This message was deleted.
# ask-for-helps
Slackbot
10/19/2022, 9:09 PMThis message was deleted.
🏁 1
🍱 1
a
Aaron Pham
10/19/2022, 9:13 PMcan you install bentoml from pip instead of conda? we don’t currently maintain the conda package for bentoml and it is outdated with the most current release.
r
raki
10/19/2022, 9:17 PMI did pip install bentoml
a
Aaron Pham
10/19/2022, 9:17 PMcan you send the whole trace stack here?
r
raki
10/19/2022, 9:20 PMwhat do you mean
a
Aaron Pham
10/19/2022, 9:22 PMI mean the output on the terminal when you run
bentoml serve service.py:svcr
raki
10/19/2022, 9:24 PM(base) C:\Users\dimi\bento_deploy>bentoml serve service.py:svc
C\Users\dimi\anaconda3\lib\site packages\paramiko\transport.py219: CryptographyDeprecationWarning: Blowfish has been deprecated
"class": algorithms.Blowfish,
2022-10-20T001524+0300 [INFO] [cli] Prometheus metrics for HTTP BentoServer from "service.py:svc" can be accessed at http://localhost:3000/metrics.
2022-10-20T001525+0300 [INFO] [cli] Starting development HTTP BentoServer from "service.py:svc" running on http://0.0.0.0:3000 (Press CTRL+C to quit)
a
Aaron Pham
10/19/2022, 9:25 PMcan you share your service code?
r
raki
10/19/2022, 9:26 PM Copy code
import bentoml
from <http://bentoml.io|bentoml.io> import JSON
model_ref = bentoml.xgboost.get("credit_risk_model:latest")
dv = model_ref.custom_objects['dictVectorizer']
model_runner = model_ref.to_runner()
svc = bentoml.Service("credit_risk_classifier", runners=[model_runner])
@svc.api(input=JSON(), output=JSON())
def classify(application_data):
vector = dv.transform(application_data)
prediction = model_runner.predict.run(vector)
print(prediction)
result = prediction[0]
if result > 0.5:
return {"status" : "DECLINED"}
elif result > 0.23:
return {"status" : "MAYBE"}
else:
return {"status" : "APPROVED"}a
Aaron Pham
10/19/2022, 9:27 PMnext time you can use triple backticks to format the code block 😄
Copy code
this is using triple backtickAaron Pham
10/19/2022, 9:27 PMThis warning is not related to bentoml then