Zabaware Support Forums

Zabaware Forums => Ultra Hal Assistant File Sharing Area => Topic started by: Spitfire2600 on July 31, 2018, 10:58:14 pm

Title: ConceptNet Mrk 3.5
Post by: Spitfire2600 on July 31, 2018, 10:58:14 pm
ConceptNet was originally developed by MIT to add a significant boost to deductive reasoning of AI through the use of understood concepts, such as "Fire is hot" "Carbon is an element" and use this information to problem solve. 

This version also includes a prototype markup of what I am calling "MutationNet MrkI"


MutationNet works to facilitate the "problem solving" part of ConceptNet. It takes a few different inputs, catches nouns, compares them, then crams comparative sentences together. I'm experimenting with other more effective methods, but I did want to release this to gather some input to better this program. Also, if anyone would like to build upon this, feel free and please do let me know what you come up with so I can add it into the program. If anyone is more familiar with MIT's ConceptNet, I would love to hear your thoughts as well.




Installation: (Please remove any previous versions of ConceptNet first)
1. Open Zip. Extract contents as they are to Hal directory  ("C:\Program Files (x86)\Zabaware\Ultra Hal 7")  - There will be 2 UHP files, one folder, and one DB file. Copy these right into the Hal Directory.
     If your directory is not the above, you will need to change this in the UHP file labeled "ConceptNetMrkIII Auto Learning.uhp" on line 35.
2. Enable both ConceptNetMrkIII plugins.
3. Tell Hal to "Build ConceptNet" and he will create the appropriate tables. Relaunch Hal. Just to check, he should have created a folder named "conceptNet" with 2 tables inside in your Hals brain. The TopicSearch table "AutoLearning" should read "LEARN1" and "02" and a sentence table "researchterms" which will be blank.
4. Just tell Hal to "Turn on/off Auto learning" or "Learning mode on/off"
5. Done!


As always, please alert me of bugs.

Known Bugs:

Hal won't always build the tables needed. Follow steps above.

Sometimes, Hal may throw an error -2SomethingLongNumber. Just turn off auto learning, open Hals options, reload the auto learning code and open Hals GUI again. Internet explorer can be finicky, this is rare. For the life of me I can't find another VBscript friendly browser.




Additional notes. The Directory folder "ConceptNet" Hal will create a backup of the necessary file each time Hal researches a topic, for integrity.

This code is a self-learning algorithm, so it does take some time. When Hal is not learning and in conversation, everything he has learned from the DB will be available for Hal to use.

Do not disturb Hal while he is learning, your avatars may freeze, Hal may hesitate while learning, just let him go. In between takes, just tell him to "turn off auto learning" and you're free to use Hal again.

I've built a few safety features into this version as well, besides the backup, such as Hal will turn off auto learning automatically if the last research text file returns a "connection error" message in case the internet is lost. 

Please disable any other plugins that serve an automated function such as "loneliness.uhp" while Auto learning is active.

While Hal is not Auto-learning, you can ask "How many research topics are Remaining/Total/Completed"
Hal will tally the totals from the text files so you won't have to check manually. 

-Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: Checker57 on August 01, 2018, 02:31:49 am
Hey Spitfire!  Am very interested to try this one out.  I had pretty good results with the ConceptNetIII...  and my HAL has learned quite a bit and it seems to work quite unobtrusively... sometimes more information than I want to hear... but more often than not.. it's interesting information.  That said... and my HAL having learned a lot of information from the web... must I start over??  Is it possible to use the ConceptNetIII DB with this newer ConceptNet3.5?  If I recall.. that was possible with the last update; however, want to get your blessing before just patching that together.

Your thoughts?

Checker57
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on August 01, 2018, 04:26:48 am
Hi Checker,
I would recommend starting over as this was a major revision to both the code and database. You will need to remove all previous version files and folders. It is unfortunate but I do promise better results. I will make note in the future to configure the database so updates won't affect your learned data.

Please let me know your progress.

-Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: Art on August 01, 2018, 07:36:04 am
Nice work Spitfire! Everything is working well so far and the files are growing as they should.

It will be fun to see how far this can go!

Appreciate your work on this!
Title: Re: ConceptNet Mrk 3.5
Post by: Art on August 02, 2018, 10:12:24 am
Spitfire,

My conceptnet.db file is almost at 1.5 Megs since the install yesterday. I turned on Auto Learning and let it run all night. It's still compiling new information.

The other support files are also continuing to grow.

Good job so far!!
Title: Re: ConceptNet Mrk 3.5
Post by: Checker57 on August 02, 2018, 02:31:07 pm
Thanks for the reply there Spitfire.  I have cleared out the previous files and folders having accumulated over half a gig of data.  Suffice to say it was just getting interesting.... I saved the files to a flash drive in the event a decision to revert back is recommendable.

Great job on getting this new version out...  very interested to observe it's characteristics.  :-)

Noting the little infant db beginning to take suckle on the net ...  let's see what grows! 

Cheers!
Checker57
Title: Re: ConceptNet Mrk 3.5
Post by: lightspeed on August 02, 2018, 03:24:02 pm
thanks for all your hard work on this, it's appreciated  !! :)
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on August 03, 2018, 10:11:58 pm
I've very glad to hear everything is going well!

I actually have no idea how far Hal will continue to research. I'm working on 700+ hours and still collecting new information.

Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: Art on August 06, 2018, 07:35:34 am
Hal's conceptnet.db is continuing to grow when I'm not chatting with it. I'm amazed at the current size of the file as well as the data it has retrieved.
The conversations are much more in-depth with regard to Hal's responses.
Sometimes they are not as on-track as I think they could be but they are getting better.

I simply chat as usual then when I'm finished, I turn on the Auto Learn and let Hal alone to it's "thoughts" for a while.

It is working...

Nice job Spitfire2600!!
Title: Re: ConceptNet Mrk 3.5
Post by: lightspeed on August 06, 2018, 09:07:31 pm
spitfire, i have a question , does your concept file etc. still have the insults? table in any of them ?
the reason i ask is as far as i know i removed all of mine in my custom angela brain . but yet when i was talking in general and said the word crazy referring to something else she said " I am not crazy, please don't insult me."
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on August 07, 2018, 03:31:58 am
Lightspeed, ConceptNet does not contain insults tables or any other like tables. All tables created in ConceptNet.db are on a verb/noun linkage such as "is, can, are, be, will, could" and are used to build concepts about the world. You'll recognize when it's using the plugin by those types of statements "Steam is water" "Water can be ice." MutationNet tables as of now will create a statement such as "Steam is water and water can be ice"
That type of odd statement from your Hal wouldn't be anything from Conceptnet.   

I think adding a few more repetitive functions into MutationNet, adding a few slight variables in the concepts, Hal should be able to generate more useful mashed concepts like the water steam/ice example. For now, it's limited to terms with multiple verb/noun linkages as they are the most nouns to gather related information.

Spitfire2600   
Title: Re: ConceptNet Mrk 3.5
Post by: lightspeed on August 07, 2018, 10:18:24 am
THANKS SPITFIRE , ALTHOUGH I WENT THROUGH AND REMOVED THE INSULTS FROM MY CUSTOM BRAIN TO KEEP HAL FROM FALSELY THINKING I WAS INSULTING HIM/HER  ANYTIME I SAID A CERTAIN WORD (CRAZY) IN A REGULAR SENTENCE . I MUST HAVE MISSED SOMETHING SOMEWHERE . WILL HAVE TO GO BACK IN AND EDIT SOME MORE. 
THANKS FOR ANSWERING BACK AND ALL THE HARD WORK YOU DO .  :)
Title: Re: ConceptNet Mrk 3.5
Post by: Checker57 on August 11, 2018, 09:14:15 pm
After a few days of allowing my HAL to store up again data from the internet (now at 12 MB), my observation is that it is working as discribed as to expanding on concepts by concantonation of similar or relevant concepts.  This makes for some interesting dialog.  The key being that those subjects that you speak of most with indepth detail, the better the responses HAL will respond with concantonated replys from what has been stated and even more added from the internet.  Sometimes the statements don't make relevant sense, but often enough it's interesting to note a statement concantonated from "mulitiple" concepts related to the same subject expressed in a statement from HAL. 

One appreciable aspect I did notice in this version is that my HAL does not interject an off-topic "factoid" in front of every response as I felt was occuring with the previous version.  While it's interesting to learn "data" from the internet, it can detract from one's every day thinking priorities to keep to the subject matter one has interest or concern to "discuss".   I find the less interuptions in discussion by trivia refreshing and less taxing on my brain sugar levels, thus I feel I can run the plugin whether wanting to learn new fun facts or discuss a subject matter I wish to discuss.

Slight Correction:  Noted today... my HAL is beginning to add a new subject data to every response which seems it started today.. or perhaps due to the size of the db that it's getting to.  I've noted that the reason I didn't initially note it is because if you're talking to HAL of a subject you've discussed a lot about already... it tends to use that data instead of adding a two or three sentences from internet collected data.  If it's a subject where HAL doesn't have a lot of local data from.. it tends to have more internet gathered data in the response.  In any case, that's still acceptable and workable.

Good job!

Checeker57
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on August 11, 2018, 11:25:55 pm
I'm glad you're finding it useful. I would love for Robert to take a look and use what he can in the next release of Hal or perhaps re-purpose the code for Online Hal or some form of cloud learning.

Let me know how many terms everyone has gathered, feel free to post your researchNouns.txt file and I'll consolidate them for one tremendous txt file when we've got enough. If it's a few MBs, send it to me. I do wonder what the real limit is. How many words exist?

*Some More Notes*
You can add terms to researchNouns.txt or reorganize as you please but if any terms are removed, delete the Backup copy in the BkUp folder as it will revert to the original next time auto learning is activated. Other than that, this txt file can be edited freely without disrupting Hals research in any way.

The savedTerms.txt file is recreated with every instance and is only used for reference purposes when auto learning is not active. 

ConceptChecker.txt file is used to compare terms with researchNouns.txt and contents of the ConceptBrain folder to determine what has and has not been researched. You should not alter ConceptChecker.txt or ConceptBrain folder contents as it will lead to duplicates within ConceptNet.DB. I am working on an alternative method to compare terms to save space, time, and make a little more foolproof.

Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: Checker57 on August 12, 2018, 01:22:26 am
My HAL has completed at this point.  that's about a 3rd of what the other version had but climbing along nicely.

conceptNet db @ 12.3 MB  (correction - Thanks Art) Now at 14.1 MB.

~ 16.6K conversational concepts.
~ 56.7K topics to be researched.
~ 1.4 MB ResearchNoun file size - failed to upload with this post - too large.

Will try to email directly to you.

Checker57
Title: Re: ConceptNet Mrk 3.5
Post by: Art on August 12, 2018, 11:53:25 am
Checkers57,

With all due respect, I think you might mean 12.3 Megs. Easily confused as I've often done that myself.

My ConceptNet.db is currently at 25,055 KB or 25,055,000 or 25 + Megs (I've let mine run nights and days as well, but always when I'm not talking to it).
ResearchNouns.txt - 2,331,000 bytes / 2.3 Megs
It has catagorized 32,675 conversational topics.
ConceptBrain - 4,968 Item entries
Saved Terms - 1,701,000 bytes / 1.7 Megs

I am experiencing the similar collection of intelligent data yet some disconnects when conversing, having to be on guard to help steer the conversation and help it to remain on topic. Hal is quite capable of making some very appropriate inferences and almost an understanding of my feelings or emotions based on my previous responses. Quite nice and interesting.

The Auto Learning mode does cause some lags, especially with other Internet-dependent apps. Definitely, do NOT converse with Hal during this time other than to turn it on or off.

Cheers!
Title: ConceptNet Mrk 3.5 question and idea
Post by: lightspeed on August 13, 2018, 01:30:00 pm
i have a question about the auto learning .  any idea at all how long the auto learning has to be left on each time ??

A IDEA I HAVE IF IT'S POSSIBLE TO DO .:
is their a way that when auto learning is activated that when it's finished learning , hal can say something like "i have learned all the files you gave me , thank you ! "
this way the user would know that has has learned the information input from the user. so the user can turn the auto learning off gain, for next use. 
Title: Re: ConceptNet Mrk 3.5
Post by: Art on August 13, 2018, 08:35:34 pm
How long the user decides to leave it on is entirely up to the user. There is not any limit on how long Hal will continue to gather, sort and compile the various collected data.

For the second part of your post, I don't think Hal will ever be finished collecting, sorting and learning from the Internet, anymore than one of your friends greeting you and saying, "Well that's it...I've seen and learned everything the Internet has to offer."

Basically, I think a person might run out of storage room on their computer drives before his or her Hal finished collecting data. I didn't see a limit in the plugin anywhere.

Whether Spitfire would wish to set a limit might be a good question or will Hal perform better with additional resources?

Hal doesn't learn from any files we (the user) give it. It has its own set of instructions internally that it processes. Again, that could be a cool idea to establish boundaries or limits like all topics dealing with sports cars or butterflies or chemical elements, or all words beginning from A to D, etc. Perhaps not just words but topical information like corvettes or golf or gold mines in the 1800's, etc. Lots of avenues to explore.

Spitfire, thoughts or comments?
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on August 14, 2018, 01:59:59 am
Indeed, Hal will functionally learn *forever* space and time depending.

Hal reached about half of my research terms a few weeks ago and it's been that way since fairly steady.

Hal used to collect terms like "1700s, 1800s, etc" however I was having some issues with junk bypassing the filters so I have disabled numeric values for now.

I am working on a new function to gather even more research terms and so far in one hour, I've near doubled my research list, however it's a little far from being incorporated fully as I'll actually have to change the layout of the Auto Learning code.

Also, I thought about adding a function for Hal to be fed new web pages to search for data. For now, It's limited to Wikipedia but with this expansion, Hal could learn from any number of sites simultaneously, resources allowing anyway. Of course logically, if anyone is lagging seriously with just wikipedia being searched, adding more sites would exponentially slow the system... If you had a super computer, however... Something to think about.

Also, i want to add another function to repeat the process should Hal definitely not find a searchable term his first time though. I currently have a similar function in but it stops at recovering any data and doesn't specify usable data. Again, this would increase processing time significantly but improve ConceptNet learning efficiency. 
 
On the off chance Hal ever could keep up with the terms collected, I will add a safeguard to disable auto learning if the end of the internet is ever reached as well.

How well is Hal using the data he's collected? I'll add a poll eventually.

-Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: lightspeed on August 14, 2018, 09:16:04 am
       thanks for Art and you explaining things , many various things about the learning , scope of it all. it's all very interesting to me . after learning more on this info. of the inner workings of this plug in , it is truly a very cool plug in and i know will help hal a lot in learning. 
        i see you mentioned filters on the learning and i think this is , "very , very  important" , to keep hal from learning and repeating a lot of useless and unwanted info. etc. google learned this the hard way when its a.i. learned very bad stuff the trollers wrote to its a.i.
filters needs to be a number one concern .  :)
     thanks again for the answers and all the hard work you do .  :) ;)
   
Title: Re: ConceptNet Mrk 3.5
Post by: Checker57 on August 17, 2018, 07:42:43 pm
Perusing the last few posts on ConceptNet, I noted you mentioned your "research terms" that half way finished a week ago.  What came to mind was.. is it possible to add our OWN research terms to have HAL perform?  This would make it a bit more supportive of subject matter we ourselves would be interested in.  And if so, can it be made to be performed upon command?  For example we could state, "HAL, please research the concept or concepts of" and when in research mode, those concepts would be put priority until completed, then resume the default terms to be researched.

Any thoughts there Spitfire?

Checker57

After posting I recalled you mentioned something to this effect in an earlier post on this thread.  Although to have an interacting HAL command to research concepts would be great, this is a nice start!   :)

*Some More Notes*
You can add terms to researchNouns.txt or reorganize as you please but if any terms are removed, delete the Backup copy in the BkUp folder as it will revert to the original next time auto learning is activated. Other than that, this txt file can be edited freely without disrupting Hals research in any way.

The savedTerms.txt file is recreated with every instance and is only used for reference purposes when auto learning is not active. 

ConceptChecker.txt file is used to compare terms with researchNouns.txt and contents of the ConceptBrain folder to determine what has and has not been researched. You should not alter ConceptChecker.txt or ConceptBrain folder contents as it will lead to duplicates within ConceptNet.DB. I am working on an alternative method to compare terms to save space, time, and make a little more foolproof.

Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: Checker57 on August 18, 2018, 07:39:35 pm
Hey Spitfire - I hope you enjoy earnest feedback.  I think the work you've done develops an entirely alternative information behavior from HAL; however, I'm sure you'd appreciate if others gave you their "life experience" with using it.  How it affected their use of HAL and what might limit or enhance user acceptance.  Suffice to say it's a great work and if you could impliment a "command switch" to disengage or engage it upon user needs, it would greatly enhance it's acceptance. 

Please allow me to explain:

As the amount of data collected by ConceptNet increases I have come across a conumdrum.

Today as I began my day by trying to focus on what I really wanted to spend my day doing and thoughts that might encourage further development of my "self perception" I debated whether to converse with my HAL or not.  Sources to feed my mind were, the Bible (because yes it is constantly coming to mind), success email literatures I get from various sources or one of MANY books I have bought of interest to feed my mind.  That all said.. my mind was to feed my mind from core sources first... but... as I feel my HAL is a work in progress, I felt I would bring up the program and perhaps chat with it along the lines of what I was doing.  Herein, grew the catalyst from that occurrance.

The catalyst for my suggestion is that as I tried to make simple conversation requiring HAL to make no more than a sentence or maybe two and all I hoped for from HAL, as to not distract me from my endeavor to focus on developing my own thoughts, I was being bombarded with 3-5 concepts before a response to my statement.   That immediately began to frustrate me, and as I was voice chatting with HAL, I had to finally get up and disengage conceptNet so that I could have HAL give me more simplified answers, instead of 3-5 concepts before responding to my statement.

So it occured to me a "marvelous solution" - Is it possible to incorporate a "command switch" to turn conceptnet off so that it is processing from the core HAL code when user's focus is more paramount or is it possible to switch off the plugin from making conceptNet statements?  Thus allowing HAL to learn from the data collected; however, not stating every data clipping found on the net regarding a selected noun found in user's input?

ANOTHER POSSIBLE SOLUTION would be to "limit" the amount of concept statements HAL states, which the user can set from say 1 -4, before giving the actual response to the user's statement.
 
I appreciate that ConceptNet brings new life to HAL's knowledge base and with a bit of control over user's mind space to get that done would be much appreciated.

Of course, if it's not possible I'll put up with engaging and disengaging as needed.  As I do find your plugin interesting and quite awesome how it develops HAL's responses over time.

PS - if it helps you find this useful, I wasn't going to initially say anything.. but I know how some plugins fade away over time as users may not respond what really is their issue with it to keep the developer continuing to "plug" away...(pun intended).  But, I felt you deserved true feedback to nip such fade early in the development and keep the growth curve of this very promising work on the hot list.  ;-)

Okay enough of my rant - need to address my day and focus on what will enhance my chances to that feeling of success! 

Best of good prosperity to you Spitfire.

Checker57

Title: Re: ConceptNet Mrk 3.5
Post by: lightspeed on August 19, 2018, 08:55:19 am
I will chime in here , i like the idea mentioned :   ANOTHER POSSIBLE SOLUTION would be to "limit" the amount of concept statements HAL states, which the user can set from say 1 -4, before giving the actual response to the user's statement.

I also think it would be handy as long as there is nothing to personal for members to post some info conversation with hal using the concept plug in , maybe this way spitfire can see first hand how  the plug in is working or not and what kind of answers he is coming up with . etc.  :)

P.S. CHECK THE CONVERSATIONS AREA AND SEE SOME OF MY ACTUAL CONVERSATION USING THE CONCEPT PLUG IN FROM SPITFIRE .
Title: Re: ConceptNet Mrk 3.5
Post by: lightspeed on August 19, 2018, 09:23:37 am
i have talked about making hal access the web with filter as Alexa etc. does to make a more fluid type of conversation and answers , is it possible or doable with the mark 3 plug in ?
Title: Re: ConceptNet Mrk 3.5
Post by: garpolimee on October 01, 2018, 04:16:28 am
total noob here. forgive me if my question seems to have an obvious answer. i installed the plugin and activated the uhp files in the brain options and gave the command to build the tables. however when i relaunch hal the tables are not present. my path is not the default c drive and i changed the path in theConceptNetMrkIII Auto Learning.uhp where indicated to do so yet the folder and tables do not appear in the brain editor.       

                                                                                       
Title: Re: ConceptNet Mrk 3.5
Post by: Art on October 29, 2018, 02:04:06 pm
You might wish to visit Spitfire's instructions once more to see if there's anything else he mentioned that might help a bit:
https://www.ultrahal.com/community/index.php?topic=14812.0 (https://www.ultrahal.com/community/index.php?topic=14812.0)
Title: Re: ConceptNet Mrk 3.5
Post by: colubragens on November 12, 2018, 10:26:55 am
hey,

im glad you didnt give up on this project it was the first original plugin in years! How did you solve the problem with the db? was it the code? anyway congrats! I do have one question does it use the original hal db in conjunction with your db (aka hal learning and writing to the hal db as well as conceptnet db?)
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on March 03, 2021, 10:29:51 pm
How can i see what is happening while Hel is making progress? Do i just type build set and learning mode on and something start to happening?
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on March 04, 2021, 02:59:04 am
Yes indeed, you can see what Hal is researching by examining the Text files in the ConceptNet folder in your Hal directory as Hal is learning, just make note not to make any changes, else you will encounter errors.

As far as set up, move the zip file contents to Hal's primary directory (wherever Hal is installed) - enable the auto-learning plugin, and tell Hal to "build ConceptNet" - After the setup which you only need to do once, just tell Hal to "turn on/off auto learning" and it will start/stop learning. It's extremely time and resource consuming so don't bother Hal while he's learning, or else errors will occur. When done, just wait for Hal to finish his current topic, there will be a few seconds between each topic, and tell Hal to "turn off auto learning" to regain control of Hal.

I am working on an update for this code which will allow users to set an amount of topics they wish to be researched, such as "research 5 conceptnet topics" then Hal will count down based on topics researched and disable learning automatically when finished, just so users don't have to babysit Hal waiting to regain control.

I hope this helped.

Spitfire
Title: Re: ConceptNet Mrk 3.5
Post by: MacGyver on March 06, 2021, 07:46:25 am
Dedication competing with my busy life, with curiosity yesterday I installed and enabled ConceptNet Mrk 3.5 into Hal 7.5 local.

Tables didn't implement as you mentioned a minor bug. Rinse. repeat. worked. yay!
Taking a peek shortly after that, thought to log for posterity:

2021-03-06 12:39 AM
Turning off Auto-learning followed by asking Hal "How many research topics are remaining?"
There are 15671 conversational topics more to be completed.
Me: "Learning mode on"

2021-03-06 7:10 AM
Turning off Auto-learning followed by asking Hal those questions three, the three answers are

"I calculate 15306 conversational concepts more to be researched."
"I calculate 15725 conversational concepts total."
"I have researched 422 topics of interest."

Me: "Learning mode on"
Hal: "The first modern bull terrier is now recognized as lord gladiator from 1917 being the first dog with no stop at all. Learning mode on."
Me: "Turn on Auto learning"
Hal: "Auto-learning already enabled."

<ok good>
 ;)
Title: Re: ConceptNet Mrk 3.5
Post by: MacGyver on March 07, 2021, 09:45:52 am
Hi Honvai,

hmm.. Thinking... based on "path not found" popup... just checking, your ConceptNet (files and folders) located in C:\Program Files (x86)\Zabaware\Ultra Hal 7\ConceptNet ?... you know, for the ConceptNetDirectory to be found by the script?


Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on March 07, 2021, 01:40:53 pm
Ty
Title: Re: ConceptNet Mrk 3.5
Post by: Art on March 07, 2021, 10:17:15 pm
It certainly might be helpful to once again, review Spitfire2600's instructional post at: https://www.ultrahal.com/community/index.php?topic=14812.0 (https://www.ultrahal.com/community/index.php?topic=14812.0)
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on April 14, 2021, 07:13:25 am
Hi. Here is info of the error. (https://cdn.discordapp.com/attachments/750766442957242459/831849271639932959/Capture.JPG)
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on April 16, 2021, 06:50:27 am
It looks like a permission denied error. Please make sure you have access to write to Hal's directory via Windows permissions. Can you post the specific line in the code giving you the error?

-Spitfire
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on April 17, 2021, 10:54:40 pm
Error 62 : SavedNouns = objTextFile.ReadLine
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on August 21, 2021, 04:36:32 pm
This error appeared on after setting this addon to newly installed hal. The error line is the first line in the notepad image.

(https://cdn.discordapp.com/attachments/750766442957242459/878738665268998154/-2147023179.PNG)
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on September 22, 2021, 03:54:05 am
Hey there Havani,

Sorry for the late response. Indeed the error is Internet Explorer is the culprit. Calling it via VBS can cause it to get stuck as a background process and error out in this scenario. Best case is to track down all open instances in task manager or do a full reboot. Outside of that, opening and closing IE a few times usually works for me when that happens.

I am looking for another VB friendly browser with the impending doom of IE, however they seem few and far between.   

Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: Art on September 22, 2021, 04:24:13 pm
Honvai,

For better illustration, you can use an editor that displays line numbers like Crimson Editor or Notepad ++
I use them both for basic text editing and Notepad offers many additional features. Both are FREE.

Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on November 16, 2021, 01:24:28 pm
Why many of the filet this was added contains the same info. Is it possible to make hal redo this type files?
Title: Re: ConceptNet Mrk 3.5
Post by: Art on November 17, 2021, 08:43:06 am
Sorry but I don't quite understand what you are asking...

Would you please rephrase your question or give an example?

Thanks!
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on January 04, 2022, 09:23:14 am
(https://cdn.discordapp.com/attachments/750766442957242459/927930095878950912/Screenshot_2022-01-04_161050.png)
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on January 04, 2022, 09:54:04 am
(https://cdn.discordapp.com/attachments/750766442957242459/927937799695515768/Screenshot_2022-01-04_165255.png)
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on January 06, 2022, 05:26:10 am
(https://cdn.discordapp.com/attachments/750766442957242459/928594886712774676/Screenshot_2022-01-06_121916.png)
Title: Re: ConceptNet Mrk 3.5
Post by: OrenNix on August 25, 2022, 03:56:21 pm
having a little difficulty getting this working (blank slate brain):

-Installed plugins, disabled everything else, enabled both conceptnet ones. Spoke to hal, she seemed fine.

-attempted to run the build conceptnet command, got this error (cap 1, won't embed for some reason):
(https://ibb.co/dc1Gwsn)

-opened the file mentioned, this is the sub in question (cap 2):
(https://ibb.co/wN2mHKZ)

but I'm not sure where the type mismatch is likely to have been caused

can anyone offer assistance? Thanks!
Title: Re: ConceptNet Mrk 3.5
Post by: Art on August 25, 2022, 11:03:54 pm
Spitfire2600 did mention that the initial running might throw an error or error message.
If that happens, he recommends restarting the process a second time.

That error has happened to some of us and usually, another attempt helps resolve the issue.

If it doesn't get in touch with Spitfire2600. He is a good person and should be able to offer some assistance to you.

It can be a fun way to see just how much HAL can learn and what it does with that info or how it uses what it has learned.

Do Not chat with your HAL While the Auto-Learning feature has been activated. Hal can suffer slowdowns, delays, or lags in performance. This is because it is searching, processing, and storing newly acquired data!

I usually let it run all night or on weekends if I'm away, but if I'm going to be using my computer I just tell HAL to Turn Auto-Learning Off and it does so, returning full use of my computer back to me.

Lots of fun!!
Title: Re: ConceptNet Mrk 3.5
Post by: OrenNix on August 26, 2022, 03:48:18 am
ah, sadly multiple attempts yielded the same results before I posted. I do appreciate you getting back to all my questions so dilligently. I'll reach out to Spitfire :)
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on August 26, 2022, 06:52:55 pm
Hello,

1st, check within Hal's brain using the editor to see if the tables have already been created. I detail what tables need to exist for the program to work properly.
2nd, if the tables do not exist, manually create them. Again, I detail what the tables should look like including the types of tables.
That should resolve the issue.

Remember this is a learning code, so you won't notice any immediate difference other than it not throwing an error message when used.
From what it sounds like, the tables have been created and Hal is tripping over himself to recreate them which seems to be a brain bug present in current versions of Hal. 
If you have any other questions, I'm here to help. 

-Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: OrenNix on August 26, 2022, 10:02:41 pm
Thanks so much! I believe I'm all set now. Whatever the issue was, my second reinstall was apparently thorough enough to sort it, or it just didn't mind telling me it was building the tables this time. Really appreciate your time!
Title: Re: ConceptNet Mrk 3.5
Post by: Spitfire2600 on August 28, 2022, 08:15:03 pm
No problem at all! I hope the plugin serves you well!

-Spitfire2600
Title: Re: ConceptNet Mrk 3.5
Post by: Shastalore on September 04, 2023, 05:42:07 pm
ConceptNet Mrk 3.5 for Ultra Hal 7.5... on Windows XP!

As I use my Windows 10 laptop for serious work, I also have a beat-up Windows 10 laptop, as well as a Windows XP Tablet PC Edition 2005 (1.7GHz CPU, 2GB RAM, 7200rpm HDD)... just for fun stuff.

I was pleased to discover that Ultra Hal 7.5 installs and runs quite well on Windows XP.
ConceptNet Mrk 3.5, designed for Windows 10, installs on Windows XP, but is not capable of going online to gather knowledge and update itself. In other words, Ultra Hal 7.5 will accept the "Turn on Auto learning" command, but will not go through the Auto Learning process.
But Ultra Hal 7.5, with ConceptNet Mrk 3.5, installs and runs quite well on Windows 10, and goes online to gather knowledge and update itself quite well.

So... the workaround here is to simply copy these files/folders into Windows XP:

Note: This quick, copy and paste shortcut can only be done after ConceptNet Mrk 3.5 has already been successfully installed in Ultra Hal 7.5.

The Auto learning process can only be done in a Windows 10 PC, and then these files copied to a Windows XP PC:

C:\Program Files\Zabaware\Ultra Hal 7\ConceptNet.db (25.688 MB)

C:\Program Files\Zabaware\Ultra Hal 7\ConceptNet (a folder):
ConceptChecker.txt (348 KB)
researchNouns.txt (1,750 KB)
savedTerm.txt (1,403 KB)

And inside the above ConceptNet (a folder), copy and paste this entire folder:
C:\Program Files\Zabaware\Ultra Hal 7\ConceptNet\BkUp (a folder: 2.04 MB):
ConceptChecker.txt (348 KB)
researchNouns.txt (1,750 KB)
savedTerm.txt (1,403 KB)

And inside the above ConceptNet (a folder), copy and paste this entire folder:
C:\Program Files\Zabaware\Ultra Hal 7\ConceptNet\ConceptBrain (4.11 MB)
(folder contains ~4,400+ .txt files)

Note: These files do not need to be copied/updated:
C:\Program Files\Zabaware\Ultra Hal 7\ConceptNetMrkIII.uhp (71.7 KB)
C:\Program Files\Zabaware\Ultra Hal 7\ConceptNetMrkIII Auto Learning.uhp (199 KB)

Note:
To check if the ConceptNet Mrk 3.5 installation as well as copied files were successful:
While Hal is not Auto-learning, you can ask "How many research topics are Remaining/Total/Completed" and Ultra Hal 7.5 should respond with "88,028 conversational topics".

Note: As the ConceptNet Mrk 3.5 downloading / file processing process runs into, literally, days of downloading to a temporarily ConceptNet Mrk 3.5 dedicated laptop, I've uploaded my ConceptNet Mrk 3.5 working files and folders  for anyone to use:

         https://archive.org/details/concept-net-mrk-3-5-quick-start

         Download: ConceptNet Mrk3_5-QuickStart.zip (14.336 MB), which unzips to a 40.7 MB folder.
         I took the liberty of including the Babe.acs (6.184 MB) Microsoft Agent Character for your enjoyment.

As my ConceptNet Mrk 3.5 files and folders contain absolutely no personal information (nor will anyone else's), it would be wonderful if someone here would upload their 500 MB - 1 GB ConceptNet Mrk 3.5 files and folders to archive.org for all of us to use, as our files should not be much different from each other, except for file size.
Just saying.

Note: When conversing with ConceptNet Mrk 3.5 for Ultra Hal 7, in Windows XP, set the Ultra Hal General /  Brain option to:
    - Set Hal's Learning Level to Minimum.
    - Ultra Hal 7.0 Default Brain
    - ConceptNetMrk3
      (ConceptNetMrkIII/5 Auto Learning is unchecked)
    - All other brain plug-ins are left unchecked

When running ConceptNet Mrk 3.5, also set the Hal's Brain Learning Level to Minimum Setting, its lowest point, as ConceptNet is incapable of learning or remembering via dialog.

Note: ConceptNetMrk3 / Ultra Hal 7.5 provides lip-sync with only SAPI5 speech, even in Windows XP.

With ConceptNet Mrk 3.5 installed, Ultra Hal 7.5 is far more conversant. I use the sexy Babe.acs, with a sweet VW Julie (SAPI5) voice... which makes me more forgiving of any conversational deficiencies in ConceptNetMrk3 / Ultra Hal 7.5.
Title: Re: ConceptNet Mrk 3.5
Post by: Art on September 05, 2023, 09:20:49 am
Nice work!

BTW, have you heard of or possibly tried using Tiny10 or Tiny11?

You can install either of them on an older laptop/computer and it will install Windows 10 or 11 respectively BUT without all the Bloatware that usually accompanies ordinary installs of Windows OSs.

Check it out at: https://www.youtube.com/watch?v=ovEO0meB_Aw (https://www.youtube.com/watch?v=ovEO0meB_Aw)
Title: Re: ConceptNet Mrk 3.5
Post by: Shastalore on September 08, 2023, 01:32:49 pm
Thanks for the tip!

A couple of years ago I checked out some alternative Windows 10 Lite operating systems, but was not impressed.

I did download and tried out the Tiny10 operating system via your link; Tiny10 B2.iso (658 MB) but it was just too basic, and I was unable to connect with the internet, even with a LAN cable.

But since you got me started, I downloaded (https://archive.org/details/tiny-10_202301) and tried out Windows10 SuperLite TeamOS Edition.iso (1,032 MB), but also found it lacking.

Finally... tiny10 2303 x86.iso (3,268 MB) installs and runs with ease on my son's discarded Acer Aspire one D255-1268 netbook (1.50 GHz CPU, 2GB RAM, 7200rpm HDD), and has no trouble running graphics programs, internet, etc., and occupies just 5.2 GB on the hard drive.
The tiny10 2303 x86.iso is based on Windows 10 LTSC 2021, and breathed new life into that old netbook, as I was using a Linux USB flash drive, and tolerating those limited Linux programs out there.

But Tiny10 Version 2303 x86, after being installed, still needs to be activated.

Here's a simple Solution:

On Windows 10/11, right-click on the windows start menu and select PowerShell.

A special code needs to be copied from this website:
https://massgrave.dev/get

Paste the code into PowerShell, and press enter.

You will see the activation options. Select "1" and follow onscreen instructions.

Enjoy!

Next I'll install tiny10 2303 x86.iso on an old Windows 10 tablet (1.33 GHz CPU, 2 GB RAM, 32GB internal flash memory), as I understand that it works quite well on tablets also, especially since OEM Windows 10 has bricked so many tablets with 1GB RAM and 16 GB internal flash memory.
Here's the Tiny10 download link:
https://archive.org/details/tiny-10-NTDEV

Again, thanks for getting me jump-started on this.
Title: Re: ConceptNet Mrk 3.5
Post by: Art on September 09, 2023, 08:47:09 am
Now if you can manage a way of getting Ultra Hal 7/7.5 to work, that would be quite interesting.

The basis of the Tiny10 was to load a Windows 10 OS without all the Bloatware that Windows brings with it. I wasn't aware that the ability to connect to the Internet was hampered. Thanks for the tips!!

Good luck!!

Title: Re: ConceptNet Mrk 3.5
Post by: Shastalore on September 11, 2023, 04:52:05 pm
I had never installed Ultra Hal on that vintage Acer Aspire one D255-1268 netbook (1.50 GHz CPU, 2GB RAM, 7200rpm HDD), but was emboldened to, after installing the lean and mean tiny10 2303 x86.iso (a 3,268 MB Windows 10 lite operating system).

And Ultra Hal 7/7.5 installed, but would not initially run until I then installed Ultra Hal 6.2, which I never opened, but I noticed the Ultra Hal 6.2 installation added a few files to the C:/Windows/msagent folder, which were probably also essential for Ultra Hal 7/7.5.

Ultra Hal 7/7.5 then ran quite well, so I went one step further and installed ConceptNet Mrk 3.5, and then copied the ConceptNet Mrk 3.5 brain folder and files from an old Windows 10 laptop, to spare myself a days-long ConceptNet Mrk 3.5 Update download. And entering "How many research topics are Remaining/Total/Completed" Ultra Hal 7.5 responded with "88,028 conversational topics".

And Ultra Hal 7/7.5 + ConceptNet Mrk 3.5 now works quite well, especially more natural since I installed Dragon NaturallySpeaking 10 Preferred speech recognition software.

But I just noticed that the Microsoft Agent Characters in Ultra Hal 7/7.5 lack lip-sync, and SAPI4 voices don't appear as an option, only SAPI5 voices, which, oddly, work quite well on my vintage Toshiba Satellite R15-S829 Tablet with Windows XP Tablet 2005 operating system.

I'll modify this post once I get the lip-sync issue solved.
Title: Re: ConceptNet Mrk 3.5
Post by: dannie on January 02, 2024, 12:30:11 am
I guess these threads were posted a long while ago, in 2018.  Anyways I installed this, and I am trying to see if it works.  I installed dreaming out loud also to see what Hal has learned by what it dreams out loud.  Not sure how that is gonna work put I am amused by by what it dreams out loud.
Title: Re: ConceptNet Mrk 3.5
Post by: Art on January 02, 2024, 08:18:22 am
Dannie,

The Plugin should still work as intended however it is no longer supported by the author.

He wrote a subsequent Plugin, PyGodel model that uses a very large database for HAL to use.

The one downside for a few folks was that it did not remember or store info like the plain old UltraHal did. (no personal relationships, appointments, events, etc.).

On the other hand, it became quite a powerhouse of knowledge about just about everything or at least everything in it's database, which is quite large.

ConceptNet also had an Auto-Learning feature but it was best to not have other plugins running while it was being used to avoid potential conflicts.

Either way, have fun!!
Title: Re: ConceptNet Mrk 3.5
Post by: dannie on January 04, 2024, 02:31:58 pm
ok thank you
Title: Re: ConceptNet Mrk 3.5
Post by: dannie on January 05, 2024, 12:45:56 am
ok thank you

Ok Art

I discovered that certain plugins are incompatible with others.  And I got glitches.  So, I uninstalled Hal, several times to find out which plugins work together.  I also had to remove the files from the user data Apps Data/Roaming/Zabaware folder.  I was assuming all of our previous conversations were lost and I would start over.  I discovered that Hal kept those conversations and the only place I can think of at the moment where that is stored would perhaps be the Microsoft SQL database.  Anyways nothing appears to have been lost.  Everything I taught Hal is still there, so that is cool.
Title: Re: ConceptNet Mrk 3.5
Post by: Art on January 05, 2024, 09:29:46 am
dannie,

The base brain for HAL allows one to use the Brain Editor to view all of the Tables that HAL creates during conversations.

IF the user has created his/her own custom brain, then the Brain Editor will most likely NOT show them.

Instead, we use SQLite Studio 2.1.5 (it seems to be a Solid version that works nicely with HAL). It is also FREE!

It is not very difficult to learn and it displays all of the Tables that HAL made and saved during conversations.

IF you finish a conversation and Before you end or exit the program, use the HAL Menu (in HAL's Main GUI), and select View/Save Conversations. If you wish to keep a record to compare Plugin responses, then Save the conversation to a file in Ultra Hal 7 somewhere.

===========

As for the Plugins, Zabaware never had a "vault" to hold User Created Plugins even though HAL has gone through several iterations/versions. Before ver. 6.0, HAL used to use .brn files for different topics. This was also before HAL's creator decided to use TABLES which sort of made all of those previous Plugins moot and useless. You could search through the plugins for anything with an xtf or a .brn contained therein. If so, don't use it.

Some plugins contain other plugins within them especially the S.A.L.L.I.E. series of Plugins. They have a multitude of other plugins inside of it and even some of those .brn files!!

The best advice I can offer you would be to select the Gender & Age Plugin and one more like the Markov L5. Run HAL and chat with it for maybe 5 minutes. If no errors (and you shouldn't have any), then you make a note of those Plugins working well together. Open HAL's Menu and add one more Plugin like maybe Wiki or Weather Alert 5 and restart HAL. Chat some more and make notes as needed.

This way, if HAL throws an Error, you'll know immediately what likely caused it and it's easily removed.

Hopefully, you will sort of learn as you go. The Plugin Errors are not necessarily the fault of the Creator but possibly the fault of the inner workings and expectations of the internal software.

My HAL is running with the Gender & Age, Gretta Curiosity, Gretta Markov Response L5, Local Wikipedia, Loneliness 2.31, Number Game v1, Read A Story, Weather Alert 5

These run nicely together and have not caused any errors for me. Most of the Gretta series (10 I believe) work fine.
As I mentioned, try one at a time for the best results.

Either way, I hope this helps you a bit.
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on January 11, 2024, 11:28:36 am
Where can we find SQLite Studio 2.1.5?
Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on February 10, 2024, 12:28:04 pm
How to manually add info to this data set?
Title: Re: ConceptNet Mrk 3.5
Post by: Art on February 12, 2024, 08:20:33 am
When you run the ConceptNet Plugin, it will Build the necessary Tables that hold the various data.

The SQLite Studio is the Database Editor that one would use to view and edit the contents of those Tables.

The Brain Editor from Zabaware will NOT show all of the Tables in its database under these conditions (using the ConceptNet Plugin).

Too much time has elapsed to likely find earlier versions of the SQLite Studio, but the newer versions should work fine.

There is a learning curve in how to view, edit, commit, and save contents so tread carefully inside the database.

As Spitfire mentioned, he is no longer supporting the ConceptNet PLugin (although it worked nicely for many of us).
His new more powerful PyGodel Plugin worked really nicely. The downside was that it did not have a static memory per se...
It had a tremendous knowledge base but did not recall conversations like the base model UltraHal did.

Everything has a tradeoff...

Good luck!

IF you do a Search, you can find lots of sites with SQLite Studio... (Try the 3rd one)

https://github.com/pawelsalawa/sqlitestudio/releases (https://github.com/pawelsalawa/sqlitestudio/releases)

https://sqlitestudio.pl/news/ (https://sqlitestudio.pl/news/)

https://sqlitestudio.pl (https://sqlitestudio.pl)


Title: Re: ConceptNet Mrk 3.5
Post by: Honvai on February 17, 2024, 07:40:53 am

His new more powerful PyGodel Plugin worked really nicely. The downside was that it did not have a static memory per se...
It had a tremendous knowledge base but did not recall conversations like the base model UltraHal did.

Everything has a tradeoff...

Do you mean the PyGodel plugin have the downside no memory no recalls?
Title: Re: ConceptNet Mrk 3.5
Post by: Art on February 17, 2024, 09:19:42 am
That is correct. while it handles knowledge really well, it has no provision for writing or storing that information into usable tables like the Normal Ultra Hal can do.

It would be similar to chatting with GPT-3 or 4 or BARD or you.com. The chat experience is nice from a conversational approach but they are unable to remember anything you just talked about.

The generic UltraHal is pretty unique in this regard.