AnythingLLM | How to get a Private Uncensored ChatGPT using Mistral-7B, LLama2, & more

Another update is hot off the press for AnythingLLM, a fully open-source and private ChatGPT equilivant software you can use.

Now, we support using custom LLM models you can run on your machine or servers you own. Now, you can use models like Mistral-7B, CodeLlama, Falcon-40B, and others and get a ChatGPT experience + more!

Chapters
0:00 Introduction of AnythingLLM
1:20 AnythingLLM Github
1:45 LMStudio Introduction
2:21 Mistral 7B Model
2:49 AnythingLLM LLM selection
3:16 LM Studio Overview & Running an Inference Server
5:49 Adding LM Studio URL into AnythingLLM
6:20 Embedding model selection
6:50 Vector database selection
7:12 AnythingLLM customization
7:21 Single or Multi-user mode
7:40 Privacy Overview
8:20 Create first workspace
8:30 Sending our first chat to Mistral!
9:25 Embedding custom files
10:30 Retrieval chat with Mistral-7B
11:29 LMStudio server log
12:00 Extra features of AnythingLLM
12:45 That's a wrap for this update!

#private #llm #chatgpt #customchatbot #gpt #openai #mistral #ai #aitools #aibusiness #chatgptcoding #chatgpttradingbot #opensource #github #developer #developers #llama #privategpt #gpts #tech #freesoftware #privatellm #anythingllm #mintplexlabs #chatgpt4 #chatgpt #gpt3 #gpt4all

[muddlefly]

Excellent presentation, very exciting progress. Congratulations!

[drmetroyt]

Please add suport for ollama in anything LLM, anything LLM is amazing waiting to try with ollama

[NNSi]

Hi! I can't get it to run on my windows 10 =(
Can anyone write a step-by-step instruction for this system? Where to enter commands, what additional libraries are needed, and the installation sequence. I tried to install many similar AI programs, but I couldn't cope with any of them = ( I'm a computer loser, I do humanitarian work.

[kleber]

My mistral is not uncensored at all, no matter how I set up the prompt... Any Idea what could it be? thx.

[slipthetrap]

Can you use AnythingLLM locally without LMStudio ? LMStudio seems like an unneeded dependency, other local AI chat thingies work without this. Just curious, thanks.

[dannish]

How do you make these locally installed Llama 'smarter'? They seem quite dumb compared to chatgpt

[AIEntusiast_]

getting error, pdf context not readable, fetching website doesnt work wont embed it

[leobudihartokusumo]

any config now to change the interface language or llm that support specific country language?

[Jascensionvoid]

Great video. They're helping me learn about this complicated subject. So let's say, for example, all I have is one windows PC. And I'm running Anything LLM and LM Studio on the same machine. I have downloaded mistral instruct. Do I still need to do the server steps you outline to get it to work with Anything LLM if it's all on the same comptuer? That's the main part I'm confused about? So how do I utilize LM Studio and Anything LLM if everything is on one machine?

[gustavopelissaro]

Could you make a video on how to deploy on Google Cloud or AWS? Thank you very much, great video

[mrrohitjadhav]

Can we process our existing data in AnythingLLM with output as files such as JSON or txt???

[youwang]

just wonder how to deploy it on render or railway? if there's a video about how to put it on cloud, it would be definitely great, thank you for ur video

[rajismyname]

how to clear memory and start a new chat?

[YensyCiprianS]

Can I run this app on an ARM Linux machine?, I have it running on Windows and it's working well but, I need to get it running on ARM Linux with no luck for now.

[dudesicko]

Poop, its nice until you than say "i already have bla bla bla installed", why the fart do you make a guide, and than skip the part people actually need?
Its like making a cooking show, and then show the ingredients, and then jump to where you serve the dinner.

[Hazardteam]

02:37 Would you finally DO something instead of endless talking?!!