This message was deleted.

Can you check your bento name?

My bento name is “ner_classifier:latest”, is that problem?

What is the name of your model?

My model name is “ner_id:latest”

Could you give me the output of this command?

bentoml get ner_classifier:latest

For this, i hacked the database and set the character limit to large value. One of my columns had a long string , 🤔that's what I remember

@ABC What is the name of the model and why does it have the chance to exceed the length of 128?

Tbh i don't know as model was developed by a data scientist and I was in rush to simply test that in bentoml, so it was not possible for me to ask to many change in the model as the same model was deployed over databricks mlflow and it was running already. *It was all mlflow models , xgboost, lightgbm and based on Hyperparameter

@ABC Thanks for your reply, I will increase the length of this field to 256 in the next version, I don't know if it will meet your needs

I fixed it anyway on db level but why is there any limit and if there is a limit, shouldn't be there any api to increase with proper warning

@ABC The length limit is added for better indexing

@Xipeng Guan is there any doc available to know what to do when we get this issue ? In cases like mine, it's almost impossible to make any changes in the ds model , so as infrastructure, what can be done

@ABC But the name of the model is set when writing bento, just add a length limit to the model name in the BentoML code

I remember I changed this and other in different columns in the database, will try to replicate that and update here

@Xipeng Guan this is what I get:

(training) root@ai-platform-research2 /home/rahmat/serving $ bentoml get ner_classifier:latest

service: service:svc

name: ner_classifier

version: iycz3mufb25hy44o

bentoml_version: 1.0.12

creation_time: '2022-12-26T11:13:09.157888+00:00'

labels:

owner: personal

stage: staging

models:

- tag: ner_id:il44jbufb25hy44o

module: bentoml.mlflow

creation_time: '2022-12-26T11:13:01.806933+00:00'

runners:

- name: ner_id

runnable_type: MLflowPyfuncRunnable

models:

- ner_id:il44jbufb25hy44o

resource_config: null

apis:

- name: classify

input_type: JSON

output_type: JSON

docker:

distro: debian

python_version: '3.8'

cuda_version: null

env: null

system_packages: null

setup_script: null

base_image: null

dockerfile_template: null

python:

requirements_txt: null

packages:

- pydantic

lock_packages: true

index_url: null

no_index: null

trusted_host: null

find_links: null

extra_index_url: null

pip_args: null

wheels: null

conda:

environment_yml: null

channels: null

dependencies: null

pip: null

, Thanks

@kurniarahmatt

alter table "model_repository" alter column "name" type varchar(256);

Oke, thanks lot.