phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

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

57
tests/local_testing/test_completion.py
View file

@ -1222,32 +1222,6 @@ def test_completion_mistral_api_modified_input():
pytest.fail(f"Error occurred: {e}")
def test_completion_claude2_1():
try:
litellm.set_verbose = True
print("claude2.1 test request")
messages = [
{
"role": "system",
"content": "Your goal is generate a joke on the topic user gives.",
},
{"role": "user", "content": "Generate a 3 liner joke for me"},
]
# test without max tokens
response = completion(model="claude-2.1", messages=messages)
# Add any assertions here to check the response
print(response)
print(response.usage)
print(response.usage.completion_tokens)
print(response["usage"]["completion_tokens"])
# print("new cost tracking")
except Exception as e:
pytest.fail(f"Error occurred: {e}")
# test_completion_claude2_1()
@pytest.mark.asyncio
async def test_acompletion_claude2_1():
try:
@ -1268,6 +1242,8 @@ async def test_acompletion_claude2_1():
print(response.usage.completion_tokens)
print(response["usage"]["completion_tokens"])
# print("new cost tracking")
except litellm.InternalServerError:
pytest.skip("model is overloaded.")
except Exception as e:
pytest.fail(f"Error occurred: {e}")
@ -4514,19 +4490,22 @@ async def test_dynamic_azure_params(stream, sync_mode):
@pytest.mark.flaky(retries=3, delay=1)
async def test_completion_ai21_chat():
litellm.set_verbose = True
response = await litellm.acompletion(
model="jamba-1.5-large",
user="ishaan",
tool_choice="auto",
seed=123,
messages=[{"role": "user", "content": "what does the document say"}],
documents=[
{
"content": "hello world",
"metadata": {"source": "google", "author": "ishaan"},
}
],
)
try:
response = await litellm.acompletion(
model="jamba-1.5-large",
user="ishaan",
tool_choice="auto",
seed=123,
messages=[{"role": "user", "content": "what does the document say"}],
documents=[
{
"content": "hello world",
"metadata": {"source": "google", "author": "ishaan"},
}
],
)
except litellm.InternalServerError:
pytest.skip("Model is overloaded")
@pytest.mark.parametrize(