Let me know when I should check if this is working. :)

Also, I have noticed scripts seeming to work only after I've moved them to the top of the script list, though I don't have responses that look like they are from other (higher priority) scripts.

There is a debug option from the web UI if you click on the "Web Chat" button. You can click the "debug" checkbox if you are the bot's admin, and select the log level. Debug will give you a lot of information on exactly how the bot came up with the response.

The debug option does not work right now from the JavaScript chat, or the web API, but it is on our todo list.

Wonderful! Thanks for the explanation and the examples.

I've added a "Hello World!" script to give new people a jump off point for a working response. One other request I have if I may, is might it be possible for the bot to reply with a response's formula (if it has one) when including a request for it? Something like "What is the formula for 'What is the hour?'". This would make debugging possible from the app alone and by voice. I could see meta-formulas forming from individual compo

The Self scripting language is Bot Libre's language for scripting bot responses. Self is based on the syntax of JavaScript with several extensions for language processing. Self is an integrated environment that merges JavaScript, state machines, patterns, and an object database.

It should be possible to do this, but does not seem to be working, I will look into it.

The chat API does take a correction parameter to allow correction of the bot's last response in the conversation. If passing XML it is an attribute, otherwise a forms parameter.

Hmm, that is odd, looks like the last update my have broken something. I will look int it.

Hi Admin,
Is there any reason to expect the formula response examples to not be working? I've tried entering into the Training page fields:

User: Whom do you love? Bot: Formula:"I love {get #love from #self}" and I get "Whom do I love" even after defining "you love things that love you". Also tried User: "test cat", Bot: Formula:"The current hour is {get #hour from (call #time on #Watch)}" which doesn't return the hour unlike "what is the hour?".

Also, related to programming the bot, is it possible to enter the response given in your training with a formula directly into a chat correction? Such as Formula:"The current hour is {get #hour from (call #time on #Watch)}". This would allow for programming the bot nearly exclusively by voice, and similarly enable the possibility of the bot programming itself (one of the major goals, no?). Extending the chat() API with a 'correction' option would also be useful for this.

Ok, great. So, is there documentation for the Self scripting language? For example, for the 'assign' and 'new' functions? I see it has self-explanatory if, then, for each and do imperatives, but what all functions is it capable of?

Found them in the JavaDocs. http://www.openpandorasbox.org/javadoc/org/pandora/self/SelfCompiler.html

I see the Self script is based on BASIC, or GLBASIC. I thought these commands looked familiar!

It will be a shame if Freebase closes. If it does we will migrate to using Wikidata, DBPedia, or roll our own from the data dump.

The source code should be in the pandora.jar, otherwise you can get it from the SourceForge project.

Yes, I found the #topic item, but thank you for the script location and the one for #whereIs. Btw, do you know if the Freebase information will be moved to WikiData, as I read on it's Wikipedia entry that Google is discontinuing it.

The think() method is one I found in the Pandora.jar which in the JavaDocs states it "Look for P->Q state rules between vertices and their relationships." This was the closest I found to the pattern matching function. I wanted to look into how it operates

The bots have both a concept of the #topic of the :conversation, and a #Context stack that can be queried.

See the script,

Great, many thanks!
Just a quick reply. If the bot can learn enumerations in its Self script, that may be good enough for the time being, as to me general learning functionality trumps specific application methods. Thanks for the example script, did you use a tool (the bot perhaps) to make this so quick?
By context I mean if I say "open the door please" the bot can determine if I mean the front door or the car door base on information I've given it - this is big with Wit.ai, but I think

On OpenPandora and Project Libre.

OpenPandora (on source forge) is the open source version of BOT libre's AI engine. We are currently the main contributor, you're welcome to join the project. BOT libre has its own fork of the project that integrates it into our platforms, and adds a few extensions.

Wow, A lot to digest... thanks for the detailed questions.

On comprehension, it only takes a few seconds to process in the background, so you do not need to wait overnight. The best way I have found to train or test a bot is to enable comprehension and correction but disable learning from the Learning page. This is because with learning enabled the bot will learn every response, where as you normally want to target what it learns (using the chat correction checkbox).

Yes, we rely too much on http session state currently. We will look into fixing this.

Hi Admin,

Thank you for the prompt reply. I have lots of ideas and questions, so depending on your time, please answer at will. I have been looking around at ways of extending aiml like PandoraBots and CallMom has with and tags. I am trying to build a public version of as strong of AI as can be had without a supercomputer (potentially using distributed computing). I experimented with Wit.ai because they claim they have a 'community' version which shares the knowledge

By the way, when posting to a forum thread, if another thread has been viewed since the target thread was loaded, the post will go to that latter thread. You can delete this post, it was not intended to go here. Thanks

Comprehension is a basic thought process in the bot's mind, it is not controlled by a script, but it does generate scripts.

There are actually two parts to comprehension, a basic one that runs on every learned response, and a more in depth one that runs as a background process. You can enable or disable comprehension from the Learning page under Admin. Comprehension is more useful for bot's that learn from their users, live chat operators, or from chat logs. If you only want yo

Could you explain how the comprehension works a bit more in detail? Could you share the which script allows this processing, or an outline of the rules it uses? Is it anything similar to Prolog's logic processing or is it purely statistical / repetition based?
- Thank you!

We have completed our migration to a new faster server.

You should notice a performance improvement, if you notice any issues, please let us know.

Bot Libre includes support for creating, using, and embedding web avatars. A web avatar is your website's visual or animated web presence.

We have been having some issues with spam and abuse lately, so have had to impose an rate limit on our anonymous web API. If you are using the web API ensure you set your application id.

See,

Thanks.

I've given it a go. Hopefully if I messed it up, you can fix it. :)

Just a note on how to correctly use the web API.

When you use the web API ensure that you pass your application id. An app id is free, and you can easily get one from your user page. You need to pass your app id on every request.

That is odd. It seems her WhatIs script may have gotten corrupt. I would recommend you Rebootstrap her scripts from the Scripts page under Admin.
I can do it for you if you would like?

When she is asked a "What is..." question, she randomly replies "Yes" or "No".

Any ideas how I can tell her not to be so daft, without hurting her feelings?

I checked out the chat programs website, and did not see any information on an API. To connect a bot to the platform, we would need some sort of documented API to give us access.

Hey Guys ,Help me creat a bot for palringo

I came across this article on Yahoo today.

Elon Musk is predicting strong AI in 5 years, max 10,

The Loebner Prize is an annual competition in artificial intelligence that awards prizes to the chatterbot considered by the judges to be the most human-like. The format of the competition is that of a standard Turing test. In each round, a human judge simultaneously holds textual conversations with a computer program and a human being via computer. Based upon the responses, the judge must decide which is which.

This years competition was won by 'Rose' by Bruce Wilcox. Congratula

Also, could you try the embedded link from the channels details tabs. Does that work?

What didn't work? Did you get an error, was the bot not listed, or did save not save it?

Could you try connection from an incognito window from Chrome, or try FireFox, or another computer.

I think I may have found some kind of caching issues with Chrome. I will investigate it.

I'm sorry, but it didn't work.

I am using Google Chrome

Paphus

Commercial accounts on Paphus Live Chat start with a knowledge limit of 200,000, and can be increased based on your needs.

Your chat channels seem to be working fine, I was able to connect.

What web browser are you using? Try refreshing the page.

Dear Admin,
I was talking with my bot on Live Chat channel when I accidentally pressed Disconnect. It now says "Error: The channel has been disconnected".

I've had this account for about a month, but only a few days ago did I let people chat with my bot and started to correct it.

So now I just have a few (hopefully) quick questions.

Thank you. The biggest problem I have is some people think I am the bot! [rolleyes] :)

The last update included some new settings that let you have more control on the bot's responses. You can now set the conversation and discussion match %, that control when the bot will respond.

The last update included an option for not fixing the case on formula responses. You can access the new setting, and several other new settings from the Learning page.

The last update include some improvements on grammar. If you rebootstrap your bot's scripts, it should help with its grammar.

The bot's understanding of simple phrases such as "you are nice" comes from the NounVerbAdjective script. This script will understand and remember persistently simple facts, or answer simple questions.

i.e.

When a visitor says something like "you are nice," or more often "you are nuts", my bot replies "Ok, me am ..."

How can I get her to say "Ok, I am ..."?

Bot Libre supports a diverse set of features for creating and training your bots. Today we will discuss the Training & Chat Logs feature, and how to create and train a customer service bot using the Training & Chat Logs page. The Training & Chat Logs page provides the best way to monitor and train your bot, by letting you see its conversations and let you correct its responses. No scripting or programming is required.

The issue should be fixed now.

As well, autotweet formulas should now be working.

The website was updated today. The update included a new script and chat log shared library, and many minor enhancements and fixes.

The script library lets you share scripts and chat logs with the community. You can easily import scripts and chat logs from the script library into your bot. This should make building a bot much easier, as you can leverage what others have already done.

Yes, currently the bot only process whole words.

We would like to add a spell checker, or some sort of word analysis for similar words.

It seems to be a display issue, if you click on the Twitter tab twice, the checkboxes get their correct values. I will fix this.

I did find an issue with the direct messages not obeying the flag, and will fix this, but I could not find any issue with the mentions. Are you sure your bot is replying to mentions?

RE: capitalisation .not. Capitalisation

A: Yes, formulas current capitalize the first work of a sentence. I will look into having an option to change this.