New to Rasa? We’ve collected some of the best resources for beginners, to help you learn the basics and level up.
The Rasa stack consists of two main parts:
Rasa Open Source, an open source machine learning framework for building AI assistants.
Rasa X, a free tool to help you share your assistant with testers, see how users are interacting with your assistant, and improve your model by annotating new training data.
Start by visiting the Developer Portal. The Developer Portal includes a roundup of the most important resources and tutorials for learning about Rasa. You’ll find installation guides, as well as online courses and video tutorials.
The Rasa for Beginners series is another great starting point. It’s a free online class hosted on Udemy that covers the fundamentals of Rasa and helps you build your first assistant. We also recommend checking out our YouTube channel, where we add new videos weekly.
Lastly, don’t forget to check out the Rasa Blog. The Blog is the best way to stay up-to-date with the latest product updates, tutorials, and resources for conversational AI teams.
If you have questions along the way, you’re in the right place. Check out our guide to asking great questions for tips on using the forum to troubleshoot and share solutions.
Hello, thanks for this important space to solve questions. I am new to coding and even though I have finished some courses in Data Camp using Python I have not been able to install the Rasa NLU library as mentioned in the documentation (http://www.rasa.com/docs/nlu/0.13.1/installation/). I have tried installing it in my machine via terminal:
MacBook-Air-2:~ juansandino$ >>> pip install -r alt_requirements/requirements_full.txt
-bash: syntax error near unexpected token `>
Hello @Juste I have installed the SpaCy and TensorFlow Pipeline dependencies, However I have a question: I am planning to gather data to train my own model and i have read that the TensorFlow pipeline will be the best alternative, would you recommend I start with that one or with spaCy? And the other question is about mixing the pipelines, meaning using spaCy to identify organizations and personas and TensoFflow to identify custom entities, Can that be done?
it won’t work for me.
Error is “Command “python setup.py egg_info” failed with error code 1 in C:\Users\AARBOR~1\AppData\Local\Temp\pip-install-v2gsdeya\matplotlib”
Collecting tensorflow==1.10.0 (from rasa_core)
Could not find a version that satisfies the requirement tensorflow==1.10.0 (from rasa_core) (from versions: )
No matching distribution found for tensorflow==1.10.0 (from rasa_core)
Hi…I have a question regarding rasa nlu pipeline.I want to know if there is any basic difference between how spacy_sklearn and tensorflow_embedding pipelines operate under the hood.I mean tensorflow_embedding must also be using the same concepts of word embeddings,reducing the dimensionality of data using PCA etc. Is the only difference then that spacy_sklearn has some pre trained data to draw upon in the form of pre trained vectors and tensorflow pipeline does not?Is my understanding correct?Also how is tensorflow_embedding pipeline related to the tensorflow framework offered by google?
I dont know where to ask the question. I am new to the community and could not find any place to ask the question.So I posted it here.Could someone help me where to go on community to ask a question
I am having problems installing on a Mac Mojave 10.14.3, using python3 in my case since python defaults to 2.7.
pip3 install -U rasa_core
removing earlier messages ...error below..
Collecting tensorflow~=1.12.0 (from rasa_core)
Could not find a version that satisfies the requirement tensorflow~=1.12.0 (from rasa_core) (from versions: 1.13.0rc1, 1.13.0rc2, 1.13.1, 2.0.0a0)
No matching distribution found for tensorflow~=1.12.0 (from rasa_core)