16efb1316c
* feature(intelligent-search): Added API to connect to Llama.cpp in EC2 and filter the response into OR filters * updated sql to filter script and added init.sql for tables * feature(intelligent-search): Changed llama.cpp for llama in GPU now contained in API * Updated Dockerfile to use GPU and download LLM from S3 * Added link to facebook/research/llama * Updated Dockerfile * Updated requirements and Dockerfile base images * fixed minor issues: Not used variables, updated COPY and replace values * fix(intelligent-search): Fixed WHERE statement filter * feature(smart-charts): Added method to create charts using llama. style(intelligent-search): Changed names for attributes to match frontend format. fix(intelligent-search): Fixed vulnerability in requiments and small issues fix * Added some test before deploying the service * Added semaphore to handle concurrency --------- Co-authored-by: EC2 Default User <ec2-user@ip-10-0-2-226.eu-central-1.compute.internal>
24 lines
799 B
Python
24 lines
799 B
Python
from fastapi.testclient import TestClient
|
|
from main import app
|
|
from decouple import config
|
|
from os import path
|
|
|
|
|
|
client = TestClient(app)
|
|
|
|
|
|
def test_alive():
|
|
response = client.get("/")
|
|
assert response.status_code == 200
|
|
|
|
def test_correct_download():
|
|
llm_dir = config('CHECKPOINT_DIR')
|
|
tokenizer_path = config('TOKENIZER_PATH')
|
|
assert path.exists(tokenizer_path) == True
|
|
assert path.exists(llm_dir) == True
|
|
|
|
def test_correct_upload():
|
|
with TestClient(app) as client_statup:
|
|
response = client_statup.post('llm/completion', headers={'Authorization': 'Bearer ' + config('LLAMA_API_AUTH_KEY', cast=str), 'Content-Type': 'application/json'}, json={"question": "Show me the sessions from Texas", "userId": 0, "projectId": 0})
|
|
assert response.status_code == 200
|
|
|