mirror of
https://github.com/tiennm99/litellm.git
synced 2026-06-17 22:48:35 +00:00
Krish Dholakia
d57be47b0f
* ci(config.yml): add a 'check_code_quality' step Addresses https://github.com/BerriAI/litellm/issues/5991 * ci(config.yml): check why circle ci doesn't pick up this test * ci(config.yml): fix to run 'check_code_quality' tests * fix(__init__.py): fix unprotected import * fix(__init__.py): don't remove unused imports * build(ruff.toml): update ruff.toml to ignore unused imports * fix: fix: ruff + pyright - fix linting + type-checking errors * fix: fix linting errors * fix(lago.py): fix module init error * fix: fix linting errors * ci(config.yml): cd into correct dir for checks * fix(proxy_server.py): fix linting error * fix(utils.py): fix bare except causes ruff linting errors * fix: ruff - fix remaining linting errors * fix(clickhouse.py): use standard logging object * fix(__init__.py): fix unprotected import * fix: ruff - fix linting errors * fix: fix linting errors * ci(config.yml): cleanup code qa step (formatting handled in local_testing) * fix(_health_endpoints.py): fix ruff linting errors * ci(config.yml): just use ruff in check_code_quality pipeline for now * build(custom_guardrail.py): include missing file * style(embedding_handler.py): fix ruff check
86 lines
2.5 KiB
Python
86 lines
2.5 KiB
Python
import os
|
|
import time
|
|
|
|
import requests
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
|
|
# Set the base URL as needed
|
|
base_url = "https://api.litellm.ai"
|
|
# Uncomment the line below if you want to switch to the local server
|
|
# base_url = "http://0.0.0.0:8000"
|
|
|
|
# Step 1 Add a config to the proxy, generate a temp key
|
|
config = {
|
|
"model_list": [
|
|
{
|
|
"model_name": "gpt-3.5-turbo",
|
|
"litellm_params": {
|
|
"model": "gpt-3.5-turbo",
|
|
"api_key": os.environ["OPENAI_API_KEY"],
|
|
},
|
|
}
|
|
]
|
|
}
|
|
|
|
response = requests.post(
|
|
url=f"{base_url}/key/generate",
|
|
json={
|
|
"config": config,
|
|
"duration": "30d", # default to 30d, set it to 30m if you want a temp key
|
|
},
|
|
headers={"Authorization": "Bearer sk-hosted-litellm"},
|
|
)
|
|
|
|
print("\nresponse from generating key", response.text)
|
|
print("\n json response from gen key", response.json())
|
|
|
|
generated_key = response.json()["key"]
|
|
print("\ngenerated key for proxy", generated_key)
|
|
|
|
# Step 2: Queue a request to the proxy, using your generated_key
|
|
print("Creating a job on the proxy")
|
|
job_response = requests.post(
|
|
url=f"{base_url}/queue/request",
|
|
json={
|
|
"model": "gpt-3.5-turbo",
|
|
"messages": [
|
|
{
|
|
"role": "system",
|
|
"content": "You are a helpful assistant. What is your name",
|
|
},
|
|
],
|
|
},
|
|
headers={"Authorization": f"Bearer {generated_key}"},
|
|
)
|
|
print(job_response.status_code)
|
|
print(job_response.text)
|
|
print("\nResponse from creating job", job_response.text)
|
|
job_response = job_response.json()
|
|
job_id = job_response["id"] # type: ignore
|
|
polling_url = job_response["url"] # type: ignore
|
|
polling_url = f"{base_url}{polling_url}"
|
|
print("\nCreated Job, Polling Url", polling_url)
|
|
|
|
# Step 3: Poll the request
|
|
while True:
|
|
try:
|
|
print("\nPolling URL", polling_url)
|
|
polling_response = requests.get(
|
|
url=polling_url, headers={"Authorization": f"Bearer {generated_key}"}
|
|
)
|
|
print("\nResponse from polling url", polling_response.text)
|
|
polling_response = polling_response.json()
|
|
status = polling_response.get("status", None) # type: ignore
|
|
if status == "finished":
|
|
llm_response = polling_response["result"] # type: ignore
|
|
print("LLM Response")
|
|
print(llm_response)
|
|
break
|
|
time.sleep(0.5)
|
|
except Exception as e:
|
|
print("got exception in polling", e)
|
|
break
|