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

(fix) proxy cli compatible with openai v1.0.0

Browse source
This commit is contained in:
ishaan-jaff 2023-11-13 10:58:18 -08:00
parent 16abdf44c9
commit e125414611
1 changed files with 14 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

27
litellm/proxy/proxy_cli.py
View file

@ -116,7 +116,7 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
print(f"ollama called")
run_ollama_serve()
if test != False:
click.echo('LiteLLM: Making a test ChatCompletions request to your proxy')
click.echo('\nLiteLLM: Making a test ChatCompletions request to your proxy')
import openai
if test == True: # flag value set
api_base = f"http://{host}:{port}"
@ -133,20 +133,21 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
"content": "this is a test request, write a short poem"
}
])
click.echo(f'LiteLLM: response from proxy {response}')
click.echo(f'\nLiteLLM: response from proxy {response}')
click.echo(f'LiteLLM: response from proxy with streaming {response}')
# response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
# {
# "role": "user",
# "content": "this is a test request, write a short poem"
# }
# ],
# stream=True,
# )
# for chunk in response:
# click.echo(f'LiteLLM: streaming response from proxy {chunk}')
print("\n Making streaming request to proxy")
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
{
"role": "user",
"content": "this is a test request, write a short poem"
}
],
stream=True,
)
for chunk in response:
click.echo(f'LiteLLM: streaming response from proxy {chunk}')
print("\n making completion request to proxy")
response = client.completions.create(model="gpt-3.5-turbo", prompt='this is a test request, write a short poem')
print(response)