Can't request model from a model server

Hi, i want to run a api server with the cmd “rasa run --enable-api --endpoints endpoints.yml --log-file api.log” and config the model server in the endpoints.yml, but i found the api server always load model from the local “models” directory, may be i have miss something, can anybody help me for this, any help will be appreciated! this is my endpoints.yml

# This file contains the different endpoints your bot can use.

# Server where the models are pulled from.
# https://rasa.com/docs/rasa/user-guide/running-the-server/#fetching-models-from-a-server/

models:
  url: "http://192.168.1.102:7020/model"
  wait_time_between_pulls:  10   # [optional](default: 100)

# Server which runs your custom actions.
# https://rasa.com/docs/rasa/core/actions/#custom-actions/

action_endpoint:
  url: "http://localhost:5055/webhook"

# Tracker store which is used to store the conversations.
# By default the conversations are stored in memory.
# https://rasa.com/docs/rasa/api/tracker-stores/

#tracker_store:
#    type: redis
#    url: <host of the redis instance, e.g. localhost>
#    port: <port of your redis instance, usually 6379>
#    db: <number of your database within redis, e.g. 0>
#    password: <password used for authentication>

tracker_store:
    type: mongod
    url: mongodb://localhost:27017
    db: rasa
    username: test
    password: test

I have read the source code rasa/core/agent.py, the “load_agent” function will check local “model_path” and then “model_server” config and then “remote_storage” config, it seems not the same order as the docs said.

the docs said: https://rasa.com/docs/rasa/user-guide/running-the-server/#running-the-http-server

I found this issue has been fixed when i upgrade the rasa from 1.1.4 to 1.2.2.it work perfectly now :smile:

1 Like

Hello, apart from what you published, did you used some action to or specific protocol to fetch the model from a model server?

Thank you!