025-05-24 19:06:00 -07:00
Ishaan Jaff
16c92c2e61
test fix test_ssl_context_transport
2025-05-24 18:52:23 -07:00
Ishaan Jaff
8a2b68a8d5
ui new build
2025-05-24 18:26:28 -07:00
Krrish Dholakia
061a2a730e
docs(managed_finetuning.md): cleanup
2025-05-24 18:21:06 -07:00
Krrish Dholakia
0119c1efaa
fix(auth_checks.py): bump in-memory cache ttl for user objects to 60s
2025-05-24 18:11:35 -07:00
Krrish Dholakia
f73fca2977
fix(auth_checks.py): set default user in-memory cache to 5s
2025-05-24 18:04:05 -07:00
Krrish Dholakia
f71bab3909
fix: fix ruff errors
2025-05-24 17:53:55 -07:00
Krish Dholakia
33d5f66387
Litellm revert redis changes ( #11135 )
...
* fix: revert user redis changes
* fix(in_memory_cache.py): don't reset ttl, if already set for object
Allows objects to expire and db checks to occur
* test: add unit test for change
2025-05-24 17:52:57 -07:00
Ishaan Jaff
7775e8471c
docs benchmarks
2025-05-24 17:43:38 -07:00
Ishaan Jaff
39feb742cd
docs aiohttp benchmarks
2025-05-24 17:41:10 -07:00
Ishaan Jaff
85bd3cfca1
fixes
2025-05-24 17:31:57 -07:00
Ishaan Jaff
c73ac784d6
docs latest release
2025-05-24 17:31:19 -07:00
Ishaan Jaff
c761c0ca2f
docs release notes
2025-05-24 17:23:31 -07:00
Ishaan Jaff
e957fbf38c
docs release notes
2025-05-24 17:17:56 -07:00
Ishaan Jaff
db96c8ca53
docs release notes
2025-05-24 17:17:44 -07:00
Ishaan Jaff
e7ede28189
notes update
2025-05-24 17:17:30 -07:00
Ishaan Jaff
c3f74b47f8
v1.71.1-stable - notes ( #11133 )
...
* draft notes
* fixes anthropic
* fixes release notes
2025-05-24 16:56:25 -07:00
Ishaan Jaff
9fc8d1c82e
[Chore]: feature flag aiohttp transport - users should opt into using aiohttp transport ( #11132 )
...
* fix: feature flag aiohttp transport
* fix: feature flag aiohttp transport
2025-05-24 16:29:53 -07:00
Krrish Dholakia
c725cbbde6
docs: add managed finetuning docs
2025-05-24 16:14:35 -07:00
Krrish Dholakia
76107bfb6b
docs(litellm_managed_files.md): add tutorial on managing file permissions
2025-05-24 14:11:15 -07:00
Krrish Dholakia
9c3cac3046
fix(common_request_processing.py): handle chunk being in bytes
...
fixes anthropic streaming error
2025-05-24 12:50:18 -07:00
Ishaan Jaff
119a73a3fc
fix: team viewer should not see create team ( #11127 )
2025-05-24 12:30:09 -07:00
Krrish Dholakia
f2cb89d610
fix: fix ruff check
2025-05-24 12:29:53 -07:00
Krrish Dholakia
8da4b3c4f1
style: add comments on schema reflecting org id field on schema
...
Closes https://github.com/BerriAI/litellm/issues/11092
2025-05-24 12:27:46 -07:00
Krrish Dholakia
1cd97e41e9
test: update tests
2025-05-24 12:26:31 -07:00
Krrish Dholakia
9990d3ce9f
fix(pre-commit-config.yaml): add enterprise folder to flake8 pre-commit checking
2025-05-24 12:19:56 -07:00
Krish Dholakia
010a4d44af
Fix passing standard optional params ( #11124 )
...
* fix(main.py): use processed non-default-params as standard input params for langfuse
Fixes https://github.com/BerriAI/litellm/issues/11072
Fixes https://github.com/BerriAI/litellm/issues/11096
* fix(main.py): rename variable to be more accurate
* test(test_langfuse_e2e_test.py): add router unit test for langfuse e2e testing
Prevent https://github.com/BerriAI/litellm/issues/11072 from happening again
* build: update lock
* fix(utils.py): refactor optional params function
make it easier to get the standardized non default params
* fix(utils.py): improve process non default params function
* fix(main.py): include provider specific params in processed non default params used in logging
ensures user can see any provider specific params on langfuse
ensures user can see any provider specific params on langfus e
2025-05-24 12:12:31 -07:00
Adam Holmberg
c58a0bb124
fix: detect and return status codes in streaming responses ( #10962 )
...
For streaming requests, the remote request is triggered and
first chunk inspected for an error code as emitted by
async_data_generator.
Potential fix for #9035
2025-05-24 12:04:46 -07:00
Krrish Dholakia
d14af20bbd
build: bump litellm-enterprise version - cleanup prints
2025-05-24 11:31:42 -07:00
Krrish Dholakia
ed02488daf
style: cleanup prints in enterprise
2025-05-24 11:29:15 -07:00
Ishaan Jaff
6aa0bec17d
(ui) qa fix org button
2025-05-24 10:41:33 -07:00
