mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 02:34:29 +00:00
b682dc4ec8
* feat(bedrock/rerank): infer model region if model given as arn * test: add unit testing to ensure bedrock region name inferred from arn on rerank * feat(bedrock/rerank/transformation.py): include search units for bedrock rerank result Resolves https://github.com/BerriAI/litellm/issues/7258#issuecomment-2671557137 * test(test_bedrock_completion.py): add testing for bedrock cohere rerank * feat(cost_calculator.py): refactor rerank cost tracking to support bedrock cost tracking * build(model_prices_and_context_window.json): add amazon.rerank model to model cost map * fix(cost_calculator.py): bedrock/common_utils.py get base model from model w/ arn -> handles rerank model * build(model_prices_and_context_window.json): add bedrock cohere rerank pricing * feat(bedrock/rerank): migrate bedrock config to basererank config * Revert "feat(bedrock/rerank): migrate bedrock config to basererank config" This reverts commit84fae1f167. * test: add testing to ensure large doc / queries are correctly counted * Revert "test: add testing to ensure large doc / queries are correctly counted" This reverts commit4337f1657e. * fix(migrate-jina-ai-to-rerank-config): enables cost tracking * refactor(jina_ai/): finish migrating jina ai to base rerank config enables cost tracking * fix(jina_ai/rerank): e2e jina ai rerank cost tracking * fix: cleanup dead code * fix: fix python3.8 compatibility error * test: fix test * test: add e2e testing for azure ai rerank * fix: fix linting error * test: mark cohere as flaky
128 lines
4.1 KiB
Python
128 lines
4.1 KiB
Python
import asyncio
|
|
import httpx
|
|
import json
|
|
import pytest
|
|
import sys
|
|
from typing import Any, Dict, List
|
|
from unittest.mock import MagicMock, Mock, patch
|
|
import os
|
|
|
|
sys.path.insert(
|
|
0, os.path.abspath("../..")
|
|
) # Adds the parent directory to the system path
|
|
import litellm
|
|
from litellm.exceptions import BadRequestError
|
|
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
|
|
from litellm.utils import (
|
|
CustomStreamWrapper,
|
|
get_supported_openai_params,
|
|
get_optional_params,
|
|
)
|
|
|
|
# test_example.py
|
|
from abc import ABC, abstractmethod
|
|
|
|
|
|
def assert_response_shape(response, custom_llm_provider):
|
|
expected_response_shape = {"id": str, "results": list, "meta": dict}
|
|
|
|
expected_results_shape = {"index": int, "relevance_score": float}
|
|
|
|
expected_meta_shape = {"api_version": dict, "billed_units": dict}
|
|
|
|
expected_api_version_shape = {"version": str}
|
|
|
|
expected_billed_units_shape = {"search_units": int}
|
|
expected_billed_units_total_tokens_shape = {"total_tokens": int}
|
|
|
|
assert isinstance(response.id, expected_response_shape["id"])
|
|
assert isinstance(response.results, expected_response_shape["results"])
|
|
for result in response.results:
|
|
assert isinstance(result["index"], expected_results_shape["index"])
|
|
assert isinstance(
|
|
result["relevance_score"], expected_results_shape["relevance_score"]
|
|
)
|
|
assert isinstance(response.meta, expected_response_shape["meta"])
|
|
|
|
if custom_llm_provider == "cohere":
|
|
|
|
assert isinstance(
|
|
response.meta["api_version"], expected_meta_shape["api_version"]
|
|
)
|
|
assert isinstance(
|
|
response.meta["api_version"]["version"],
|
|
expected_api_version_shape["version"],
|
|
)
|
|
assert isinstance(
|
|
response.meta["billed_units"], expected_meta_shape["billed_units"]
|
|
)
|
|
if "total_tokens" in response.meta["billed_units"]:
|
|
assert isinstance(
|
|
response.meta["billed_units"]["total_tokens"],
|
|
expected_billed_units_total_tokens_shape["total_tokens"],
|
|
)
|
|
else:
|
|
assert isinstance(
|
|
response.meta["billed_units"]["search_units"],
|
|
expected_billed_units_shape["search_units"],
|
|
)
|
|
|
|
|
|
class BaseLLMRerankTest(ABC):
|
|
"""
|
|
Abstract base test class that enforces a common test across all test classes.
|
|
"""
|
|
|
|
@abstractmethod
|
|
def get_base_rerank_call_args(self) -> dict:
|
|
"""Must return the base rerank call args"""
|
|
pass
|
|
|
|
@abstractmethod
|
|
def get_custom_llm_provider(self) -> litellm.LlmProviders:
|
|
"""Must return the custom llm provider"""
|
|
pass
|
|
|
|
@pytest.mark.asyncio()
|
|
@pytest.mark.parametrize("sync_mode", [True, False])
|
|
async def test_basic_rerank(self, sync_mode):
|
|
litellm._turn_on_debug()
|
|
os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
|
|
litellm.model_cost = litellm.get_model_cost_map(url="")
|
|
rerank_call_args = self.get_base_rerank_call_args()
|
|
custom_llm_provider = self.get_custom_llm_provider()
|
|
if sync_mode is True:
|
|
response = litellm.rerank(
|
|
**rerank_call_args,
|
|
query="hello",
|
|
documents=["hello", "world"],
|
|
top_n=2,
|
|
)
|
|
|
|
print("re rank response: ", response)
|
|
|
|
assert response.id is not None
|
|
assert response.results is not None
|
|
|
|
assert response._hidden_params["response_cost"] is not None
|
|
assert response._hidden_params["response_cost"] > 0
|
|
|
|
assert_response_shape(
|
|
response=response, custom_llm_provider=custom_llm_provider.value
|
|
)
|
|
else:
|
|
response = await litellm.arerank(
|
|
**rerank_call_args,
|
|
query="hello",
|
|
documents=["hello", "world"],
|
|
top_n=2,
|
|
)
|
|
|
|
print("async re rank response: ", response)
|
|
|
|
assert response.id is not None
|
|
assert response.results is not None
|
|
|
|
assert_response_shape(
|
|
response=response, custom_llm_provider=custom_llm_provider.value
|
|
)
|