mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 10:44:24 +00:00
f44ab00de2
* fix(azure.py): handle /openai/deployment in azure api base * fix(factory.py): fix faulty anthropic tool result translation check Fixes https://github.com/BerriAI/litellm/issues/6422 * fix(gpt_transformation.py): add support for parallel_tool_calls to azure Fixes https://github.com/BerriAI/litellm/issues/6440 * fix(factory.py): support anthropic prompt caching for tool results * fix(vertex_ai/common_utils): don't pop non-null required field Fixes https://github.com/BerriAI/litellm/issues/6426 * feat(vertex_ai.py): support code_execution tool call for vertex ai + gemini Closes https://github.com/BerriAI/litellm/issues/6434 * build(model_prices_and_context_window.json): Add 'supports_assistant_prefill' for bedrock claude-3-5-sonnet v2 models Closes https://github.com/BerriAI/litellm/issues/6437 * fix(types/utils.py): fix linting * test: update test to include required fields * test: fix test * test: handle flaky test * test: remove e2e test - hitting gemini rate limits
130 lines
4.3 KiB
Python
130 lines
4.3 KiB
Python
import sys
|
|
import os
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../../")
|
|
) # Adds the parent directory to the system path
|
|
|
|
import pytest
|
|
from litellm.llms.AzureOpenAI.common_utils import process_azure_headers
|
|
from httpx import Headers
|
|
|
|
|
|
def test_process_azure_headers_empty():
|
|
result = process_azure_headers({})
|
|
assert result == {}, "Expected empty dictionary for no input"
|
|
|
|
|
|
def test_process_azure_headers_with_all_headers():
|
|
input_headers = Headers(
|
|
{
|
|
"x-ratelimit-limit-requests": "100",
|
|
"x-ratelimit-remaining-requests": "90",
|
|
"x-ratelimit-limit-tokens": "10000",
|
|
"x-ratelimit-remaining-tokens": "9000",
|
|
"other-header": "value",
|
|
}
|
|
)
|
|
|
|
expected_output = {
|
|
"x-ratelimit-limit-requests": "100",
|
|
"x-ratelimit-remaining-requests": "90",
|
|
"x-ratelimit-limit-tokens": "10000",
|
|
"x-ratelimit-remaining-tokens": "9000",
|
|
"llm_provider-x-ratelimit-limit-requests": "100",
|
|
"llm_provider-x-ratelimit-remaining-requests": "90",
|
|
"llm_provider-x-ratelimit-limit-tokens": "10000",
|
|
"llm_provider-x-ratelimit-remaining-tokens": "9000",
|
|
"llm_provider-other-header": "value",
|
|
}
|
|
|
|
result = process_azure_headers(input_headers)
|
|
assert result == expected_output, "Unexpected output for all Azure headers"
|
|
|
|
|
|
def test_process_azure_headers_with_partial_headers():
|
|
input_headers = Headers(
|
|
{
|
|
"x-ratelimit-limit-requests": "100",
|
|
"x-ratelimit-remaining-tokens": "9000",
|
|
"other-header": "value",
|
|
}
|
|
)
|
|
|
|
expected_output = {
|
|
"x-ratelimit-limit-requests": "100",
|
|
"x-ratelimit-remaining-tokens": "9000",
|
|
"llm_provider-x-ratelimit-limit-requests": "100",
|
|
"llm_provider-x-ratelimit-remaining-tokens": "9000",
|
|
"llm_provider-other-header": "value",
|
|
}
|
|
|
|
result = process_azure_headers(input_headers)
|
|
assert result == expected_output, "Unexpected output for partial Azure headers"
|
|
|
|
|
|
def test_process_azure_headers_with_no_matching_headers():
|
|
input_headers = Headers(
|
|
{"unrelated-header-1": "value1", "unrelated-header-2": "value2"}
|
|
)
|
|
|
|
expected_output = {
|
|
"llm_provider-unrelated-header-1": "value1",
|
|
"llm_provider-unrelated-header-2": "value2",
|
|
}
|
|
|
|
result = process_azure_headers(input_headers)
|
|
assert result == expected_output, "Unexpected output for non-matching headers"
|
|
|
|
|
|
def test_process_azure_headers_with_dict_input():
|
|
input_headers = {
|
|
"x-ratelimit-limit-requests": "100",
|
|
"x-ratelimit-remaining-requests": "90",
|
|
"other-header": "value",
|
|
}
|
|
|
|
expected_output = {
|
|
"x-ratelimit-limit-requests": "100",
|
|
"x-ratelimit-remaining-requests": "90",
|
|
"llm_provider-x-ratelimit-limit-requests": "100",
|
|
"llm_provider-x-ratelimit-remaining-requests": "90",
|
|
"llm_provider-other-header": "value",
|
|
}
|
|
|
|
result = process_azure_headers(input_headers)
|
|
assert result == expected_output, "Unexpected output for dict input"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"api_base, model, expected_endpoint",
|
|
[
|
|
(
|
|
"https://my-endpoint-sweden-berri992.openai.azure.com",
|
|
"dall-e-3-test",
|
|
"https://my-endpoint-sweden-berri992.openai.azure.com/openai/deployments/dall-e-3-test/images/generations?api-version=2023-12-01-preview",
|
|
),
|
|
(
|
|
"https://my-endpoint-sweden-berri992.openai.azure.com/openai/deployments/my-custom-deployment",
|
|
"dall-e-3",
|
|
"https://my-endpoint-sweden-berri992.openai.azure.com/openai/deployments/my-custom-deployment/images/generations?api-version=2023-12-01-preview",
|
|
),
|
|
],
|
|
)
|
|
def test_process_azure_endpoint_url(api_base, model, expected_endpoint):
|
|
from litellm.llms.AzureOpenAI.azure import AzureChatCompletion
|
|
|
|
azure_chat_completion = AzureChatCompletion()
|
|
input_args = {
|
|
"azure_client_params": {
|
|
"api_version": "2023-12-01-preview",
|
|
"azure_endpoint": api_base,
|
|
"azure_deployment": model,
|
|
"max_retries": 2,
|
|
"timeout": 600,
|
|
"api_key": "f28ab7b695af4154bc53498e5bdccb07",
|
|
},
|
|
"model": model,
|
|
}
|
|
result = azure_chat_completion.create_azure_base_url(**input_args)
|
|
assert result == expected_endpoint, "Unexpected endpoint"
|