phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity

(feat) proxy, use --model with --test

Browse source
This commit is contained in:
ishaan-jaff 2023-12-26 09:40:58 +05:30
parent 05b9b3aacd
commit d273d19bd9
1 changed files with 10 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

15
litellm/proxy/proxy_cli.py
View file

@ -321,7 +321,10 @@ def run_server(
print(json.dumps(response.json(), indent=4)) print(json.dumps(response.json(), indent=4))
return return
if test != False: if test != False:
click.echo("\nLiteLLM: Making a test ChatCompletions request to your proxy") request_model = model or "gpt-3.5-turbo"
click.echo(
f"\nLiteLLM: Making a test ChatCompletions request to your proxy. Model={request_model}"
)
import openai import openai
if test == True: # flag value set if test == True: # flag value set
@ -331,7 +334,7 @@ def run_server(
client = openai.OpenAI(api_key="My API Key", base_url=api_base) client = openai.OpenAI(api_key="My API Key", base_url=api_base)
response = client.chat.completions.create( response = client.chat.completions.create(
model="gpt-3.5-turbo", model=request_model,
messages=[ messages=[
{ {
"role": "user", "role": "user",
@ -342,10 +345,12 @@ def run_server(
) )
click.echo(f"\nLiteLLM: response from proxy {response}") click.echo(f"\nLiteLLM: response from proxy {response}")
print("\n Making streaming request to proxy") print(
f"\n LiteLLM: Making a test ChatCompletions + streaming request to proxy. Model={request_model}"
)
response = client.chat.completions.create( response = client.chat.completions.create(
model="gpt-3.5-turbo", model=request_model,
messages=[ messages=[
{ {
"role": "user", "role": "user",
@ -358,7 +363,7 @@ def run_server(
click.echo(f"LiteLLM: streaming response from proxy {chunk}") click.echo(f"LiteLLM: streaming response from proxy {chunk}")
print("\n making completion request to proxy") print("\n making completion request to proxy")
response = client.completions.create( response = client.completions.create(
model="gpt-3.5-turbo", prompt="this is a test request, write a short poem" model=request_model, prompt="this is a test request, write a short poem"
) )
print(response) print(response)