(feat) Add cost tracking for /batches requests OpenAI (#7384)

* add basic logging for create`batch`

* add create_batch as a call type

* add basic dd logging for batches

* basic batch creation logging on DD

* batch endpoints add cost calc

* fix batches_async_logging

* separate folder for batches testing

* new job for batches tests

* test batches logging

* fix validation logic

* add vertex_batch_completions.jsonl

* test test_async_create_batch

* test_async_create_batch

* update tests

* test_completion_with_no_model

* remove dead code

* update load_vertex_ai_credentials

* test_avertex_batch_prediction

* update get async httpx client

* fix get_async_httpx_client

* update test_avertex_batch_prediction

* fix batches testing config.yaml

* add google deps

* fix vertex files handler
This commit is contained in:
Ishaan Jaff 2024-12-23 17:47:26 -08:00 committed by GitHub
parent 9d66976162
commit 00544b97c8
13 changed files with 649 additions and 78 deletions

View file

@ -2,10 +2,12 @@ from typing import Any, Coroutine, Optional, Union
import httpx
from litellm import LlmProviders
from litellm.integrations.gcs_bucket.gcs_bucket_base import (
GCSBucketBase,
GCSLoggingConfig,
)
from litellm.llms.custom_httpx.http_handler import get_async_httpx_client
from litellm.types.llms.openai import CreateFileRequest, FileObject
from .transformation import VertexAIFilesTransformation
@ -20,6 +22,12 @@ class VertexAIFilesHandler(GCSBucketBase):
This implementation uploads files on GCS Buckets
"""
def __init__(self):
super().__init__()
self.async_httpx_client = get_async_httpx_client(
llm_provider=LlmProviders.VERTEX_AI,
)
pass
async def async_create_file(