ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
34,378 Commits 9 Branches 7 Tags 935 MiB
dd183a7fcb
Commit Graph

34378 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Krrish Dholakia
33472bfd2b fix(factory.py): support 'function' openai message role for anthropic 
Fixes https://github.com/BerriAI/litellm/issues/3446
 2024-05-04 10:03:30 -07:00
Ishaan Jaff
0bc6969e4d
Merge pull request #3408 from msabramo/test_proxy_exception_mapping_mock_improvements 
Improve mocking in `test_proxy_exception_mapping.py`
 2024-05-04 09:29:41 -07:00
Krrish Dholakia
5a79f648c6 fix(caching.py): fix redis caching ping check 
don't fail to startup. Log an error message.
 2024-05-04 08:48:53 -07:00
Krish Dholakia
e7149a6812
Merge pull request #3445 from paneru-rajan/Issue-1159-imrove-reaceloop-doc 
Improve the document of Traceloop
 2024-05-04 08:35:56 -07:00
alisalim17
416d459a77 enable exception logging in logfire_openai.error() by setting _exc_info to True 2024-05-04 19:33:38 +04:00
alisalim17
7e0b479a37 docs: add documentation for logfire integration 2024-05-04 17:47:54 +04:00
alisalim17
978912ef32 feat: add failure handler for logfire 2024-05-04 17:40:23 +04:00
Rajan Paneru
7d9377f18a Improve the document of Traceloop 
If we follow exact step I was getting two errors, which this Pull-Request will fix:
* Fixed the yaml snippet spacing issue: it was throwing error when running copy+paste code
* Added api_key: my-fake-key as to run litellm --config config.yaml --debug it will be required, otherwise it will fail

Need for Improvements:
* The traceloop is ambigous, because it's a company that maintains OpenLLMetry, and has observability solution and the sdk name is aslo traceloop-sdk
* The doc was missing several other observability solutions
* The steps were not quite obvious, added one more steps to make things clear
 2024-05-04 22:42:53 +09:30
alisalim17
134611a8f4 test: add tests for logfire 2024-05-04 16:23:06 +04:00
alisalim17
39099e9c5b feat: add logfire integration 2024-05-04 16:22:53 +04:00
Lunik
1639a51f24
🔊 fix: Correctly use verbose logging 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-04 11:04:23 +02:00
Lunik
8783fd4895
✨ feat: Use 8 severity levels for azure content safety 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-04 10:45:39 +02:00
Lunik
ebbeb333c6
✏️ doc: typo in azure content safety 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-04 10:45:15 +02:00
Lunik
cb178723ca
📝 doc: Azure content safety Proxy usage 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-04 10:39:43 +02:00
Ishaan Jaff
8e9ba0f27f
Merge pull request #3441 from BerriAI/ui_select_start_end_time 
UI select start end time
 2024-05-03 22:14:58 -07:00
Ishaan Jaff
2cfb37aaaf add text about model group / time range 2024-05-03 22:14:12 -07:00
Ishaan Jaff
1d9a96bf8f ui - set models and start/endtimes 2024-05-03 22:10:40 -07:00
Ishaan Jaff
19aa43798c ui - select model group 2024-05-03 22:09:22 -07:00
Ishaan Jaff
e7adbb3801 ui - model dashboard 2024-05-03 22:09:01 -07:00
Ishaan Jaff
d4afe8a3bc ui - view logs by model group and time 2024-05-03 21:59:22 -07:00
Krrish Dholakia
b7ca9a53c9 refactor(main.py): trigger new build 2024-05-03 21:53:51 -07:00
Ishaan Jaff
611e7bd403 ui - select model group and date time range 2024-05-03 21:51:47 -07:00
Krrish Dholakia
fa47ce456d bump: version 1.35.37 → 1.35.38 2024-05-03 21:38:32 -07:00
Krrish Dholakia
8249c986bf fix(main.py): support new 'supports_system_message=False' param 
Fixes https://github.com/BerriAI/litellm/issues/3325
 2024-05-03 21:31:45 -07:00
Ishaan Jaff
ed714a9d6e ui select model and start and endtime 2024-05-03 21:21:41 -07:00
Ishaan Jaff
d806fe3513 startTime and endTime on UI 2024-05-03 21:21:28 -07:00
Ishaan Jaff
fccdb92c6b fix - select startTime and endTime on UI 2024-05-03 21:20:19 -07:00
Ishaan Jaff
f7150cdba2 ui - slect start and end date 2024-05-03 20:52:30 -07:00
Krrish Dholakia
a35ac050d2 test(test_router_fallbacks.py): bump test limits 2024-05-03 20:42:29 -07:00
Ishaan Jaff
01a11ccced ui - new build 2024-05-03 20:40:58 -07:00
Sebastián Estévez
fc0ced48c1
add_function_to_prompt bug fix 
This blows up when there's no "functions" in the dictionary even when tools is present because the inner function executes regardless (does not short circuit).
 2024-05-03 23:38:54 -04:00
Krish Dholakia
7d2aa2f645
Merge pull request #3433 from BerriAI/litellm_timeout_fix 
fix(bedrock.py): convert httpx.timeout to boto3 valid timeout
 2024-05-03 18:53:59 -07:00
Marc Abramowitz
eb433bde86 Add route: "/engines/{model:path}/chat/completions" 
Without this, it results in:

```pytb
Traceback (most recent call last):
  File "/Users/abramowi/Code/OpenSource/litellm/litellm/proxy/proxy_server.py", line 3836, in completion
    raise HTTPException(
fastapi.exceptions.HTTPException: 400: {'error': 'completion: Invalid model name passed in model=gpt-3.5-turbo/chat'}
```
 2024-05-03 18:02:29 -07:00
Marc Abramowitz
4ce4927c0c Add test_engines_model_chat_completions 2024-05-03 17:56:39 -07:00
Krish Dholakia
e6e742d464
Merge pull request #3436 from BerriAI/litellm_anthropic_stop_sequence_fix 
fix(anthropic.py): drop unsupported non-whitespace character value wh…
 2024-05-03 17:53:29 -07:00
Krrish Dholakia
097714e02f fix(anthropic.py): handle whitespace characters for anthropic calls 2024-05-03 17:31:34 -07:00
Krrish Dholakia
0450abfdc1 fix(bedrock.py): fix boto3 config init 2024-05-03 17:22:06 -07:00
Ishaan Jaff
debd8137f3
Merge pull request #3435 from BerriAI/litellm_ui_filter_exceptions_by_model_group 
Admin UI - filter exceptions by model group
 2024-05-03 17:18:44 -07:00
Krrish Dholakia
0b9fa53e3e fix(anthropic.py): drop unsupported non-whitespace character value when calling anthropic with stop sequences 
Fixes https://github.com/BerriAI/litellm/issues/3286
 2024-05-03 16:59:49 -07:00
Ishaan Jaff
e7034ea53d feat - filter exceptions by model group 2024-05-03 16:54:24 -07:00
Ishaan Jaff
d3152e606f fix - ui filter exceptions by modelGroup 2024-05-03 16:53:24 -07:00
Krrish Dholakia
f7eee60943 docs(exception_mapping.md): update exception mapping docs with 'should_retry' 2024-05-03 16:51:26 -07:00
Ishaan Jaff
2084cfd959 fix - test_check_num_callbacks 2024-05-03 16:41:08 -07:00
Ishaan Jaff
5e6b6c41c4
Merge pull request #3432 from BerriAI/litellm_add_bedrock_titan_embed 
Feat - add bedrock titan embed-v2
 2024-05-03 16:28:12 -07:00
Ishaan Jaff
926670bfb7
Merge pull request #3429 from BerriAI/litellm_add_unit_tests_slack_alerts 
[Test] Add Slack Alerting unit tests
 2024-05-03 16:27:40 -07:00
Ishaan Jaff
3dd1e8dfe7
Merge pull request #3427 from BerriAI/litellm_test_alert_size 
[Test] - Ensure only 1 slack callback + Size of of all callbacks do not grow
 2024-05-03 16:27:16 -07:00
Krish Dholakia
1b35a75245
Merge pull request #3430 from BerriAI/litellm_return_api_base 
feat(proxy_server.py): return api base in response headers
 2024-05-03 16:25:21 -07:00
Krrish Dholakia
a732d8772a fix(bedrock.py): convert httpx.timeout to boto3 valid timeout 
Closes https://github.com/BerriAI/litellm/issues/3398
 2024-05-03 16:24:21 -07:00
Ishaan Jaff
401bf8d67e test - bedrock v2 supports dimension 2024-05-03 16:23:37 -07:00
Ishaan Jaff
4a39b95acc fix - support dimension for titan embed v2 2024-05-03 16:13:27 -07:00