These responses are most likely coming from your bot's NounVerbAdjectiveStateMachine or Understanding script. You seem to have many duplicate scripts, you should delete the duplicates, or rebootstrap your bot's scripts and re add the ones you want.

Your bot is very old (2014), and Bot Libre has evolved since then, so you may also consider rebuilding your bot.

To rebuild a bot do the following:

So basically I was talking to my bot, and then the grammar problems started... This keeps happening all the time

Quotation:

You: Hi there

the redirect script does not work with the random tag.

thankyou that worked.

Looking at your bot, your greeting redirects to the question "script_hour" but you have no response for this.

In your script the pattern should be "script_hour" not "hour".

this is what Sheila bing greeting is now.wait here.walks away down the hallway.comes back 30 minutes.here is your script_hour on a tray. 

i have a a aiml script called hour and it has hour as a pattern.

put in the search Sheila bing rating= mature

okay I did not know that.

So a "redirect" send the redirect text as a message to the bot and returns the response.

For example if a bot had a script that had the pattern "hello" and returned "hello world", then in a Template redirect("hello") would return "hello world".

This script is what I was talking about.

 

Template("{ redirect("script_greeting") }")

I have tested this, and it does work.

I'm not sure what you tried.

redirect to a script does not work because the default response overrides it.

As with any regression testing, changes to code and functionality can affect previous results. That is the entire point of regression testing. If changes never affected existing results, then there would be no point to regression testing.

Thanks for your answer.

Synonyms support was added in 6.5, so is not available in 6.1.

If you enable the Wiktionary sense in your bot (even in 6.1) it will automatically import word meta data from Wiktionary (English) when it encounters new words. This includes if the word is a noun/verb/adjective and its synonyms.

Hi,

For Synonums, I didn't catch your point. How do i do below things? Is it possible with current SDK version 6.1?

Synonyms are global, so can be defined once, and apply to all of the bot's responses. 

Synonyms can be automatically loaded from Wiktionary as the bot learns new words. 

If you upload AIML from a file or our script library it gets the file/script name.
If you create a new AIML script from the bot's scripts it will be named 'aiml', to have a different name, first save it as a Self script with the name, then change the code to AIML.

that is good to know.But how do I rename a aiml script after I have made it.Because most of my new scripts I made are just called aiml.

Bot Libre's NLP does not use deep learning, but a similar machine learning algorithm that allows the bot to analyse the words in a user's input and match it to one of its trained questions and response.

To run code in a greeting there are 2 options, use a Template, or use a redirect.

For example, for a Template you can use something like:

Template("{var hour = Date.get(Date.date(), #hour); if (hour < 10) { "Good morning." } else if (hour > 18) { "Good evening." } else { "Good day." } }")

For a redirect, you use a Template in your greeting that does a redirect to a response that is handled by a script.

I understand that Bot works based on script and some additional intelligence applied to find related answer for the user question. Can I know which specific aspect of BotLibre is based on deep learning? 

I figured out how to make  the chatbot know the hour with the greeting.so it can ask if you want breakfast, dinner or lunch.i am going to use that for that.

can I run a self script in a greeting?

Even without keywords, adding new response will affect what response a bot chooses, if the new response better matches a question by the user.

A response will always be used for the question it was add for, but for similar questions the bot will always try to find the best matching response. To have a response used for many variations of a question, define an intent label for the response and add it as the response for the valid variations.

Hi,

Thanks for quick reply.

I see 2 changes in your suggestion.  1) Additional question with "policy" word added and 2) set "life" as keyword (which should be in both question I think).

With these changes, now it will work fine. However, my point is how do I avoid such regression?

Earlier I had just first 2 questions in script file. Without having question  "what is insurance policy?" in script file, below were answers

Note that, "what is life insurance policy" equally matches "what is life insurance" and "what is insurance policy", so even without the keyword, the bot may use either response.

I would recommend you also add "life" as a keyword to the first response.

Also, if you want "what is life insurance policy" to use the first response then add it as a valid question for this label as well.

Though mentioning keywords is very useful I find very dangerous too.  e.g. I have 2 questions  

what is life insurance?
this is answer for life insurance

what is standard cover in policy?
answer for standard cover
keywords: standard

This works fine and give answer if someone ask "what is life insurance policy". (Assume I didn't consider adding policy as word in question).

that worked I look at it wrong in the documentation.

This error say use are missing an end tag. Your AIML is not valid AIML or even XML.

Change </star> to <star/>

Your original code works fine, but the code in your error is different.

What error do you get?

We are planning to update our SDK to Bot Libre 7 next month.

Google dropped API.AI and replaced it with DialogFlow.

You can integrate a Bot Libre for with Dialog Flow using a "proxy" bot on Bot Libre that forwards requests to the DialogFlow web REST API using a Self script that uses the Http class.

I need a help with my project, i need to do a chatbot using API.AI and conected to an avatar 3d of botlibre

My E-MAil [email protected]

that worked.has a chatbot been made before that can decide whether it likes or dislikes something.I am going to adapt this to make my  my chatbot choose whether it has something the user says they have.i want to use this with a set if possible. 

For also remembering like vs dislike, you would need another property to store this.

Something like.

how can dump the memory of what has been learned from this script.i want to start over. 

what do you mean by take responsibility for the next generation.

I need it to randomly select like or dislike ounce.

it is not choicing whether it likes a state or not.it is supposed to chose.it is saying I like Canada and I do not like Canada if I ask it over

and over again.

okay I will try it.

Looking at your bot you have an AIML pattern for "who lives * you", the template should be as follows.

Note my previous example was missing the #self.country at the end.

i fixed your script by looking at the debug.but your aiml script does not do anything.sheila strong is in the entertainment category.

type when talking to here where do you live.then enter it.then type who lives there with you then enter it.

it just says I do not know.

your aiml script spits out an error.did you test it?

What do you mean by "writing first"?

A bot has a "greeting" if set the bot will start the conversation with the greeting. If you delete its greeting, then it wait wait for the user to ask a question.

Well, I'm not certain what you are trying to do, but maybe try something like:

<category> <pattern>where * live</pattern> <template> <random>
<li I like <self>if (#self.country == null) { #self.country = random("USA", "Canada", "Mexico"); }; #self.country</self></li>

Hello! I want to ask a question - How do I prevent a bot from writing first?

Thank!

I can do it with that in aiml but what the chatbot decides to like or not is remembered as long as the conversation.that is a partial

solution.

your aiml script does not remember random choice.If you keep asking the chatbot if it likes the state it will change it's mind.

this does not make the chatbot remember it's random choice.

You could use some Self in your AIML like: <category> <pattern>where * live</pattern> <template> <random>
<li I like <self>var country = random("USA", "Canada", "Mexico"); #self.like =+ country; country</self></li>

There are several examples above.
What exactly are you trying to do, and what code do you have so far?

how would i implement this?

could someone help me with this?Or show me how to do it in aiml script?