rasa-core

How rasa_nlu using lookup_tables for entity extraction?

由 百般思念 提交于 2020-01-16 08:16:08
问题 I am trying to develop a chatbot using rasa nlu and rasa core. But I am not getting the link how rasa_nlu using lookup_tables for entity extraction. I had already go through (http://blog.rasa.com/improving-entity-extraction/) link but not getting it. How should lookup_table used for to extract the entity? 回答1: Requirements : If you want to use lookup tables, make sure: you have the components intent_entity_featurizer_regex and ner_crf in your NLU pipeline the entities you want to match fit

Rasa custom actions not connected

由 帅比萌擦擦* 提交于 2020-01-16 04:18:08
问题 So, I just started with Rasa this week, but I’m quite happy with the results so far, as in that it responds well et cetera. However, I now have custom actions in an actions.py file, but when I’m in the rasa shell it seems to miss that file entirely and asks for another input. (see the image below) It doesn't even give an error. What am I doing wrong? I tried to run "rasa run actions" in another terminal, with an action_endpoint in the endpoints.yml file. In the endpoints file: `action

How to identify multiple entities in RASA

由 南笙酒味 提交于 2019-12-24 10:37:15
问题 I want to extract multiple entities from a user input. Example- "Service httpd is not responding because of high CPU usage and DNS Error" So here I want to identify below: Httpd High CPU usage DNS Error And I will be using this keywords to get a response from a Database. 回答1: Just annotate them accordingly, e.g. ## intent: query_error - Service [httpd](keyword) is not responding because of [high CPU usage](keyword) and [DNS Error](keyword) Having the sentence from above, Rasa NLU would

How to use Hindi Model in RASA NLU?

由 倖福魔咒の 提交于 2019-12-24 10:29:31
问题 I have build my model for Hindi language using FastText with spacy backend. I followed this tutorial to to build my model using FastText. This URL I have also linked my model with spacy by following command python -m spacy link nl_model hi Model is linked successfully you can check in the image below Now I am not finding any help for using hindi language, Like what kind of config files do I need to use, where to import hindi model and how to proceed now? I also have question like how our data

Make train-core // Import Error : DDL Load failed

由 不打扰是莪最后的温柔 提交于 2019-12-11 16:46:18
问题 I wanted to get the starter-pack-rasa-stack https://github.com/RasaHQ/starter-pack-rasa-stack working for me. While trying to make train-core I encountered a Problem with DDL load. I want to say that I am using the german Version of spacy_sklearn, if this makes any difference. Traceback (most recent call last): File "C:\Users\Yannic\AppData\Local\Programs\Python\Python36\lib\runpy.py", line 193, in _run_module_as_main "__main__", mod_spec) File "C:\Users\Yannic\AppData\Local\Programs\Python

Rasa. Wrong confidence score for non-related messages

由 那年仲夏 提交于 2019-12-11 08:10:14
问题 I’m building bot using rasa to response for user’s questions and I have an issue. Rasa gives me high level of confidence for messages that are completely not related to intent’s examples. I have medical-related intents but message like “I like coffee” gives me even more confidence than messages related. Also, random chars messages like “laj jfias jjlas fe” also give me high confidence. Could anyone give me a hint how to fix this? Where can I look for a bug? This is my config: language: "en"

Get Intent Value in RASA Core/NLU

由 不问归期 提交于 2019-12-10 16:31:54
问题 Greeting I am working on RASA chatbot. I am handling Custom actions for a particular intent using below code. In the custom action I want to get current intent value. SO i dont know that line of code which can give me value of current intent #this file will be used to all custom actions from __future__ import absolute_import from __future__ import division from __future__ import unicode_literals import requests import json from zeep import Client from random import randint from rasa_core

Difference between Rasa core and Rasa nlu

由 喜欢而已 提交于 2019-12-04 08:18:18
问题 I tried to understand about rasa from official documentation of Rasa core and Rasa nlu but not able to deduce much. What I am able to understand is Rasa core is used to guide the flow of conversation while Rasa nlu is to understand and process the text to extract information (entities) Second thing, there are examples to build chatbot in Rasa core as well as Rasa nlu both can be used to build chatbot but couldn't understand what's the difference in two approaches and when to follow which one.

Difference between Rasa core and Rasa nlu

由 时间秒杀一切 提交于 2019-12-02 22:18:53
I tried to understand about rasa from official documentation of Rasa core and Rasa nlu but not able to deduce much. What I am able to understand is Rasa core is used to guide the flow of conversation while Rasa nlu is to understand and process the text to extract information (entities) Second thing, there are examples to build chatbot in Rasa core as well as Rasa nlu both can be used to build chatbot but couldn't understand what's the difference in two approaches and when to follow which one. Could you please help me to understand in a better way. Trinca You got it right. Both work together

rasa core installation existing package found

由 烈酒焚心 提交于 2019-12-02 15:05:18
问题 I am downloading rasa core and the NLU. But installing rasa core is presenting a frustrating error I do not understand. pip install rasa_core Results in an error Installing collected packages: pyparsing, kiwisolver, matplotlib, rasa-nlu, graphviz, redis, fakeredis, decorator, networkx, fbmessenger, click, itsdangerous, flask, jsonpickle, h5py, Keras, tzlocal, apscheduler, websocket-client, slackclient, python-telegram-bot, ply, pandoc, packaging, snowballstemmer, alabaster, sphinxcontrib
订阅 rasa-core