rasa

问题 I am trying to deploy a rasa project described like here to google app engine, But the build failed due to some permission issues The scripts try to create a folder inside container, FROM rasa/rasa ENV BOT_ENV=production COPY . /var/www WORKDIR /var/www RUN rasa train ENTRYPOINT [ "rasa", "run", "-p", "8080"] I have added following permissions to google cloud build. Error log frome cloud build. Epochs: 100%|██████████| 100/100 [00:16<00:00, 6.04it/s, t_loss=1.485, i_loss=0.104, i_acc=1.000]

问题 I am intalling Rasa X in a Python 3.7 conda environment on Windows 10. pip version is 20.3.3. pip3 install rasa-x --extra-index-url https://pypi.rasa.com/simple It have been going on for 5-6 hours and seems to be confused: Any idea what I can do to fix this? 回答1: It is caused by the dependency resolution backtracking logic introduced in pip v20.3. (docs) A fix for now is to downgrade pip to v20.2, with: pip install --upgrade pip==20.2 回答2: Instead of downgrading pip you can also use the old

问题 I am intalling Rasa X in a Python 3.7 conda environment on Windows 10. pip version is 20.3.3. pip3 install rasa-x --extra-index-url https://pypi.rasa.com/simple It have been going on for 5-6 hours and seems to be confused: Any idea what I can do to fix this? 回答1: It is caused by the dependency resolution backtracking logic introduced in pip v20.3. (docs) A fix for now is to downgrade pip to v20.2, with: pip install --upgrade pip==20.2 回答2: Instead of downgrading pip you can also use the old

问题 based on the story below: ## certif deny_repeat_affirm_stop * greet - utter_greet * request_certificate - certificate_form - form{"name": "certificate_form"} - form{"name": null} - utter_did_that_help * deny - utter_ask_again * request_certificate - certificate_form - form{"name": "certificate_form"} - form{"name": null} - utter_did_that_help * affirm - utter_noworries * goodbye - utter_goodbye - action_restart i need to post (rest api) the form to an service, how can i do that from actions

问题 based on the story below: ## certif deny_repeat_affirm_stop * greet - utter_greet * request_certificate - certificate_form - form{"name": "certificate_form"} - form{"name": null} - utter_did_that_help * deny - utter_ask_again * request_certificate - certificate_form - form{"name": "certificate_form"} - form{"name": null} - utter_did_that_help * affirm - utter_noworries * goodbye - utter_goodbye - action_restart i need to post (rest api) the form to an service, how can i do that from actions

问题 Iam getting the below error ModuleNotFoundError: No module named 'rasa_nlu', even though i installed rasa_nlu and rasa My code : from rasa_nlu.training_data import load_data from rasa_nlu.config import RasaNLUConfig from rasa_nlu.model import Trainer def train_nlu(data, config, model_dir): training_data = load_data(data) trainer = Trainer(RasaNLUConfig(config)) trainer.train(training_data) model_directory = trainer.persist(model_dir, fixed_model_name='weathernlu') if __name__ == '__main__':

问题 When I run rasa init --no-prompt I am getting the above error. I am not able to debug the cause for this error, Above are the commands I have used to install Rasa. pip3 install rasa pip3 install --upgrade tensorflow rasa pip3 install --upgrade tensorflow-addons rasa pip install --upgrade pip pip3 install --upgrade tensorflow-addons rasa --use-feature=2020-resolver Above are my details of the versions used Rasa version: 1.10.10 Python version: 3.6.9 Operating system Ubuntu 18.04.4 64 bit

问题 Web bot is integrated in javascript based website ,when user login in website then they can access the chatbot icon. When they open it chatbot starts ,but currently it doesn't collect user data . But , now user data is important because further we want to call actions based on user id. If we will be able to know the user id then we can send the specific query to user from bot. If user is US based then bot should only reply US region based data ,but if user is APAC then bot should only provide

问题 def get_nlg(graph_query): driver = Graph("neo4j://localhost:7687", auth=("neo4j","password")) graph_response = graph.evaluate(graph_query) For the above code, I replaced with the driver code as below, but its not working, what is the function in neo4j driver equivalent to evaluate() function in py2neo? def get_nlg(graph_query): driver = GraphDatabase.driver("neo4j://localhost:7687", auth=("neo4j","password")) with driver.session() as session: graph_response = session.run(graph_query) return

问题 def get_nlg(graph_query): driver = Graph("neo4j://localhost:7687", auth=("neo4j","password")) graph_response = graph.evaluate(graph_query) For the above code, I replaced with the driver code as below, but its not working, what is the function in neo4j driver equivalent to evaluate() function in py2neo? def get_nlg(graph_query): driver = GraphDatabase.driver("neo4j://localhost:7687", auth=("neo4j","password")) with driver.session() as session: graph_response = session.run(graph_query) return