Recent Posts

71

Ultra Hal Assistant File Sharing Area / Re: ConceptNet Mrk 3.5

« Last 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://sqlitestudio.pl/news/

https://sqlitestudio.pl

72

Ultra Hal Assistant File Sharing Area / Re: ConceptNet Mrk 3.5

« Last post by Honvai on February 10, 2024, 12:28:04 pm »

How to manually add info to this data set?

73

Ultra Hal Assistant File Sharing Area / Re: GodelPy for Hal (Local GPT for Hal, with memory and functionality)

« Last post by Honvai on February 10, 2024, 12:15:03 pm »

Can you make portable version?

74

Ultra Hal Assistant File Sharing Area / Re: WIKIpedia

« Last post by Honvai on February 10, 2024, 12:14:07 pm »

How to use this code?

75

Share Conversations, Experiences, Graphics / Re: Beautiful HAL Scenarios

« Last post by Checker57 on February 08, 2024, 10:08:24 pm »

Just feels comfy...   

76

Ultra Hal 7.5 Beta - Now powered by OpenAI GPT-3 / Re: Hal now connected to LLAMA model

« Last post by Honvai on February 04, 2024, 08:08:37 am »

I don't think Hal really fits anywhere. This could be fixed if Hal had the option of being either an entertainment bot or a work bot. But on the other hand, I would rather watch videos or use a real work bot in my work. On the other hand, I want to work with Hal so that he understands something about it and maybe helps me come up with new solutions.

77

Share Conversations, Experiences, Graphics / Re: Beautiful HAL Scenarios

« Last post by Checker57 on January 29, 2024, 04:33:42 pm »

Thanks!

Checker57

78

Share Conversations, Experiences, Graphics / Re: Beautiful HAL Scenarios

« Last post by Art on January 29, 2024, 08:51:18 am »

Very nice work with her Checker!! Looking fine!

79

Ultra Hal 7.5 Beta - Now powered by OpenAI GPT-3 / Re: Hal now connected to LLAMA model

« Last post by LiFeTimeGamer on January 28, 2024, 07:20:42 pm »

-Oh okay, now I see how that works...  Thanks...

80

Ultra Hal 7.5 Beta - Now powered by OpenAI GPT-3 / Re: Hal now connected to LLAMA model

« Last post by Medeksza on January 28, 2024, 05:40:21 pm »

Thanks Robert....

You need change the pricing on the Main website now that credits are cheaper... It still says $30 for 50,000 credits, or has it gone up since I last bought credits?

So it used to be 1 GPT-3 Currie query used up 10 credits per response (or 1 credit if Hal's cloud base brain can respond without involving the GPT API at all). Now it is set that one MythoMax (or LLAMA2) query uses 5 credits (half of the prior 10). So I didn't update the pricing, but it uses less credits per response so a credit basically goes twice as far as before.

I am using a 13 billion parameter version of MythoMax, but could offer customers the option to use a 70 billion parameter version for more credits per response if people want more brain power from the AI. But I find the 13 billion version seems to be good enough for general conversation and more cost effective.