apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-27 14:17:15 +02:00
Code Issues Projects Releases Packages Wiki Activity

Use intent model from archfc to pick prompt gateway (#328)

Browse source
This commit is contained in:
Shuguang Chen 2024-12-20 13:25:01 -08:00 • committed by GitHub
parent 67b8fd635e
commit ba7279becb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
151 changed files with 8642 additions and 10932 deletions
Download patch file Download diff file Expand all files Collapse all files

36
e2e_tests/test_llm_gateway.py
View file

@ -1,36 +0,0 @@
import json
import pytest
import requests
from common import LLM_GATEWAY_ENDPOINT, get_data_chunks
# test default llm
@pytest.mark.parametrize("stream", [True, False])
@pytest.mark.parametrize("provider_hint", [None, "gpt-3.5-turbo-0125"])
def test_hello_llm_gateway_llm(stream, provider_hint):
expected_llm = "gpt-4o-mini-2024-07-18" if provider_hint is None else provider_hint
body = {
"messages": [
{
"role": "user",
"content": "hello",
}
],
"stream": stream,
}
headers = {}
if provider_hint:
headers["x-arch-llm-provider-hint"] = provider_hint
response = requests.post(
LLM_GATEWAY_ENDPOINT, json=body, stream=stream, headers=headers
)
assert response.status_code == 200
if stream:
chunks = get_data_chunks(response)
assert len(chunks) > 0
response_json = json.loads(chunks[0])
assert response_json.get("model") == expected_llm
else:
response_json = response.json()
assert response_json.get("model") == expected_llm