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

(fix) proxy cli use openai v1.0.0

Browse source
This commit is contained in:
ishaan-jaff 2023-11-13 10:08:48 -08:00
parent a21ff38694
commit 18b694f01a
1 changed files with 18 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

34
litellm/proxy/proxy_cli.py
View file

@ -122,13 +122,12 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
api_base = f"http://{host}:{port}" api_base = f"http://{host}:{port}"
else: else:
api_base = test api_base = test
openai.api_base = api_base client = openai.OpenAI(
openai.api_key = "temp-key" api_key="My API Key",
print(openai.api_base) base_url=api_base
response = openai.completions.create(model="gpt-3.5-turbo", prompt='this is a test request, write a short poem') )
print(response)
response = openai.chat.completions.create(model="gpt-3.5-turbo", messages = [ response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{ {
"role": "user", "role": "user",
"content": "this is a test request, write a short poem" "content": "this is a test request, write a short poem"
@ -137,16 +136,19 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
click.echo(f'LiteLLM: response from proxy {response}') click.echo(f'LiteLLM: response from proxy {response}')
click.echo(f'LiteLLM: response from proxy with streaming {response}') click.echo(f'LiteLLM: response from proxy with streaming {response}')
response = openai.chat.completions.create(model="gpt-3.5-turbo", messages = [ # response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{ # {
"role": "user", # "role": "user",
"content": "this is a test request, write a short poem" # "content": "this is a test request, write a short poem"
} # }
], # ],
stream=True, # stream=True,
) # )
for chunk in response: # for chunk in response:
click.echo(f'LiteLLM: streaming response from proxy {chunk}') # click.echo(f'LiteLLM: streaming response from proxy {chunk}')
response = client.completions.create(model="gpt-3.5-turbo", prompt='this is a test request, write a short poem')
print(response)
return return
else: else: