Hi all, I’m currently using RASA 2.8.1. My project require me to call rasa train from the python script and then replace the currently used model with the newly trained one. Previously, I have used subprocess to call this line from a script rasa train --domain data I have 2 problems: Are there any way to call rasa train directly from the python code without going through bash? After training, how can I use the new model without restarting rasa server? Thank you all.

Here :slight_smile: RasaHQ/rasa/blob/main/rasa/server.py#L1335 model_server=model_server, remote_storage=remote_storage, endpoints=endpoints, ) new_agent.lock_store = app.agent.lock_store app.agent = new_agent logger.debug(f"Successfully loaded model '{model_path}'.") return response.json(None, status=HTTPStatus.NO_CONTENT) @app.delete("/model") @requires_auth(app, auth_token) async def unload_model(request: Request) -> HTTPResponse: model_file = app.agent.model_name app.agent = Agent(lock_store=app.agent.lock_store) logger.debug(f"Successfully unloaded model '{model_file}'.") return response.json(None, status=HTTPStatus.NO_CONTENT) @app.get("/domain")

can we write a separate python script and run this code? will it be able to unload previous models and place a new model? I want to do this job through jenkins, i.e train the new model and replace it with current one, not sure how to do it

I imagine you could. I’m investigating this now for a project in my company using MLFlow for versioning and deployment. I got the model path with model_path = training_results.model and then used that like this: requests.delete('server/model') requests.put('server/model', {"model_file":"/rasa/mlflow-rasa/{}".format(model_path)}) I’ll let you know how it goes

thanks for reply @jonathanpwheat , I’m successfully able to delete the current model on server by hitting api but unable to put or replace model when server is running, it will be really helpful if you find the answer

I’m getting the same result - doesn’t swap out without a restart I’ll keep digging and will let you know if I discover anything

Hi guys! Nice work at this thread! RASA api has endpoint to set current model with put request http://localhost:5005/model { "model_file": "/absolute-path-to-models-directory/models/20190512.tar.gz" } Replace the currently loaded model Sometimes, i upload model file using SFTP (filezilla) and use this API endpoint to replace the current loaded without restart the server

Thanks @itsjhonny Interesting. I tried what you had and was able to get just the single line “model_file” to work. I had been trying the whole object { "model_file": "/rasa/mlflow-rasa/models/20220615-144600-cruel-guide.tar.gz", "model_server": { "url": "http://localhost:5005/model", "params": {}, "headers": {}, "basic_auth": {}, "token": "", "token_name": "", "wait_time_between_pulls": 0 } } FYI I got that format from Rasa Open Source Documentation

Hi @itsjhonny , & jonathanpwheat Im trying to put model like this, import json import requests obj = { "model_file": "C:/Users/Akash/Desktop/MyChatbot/models/core-20220616-185933-soft-cycle.tar.gz" } print(obj) r = requests.delete('http://localhost:5005/model') print(r) # print content of request print(r.content) r = requests.put('http://localhost:5005/model', data = json.dumps(obj)) # check status code for response received # success code - 200 print(r) # print content of request print(r.content) and running this python script, I’m sure I’m going wrong but dont know whats the answer It would be great if you can tell me what i can do with this I’m trying this on localhost Thanks

@ShirudeAkash I didn’t have to delete the old model, it just swapped out the new one. The only difference I see is that I have headers in my call, everything else looks prett much the same My code actually trains a new model then swaps it out in the same script. So I get the model info from the training_results.model which is actually models/whatever-the-mode-is-named.tar.gz then I build the model_file complete absolute path and use that value in my data json object model_path = training_results.model model_file = '/rasa/mlflow-rasa/{}'.format(model_path) rasa_server_url = 'http://localhost:5005/model' headers = {'Content-Type': 'application/json'} data = { "model_file":'{}'.format(model_file) } request = requests.put(rasa_server_url, headers=headers, data=json.dumps(data), verify=False) You mention in your comments you’re getting a 200 code, are you certain it didn’t swap out the model? I ran rasa run -m models --enable-api --log-file out.log --cors "*" --endpoints endpoints-local.yml --credentials credentials.yml --debug so I could see it working when the new model was injected

@ShirudeAkash I was incorrect and updated my post. I ran rasa (in server mode) with rasa run -m models --enable-api --log-file out.log --cors "*" --endpoints endpoints.yml --credentials credentials.yml And used a separate chat client to interact with it. You can see the change here in the console of the server 2022-06-16 13:13:00 INFO rasa.core.processor - Loading model models/20220615-164453-pallid-island.tar.gz... 2022-06-16 13:13:01 INFO rasa.nlu.utils.spacy_utils - Trying to load SpaCy model with name 'en_core_web_md'. 2022-06-16 13:13:02 INFO rasa.nlu.utils.spacy_utils - Trying to load SpaCy model with name 'en_core_web_md'. 2022-06-16 13:13:27 INFO root - Rasa server is up and running. 2022-06-16 13:15:52 INFO rasa.core.processor - Loading model /home/jwheat/Code/NearlyHuman/rasa/mlflow-rasa/models/20220616-131544-piercing-platform.tar.gz... 2022-06-16 13:15:52 INFO rasa.nlu.utils.spacy_utils - Trying to load SpaCy model with name 'en_core_web_md'. 2022-06-16 13:15:53 INFO rasa.nlu.utils.spacy_utils - Trying to load SpaCy model with name 'en_core_web_md'.

hi @jonathanpwheat , thanks for the help, I have successfully solved the issue,

How to run training and replace current RASA model from python script

Rasa Open Source

kalpa916 (Kalpataru Sahoo) July 13, 2022, 3:34am 39

Thanks @jonathanpwheat

Topic		Replies	Views
Reloading a model in a running system using rasa_nlu.train Rasa Open Source	4	1065	August 27, 2018
Trouble replacing new models through the API Rasa Open Source	1	791	May 7, 2021
Train Rasa NLU without having to restart the server Rasa Open Source	21	2483	May 12, 2022
Order Rasa to train a new model through HTTP API Rasa Open Source	1	927	October 10, 2019
Upload a trained model Rasa Open Source	0	529	January 22, 2019

How to run training and replace current RASA model from python script

Related topics