phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

LiteLLM Minor Fixes & Improvements (11/19/2024) (#6820)

Browse source 
* fix(anthropic/chat/transformation.py): add json schema as values: json_schema

fixes passing pydantic obj to anthropic

Fixes https://github.com/BerriAI/litellm/issues/6766

* (feat): Add timestamp_granularities parameter to transcription API (#6457)

* Add timestamp_granularities parameter to transcription API

* add param to the local test

* fix(databricks/chat.py): handle max_retries optional param handling for openai-like calls

Fixes issue with calling finetuned vertex ai models via databricks route

* build(ui/): add team admins via proxy ui

* fix: fix linting error

* test: fix test

* docs(vertex.md): refactor docs

* test: handle overloaded anthropic model error

* test: remove duplicate test

* test: fix test

* test: update test to handle model overloaded error

---------

Co-authored-by: Show <35062952+BrunooShow@users.noreply.github.com>
This commit is contained in:
Krish Dholakia 2024-11-21 00:57:58 +05:30 • committed by GitHub
parent 7d0e1f05ac
commit b0be5bf3a1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 200 additions and 193 deletions
Download patch file Download diff file Expand all files Collapse all files

43
tests/llm_translation/base_llm_unit_tests.py
View file

@ -42,11 +42,14 @@ class BaseLLMChatTest(ABC):
"content": [{"type": "text", "text": "Hello, how are you?"}],
}
]
response = litellm.completion(
**base_completion_call_args,
messages=messages,
)
assert response is not None
try:
response = litellm.completion(
**base_completion_call_args,
messages=messages,
)
assert response is not None
except litellm.InternalServerError:
pass
# for OpenAI the content contains the JSON schema, so we need to assert that the content is not None
assert response.choices[0].message.content is not None
@ -89,6 +92,36 @@ class BaseLLMChatTest(ABC):
# relevant issue: https://github.com/BerriAI/litellm/issues/6741
assert response.choices[0].message.content is not None
def test_json_response_pydantic_obj(self):
from pydantic import BaseModel
from litellm.utils import supports_response_schema
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
litellm.model_cost = litellm.get_model_cost_map(url="")
class TestModel(BaseModel):
first_response: str
base_completion_call_args = self.get_base_completion_call_args()
if not supports_response_schema(base_completion_call_args["model"], None):
pytest.skip("Model does not support response schema")
try:
res = litellm.completion(
**base_completion_call_args,
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{
"role": "user",
"content": "What is the capital of France?",
},
],
response_format=TestModel,
)
assert res is not None
except litellm.InternalServerError:
pytest.skip("Model is overloaded")
def test_json_response_format_stream(self):
"""
Test that the JSON response format with streaming is supported by the LLM API