litellm-mirror/tests/llm_translation/test_vertex.py
Krish Dholakia 1e403a8447
Litellm dev 10 29 2024 (#6502)
* fix(core_helpers.py): return None, instead of raising kwargs is None error

Closes https://github.com/BerriAI/litellm/issues/6500

* docs(cost_tracking.md): cleanup doc

* fix(vertex_and_google_ai_studio.py): handle function call with no params passed in

Closes https://github.com/BerriAI/litellm/issues/6495

* test(test_router_timeout.py): add test for router timeout + retry logic

* test: update test to use module level values

* (fix) Prometheus - Log Postgres DB latency, status on prometheus  (#6484)

* fix logging DB fails on prometheus

* unit testing log to otel wrapper

* unit testing for service logger + prometheus

* use LATENCY buckets for service logging

* fix service logging

* docs clarify vertex vs gemini

* (router_strategy/) ensure all async functions use async cache methods (#6489)

* fix router strat

* use async set / get cache in router_strategy

* add coverage for router strategy

* fix imports

* fix batch_get_cache

* use async methods for least busy

* fix least busy use async methods

* fix test_dual_cache_increment

* test async_get_available_deployment when routing_strategy="least-busy"

* (fix) proxy - fix when `STORE_MODEL_IN_DB` should be set (#6492)

* set store_model_in_db at the top

* correctly use store_model_in_db global

* (fix) `PrometheusServicesLogger` `_get_metric` should return metric in Registry  (#6486)

* fix logging DB fails on prometheus

* unit testing log to otel wrapper

* unit testing for service logger + prometheus

* use LATENCY buckets for service logging

* fix service logging

* fix _get_metric in prom services logger

* add clear doc string

* unit testing for prom service logger

* bump: version 1.51.0 → 1.51.1

* Add `azure/gpt-4o-mini-2024-07-18` to model_prices_and_context_window.json (#6477)

* Update utils.py (#6468)

Fixed missing keys

* (perf) Litellm redis router fix - ~100ms improvement (#6483)

* docs(exception_mapping.md): add missing exception types

Fixes https://github.com/Aider-AI/aider/issues/2120#issuecomment-2438971183

* fix(main.py): register custom model pricing with specific key

Ensure custom model pricing is registered to the specific model+provider key combination

* test: make testing more robust for custom pricing

* fix(redis_cache.py): instrument otel logging for sync redis calls

ensures complete coverage for all redis cache calls

* refactor: pass parent_otel_span for redis caching calls in router

allows for more observability into what calls are causing latency issues

* test: update tests with new params

* refactor: ensure e2e otel tracing for router

* refactor(router.py): add more otel tracing acrosss router

catch all latency issues for router requests

* fix: fix linting error

* fix(router.py): fix linting error

* fix: fix test

* test: fix tests

* fix(dual_cache.py): pass ttl to redis cache

* fix: fix param

* perf(cooldown_cache.py): improve cooldown cache, to store cache results in memory for 5s, prevents redis call from being made on each request

reduces 100ms latency per call with caching enabled on router

* fix: fix test

* fix(cooldown_cache.py): handle if a result is None

* fix(cooldown_cache.py): add debug statements

* refactor(dual_cache.py): move to using an in-memory check for batch get cache, to prevent redis from being hit for every call

* fix(cooldown_cache.py): fix linting erropr

* refactor(prometheus.py): move to using standard logging payload for reading the remaining request / tokens

Ensures prometheus token tracking works for anthropic as well

* fix: fix linting error

* fix(redis_cache.py): make sure ttl is always int (handle float values)

Fixes issue where redis_client.ex was not working correctly due to float ttl

* fix: fix linting error

* test: update test

* fix: fix linting error

---------

Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
Co-authored-by: Xingyao Wang <xingyao@all-hands.dev>
Co-authored-by: vibhanshu-ob <115142120+vibhanshu-ob@users.noreply.github.com>
2024-10-29 22:04:16 -07:00

180 lines
4.9 KiB
Python

import json
import os
import sys
import traceback
from dotenv import load_dotenv
load_dotenv()
import io
from unittest.mock import AsyncMock, MagicMock, patch
sys.path.insert(
0, os.path.abspath("../..")
) # Adds the parent directory to the system path
import pytest
import litellm
from litellm import get_optional_params
def test_completion_pydantic_obj_2():
from pydantic import BaseModel
from litellm.llms.custom_httpx.http_handler import HTTPHandler
litellm.set_verbose = True
class CalendarEvent(BaseModel):
name: str
date: str
participants: list[str]
class EventsList(BaseModel):
events: list[CalendarEvent]
messages = [
{"role": "user", "content": "List important events from the 20th century."}
]
expected_request_body = {
"contents": [
{
"role": "user",
"parts": [{"text": "List important events from the 20th century."}],
}
],
"generationConfig": {
"response_mime_type": "application/json",
"response_schema": {
"properties": {
"events": {
"items": {
"properties": {
"name": {"type": "string"},
"date": {"type": "string"},
"participants": {
"items": {"type": "string"},
"type": "array",
},
},
"required": [
"name",
"date",
"participants",
],
"type": "object",
},
"type": "array",
}
},
"required": [
"events",
],
"type": "object",
},
},
}
client = HTTPHandler()
with patch.object(client, "post", new=MagicMock()) as mock_post:
mock_post.return_value = expected_request_body
try:
litellm.completion(
model="gemini/gemini-1.5-pro",
messages=messages,
response_format=EventsList,
client=client,
)
except Exception as e:
print(e)
mock_post.assert_called_once()
print(mock_post.call_args.kwargs)
assert mock_post.call_args.kwargs["json"] == expected_request_body
def test_build_vertex_schema():
from litellm.llms.vertex_ai_and_google_ai_studio.common_utils import (
_build_vertex_schema,
)
import json
schema = {
"type": "object",
"properties": {
"recipes": {
"type": "array",
"items": {
"type": "object",
"properties": {"recipe_name": {"type": "string"}},
"required": ["recipe_name"],
},
}
},
"required": ["recipes"],
}
new_schema = _build_vertex_schema(schema)
print(f"new_schema: {new_schema}")
assert new_schema["type"] == schema["type"]
assert new_schema["properties"] == schema["properties"]
assert "required" in new_schema and new_schema["required"] == schema["required"]
@pytest.mark.parametrize(
"tools, key",
[
([{"googleSearchRetrieval": {}}], "googleSearchRetrieval"),
([{"code_execution": {}}], "code_execution"),
],
)
def test_vertex_tool_params(tools, key):
optional_params = get_optional_params(
model="gemini-1.5-pro",
custom_llm_provider="vertex_ai",
tools=tools,
)
print(optional_params)
assert optional_params["tools"][0][key] == {}
@pytest.mark.parametrize(
"tool, expect_parameters",
[
(
{
"name": "test_function",
"description": "test_function_description",
"parameters": {
"type": "object",
"properties": {"test_param": {"type": "string"}},
},
},
True,
),
(
{
"name": "test_function",
},
False,
),
],
)
def test_vertex_function_translation(tool, expect_parameters):
"""
If param not set, don't set it in the request
"""
tools = [tool]
optional_params = get_optional_params(
model="gemini-1.5-pro",
custom_llm_provider="vertex_ai",
tools=tools,
)
print(optional_params)
if expect_parameters:
assert "parameters" in optional_params["tools"][0]["function_declarations"][0]
else:
assert (
"parameters" not in optional_params["tools"][0]["function_declarations"][0]
)