Difference between Rasa core and Rasa nlu

Question

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

Answer 1

@trinca's answer is correct. I just rephrase a bit the points

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.

No, NLU/Core are not different approaches, rather, these are different components of a dialog manager engine.

1. RASA NLU is a intent/entities classifier:

   You off-line trains the classifier with a number of examples sentences with attached relative intent (and entities) tags.

   Afterward, at run-time, you submit to the classifier an incoming sentence and you have back an intent tag and a list of possible entities related to the intent, as result of the classification.

2. RASA Core is a (probabilistic) dialog manager:

   It decides/guess which is the next probable "state" (again just an intent) of the chatbot conversation. It's off-line trained with a RASA specialities: "stories". These are possible sequences of intents, following examples of conversation that developers submit in the train phase.

   Afterward, at run-time, RASA Core, when a user submit a sentence (so a corresponding intent guessed bu previous mentioned NLU component) it guess the "probable" next state of the conversation (an intent).

Notes:

IMMO you can't build a chatbot with just the NLU (an intent classifier) component proposed by many competitors as the "solution" to build bots), because with just the intents classifier (The NLU) you can manage just "stateless" dialogs (single turn volleys without any context of the conversation).

An the end of the day RASA is winner in comparison with other mentioned frameworks (these are often just channel gateways/intente classifiers) because the dialog manager component and the stories way to design/develop a conversation, without hardcoded rules (if/then).