Smart RSS

AnythingLLM is a private, customizable, and extendable single or multi-user document chatbot software. https://useanything.comIn this video, we will show how to deploy a working instance of AnythingLLM in 10 minutes! While this method is more expensive to run it can be a quick solution for a proof-of-concept! AnythingLLM supports multiple vector databases like Chroma, Pinecone, QDrant, and Weaviate as well as both OpenAI and Azure OpenAI LLM services! Fully end to end for your enjoyment!Get a free 3-day trial hosted instance at https://my.mintplexlabs.com/aio-checkout?product=anythingllmChapters0:00 What is AnythingLLM?0:57 Useanything.com Hosted solution2:07 Render.com Introduction2:51 Selecting the open source Github Repo3:10 Configuring the service3:56 Consulting the docs!4:22 Selecting your instance size $$5:10 Setting up storage7:15 TURN OFF AUTO DEPLOY!!7:34 Vector Database selections7:40 LLM Selections8:10 Done!8:55 Checking out our AnythingLLM instance 9:26 Total cost and Summary#opensource #ai #aitools #chatgpt4 #gpt #privategpt #vector #vectordatabase #chromadb #chroma #pinecone #azure #weaviate #aitoolsforbusiness #github #dev #openai #openaichat #DIYChatbot #chatbot #chatwithdocuments #chatwithpdf #gpt #llm

AnythingLLM is an open-source full-stack "Chat with your documents" application that is constantly evolving and will enable you to chat with your documents in a private and enterprise environment.Lean more: https://useanything.comGitHub: https://github.com/Mintplex-Labs/anything-llmChapters0:00 What is AnythingLLM & what’s new?0:46 Where to find on GitHub1:29 Onboarding - Introduction1:51 Onboarding - LLM Selection2:34 Onboarding - Vector Database Selection3:27 Onboarding - Appearance and customization3:51 Onboarding - Single and Multi-User mode setup options5:07 Onboarding - Create the first workspace5:45 The chat interface6:17 Uploading a custom document(s) for chatting7:16 Workspace settings overview8:15 Citations10:00 AnythingLLM Controls10:20 Settings - System Preferences10:43 Settings - Inviting new members10:58 Settings - User management11:15 Settings - Workspace management11:32 Settings - Workspace chat management11:50 Settings - Appearance settings & default chat view12:27 Settings - API Key and endpoint documentation12:48 Settings - LLM preference12:56 Settings - Vector database preference13:05 Settings - Exporting or importing AnythingLLM snapshots13:17 Settings - Security settings12:30 Wrapping up!#openai #chatgpt4 #chatwithdocs #localgpt #privategpt #gpt #useGPT #gpt4all #ai #aitools #aitools2023 #aitoolsforbusiness #opensource #openaiapi #nodejs #reactjs #opensourcesoftware #ai #aiagents #claude #anthropic #vectordatabase #privategpt

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!Github: https://github.com/Mintplex-Labs/anything-llmHosted: https://useanything.comContact Me: tim@mintplexlabs.comChapters0:00 Introduction of AnythingLLM1:20 AnythingLLM Github1:45 LMStudio Introduction2:21 Mistral 7B Model2:49 AnythingLLM LLM selection3:16 LM Studio Overview & Running an Inference Server5:49 Adding LM Studio URL into AnythingLLM6:20 Embedding model selection6:50 Vector database selection7:12 AnythingLLM customization7:21 Single or Multi-user mode7:40 Privacy Overview8:20 Create first workspace8:30 Sending our first chat to Mistral!9:25 Embedding custom files10:30 Retrieval chat with Mistral-7B11:29 LMStudio server log12:00 Extra features of AnythingLLM12:45 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

In a world of pay-per-token LLMs you probably have looked everywhere to get your Local or Cloud-hosted LLM model to act like an AI assistant on your website - well now with AnythingLLM it is free and open source!Today, we are going to create an AI chatbot for our website trained on the data from our own website! All of this is built into the AnythingLLM cloud or our self-hosted version you can run anywhere. The embed takes minutes to set up and is a single HTML snippet you can embed into your website and get a powerful chatbot to handle customer questions.With AnythingLLM, you can now publish smarter chatbots using any LLM trained on your custom documents and show them on any webpage will all the controls and tools you need to make sure the questions are on topic and costs are controlled!AnythingLLM supports link-scraping, PDFs, text documents, and so much more then you can throw at it!Learn about AnythingLLM Hosted: https://useanything.comOpen-source self-hosted AnythingLLM: https://github.com/Mintplex-Labs/anything-llmChapters0:00 Introduction to AnythingLLM Embeds0:34 AnythingLLM Cloud or Github setup0:52 Chatbots are everywhere - intro to demo!1:34 What is an AnythingLLM workspace?2:19 Aside: How to use any LLM for your AI chatbot2:45 Create the workspace3:25 Add custom documents to a workspace for knowledge3:42 AnythingLLM has a free embedder? WOW4:15 Showing how much smarter our workspace is4:49 Creating the embed & available controls and settings7:07 How to copy the embed to paste into your site7:21 How to do this with your site (or via Framer)8:03 Success!8:39 Customizations for your embed9:31 Thank you!

Running local LLMS for inferencing, character building, private chats, or just custom documents has been all the rage, but it isn't easy for the layperson.Today, with only a single laptop, no GPU, and two free applications you can get a fully private Local LLM RAG chatbot running in less than 5 minutes!This is no joke - the teams at Ollama and AnythingLLM are now fully compatible, meaning that the sky is the limit. Run models like LLama-2, Mistral, CodeLLama, and more to make your dreams a reality with only a CPU.Ollama: https://ollama.com/AnythingLLM: https://useanything.com/downloadAnd you are off to the races. Have fun!Chapters0:00 Introduction to Ollama x AnythingLLM on a laptop0:36 Introduction to Ollama1:11 Technical limitations1:48 Ollama Windows is coming soon!2:11 Let’s get started already!2:17 Install Ollama2:25 Ollama model selection2:41 Running your first model3:33 Running the Llama-2 Model by Meta3:57 Sending our first Local LLM chat!4:53 Giving Ollama superpowers with AnythingLLM5:31 Connecting Ollama to AnythingLLM6:45 AnythingLLM express setup details7:28 Create your AnythingLLM workspace7:45 Embedding custom documents for RAG for Ollama8:22 Advanced settings for AnythingLLM8:53 Sending a chat to Ollama with full RAG capabilities9:30 Closing thoughts and considerations#opensource #llm #privategpt #localagent #chatbot #ragchatbot #rag #openai #gpt #customgpt #localai #ollama #freechatbot #aitools #aitoolsyouneed #aitoolsforbusiness #freeaitool #freeaitools #llama2 #mistral #langchain #tutorial #aitutorial #aitools2024 #aiforbeginners #aiforproductivity

Was yesterday the day GPT-5 actually started training? This video has everything we think we know so far about GPT-5, drawing on exclusive interviews, OpenAI employee comments, Altman confirmations and more. Think of this as the ultimate compilation of GPT-5 news. Plus, as a bonus, you’ll get 1 super-practical tip on typing to ChatGPT and a Dalle-3 discovery.AI Insiders: https://www.patreon.com/AIExplainedGPT-5 Training Tweets?: https://twitter.com/gdb/status/1750558864469299622https://twitter.com/_jasonwei/status/1750609836713365570Altman Gates: https://www.youtube.com/watch?v=8-Ymdc6EdKwAltman Guessing Game: https://www.ft.com/content/dd9ba2f6-f509-42f0-8e97-4271c7b84dedOpenAI Cryptic Tweets Ben Newhouse: https://twitter.com/gopatrik/with_replies?ref_src=twsrc%5Egoogle%7Ctwcamp%5Eserp%7Ctwgr%5EauthorAltman Davos: https://www.youtube.com/watch?v=HtXdhcvUD1sAltman Axios: https://www.youtube.com/watch?v=QFXp_TU-bO8Altman In the Room: https://www.youtube.com/watch?v=AVmiEtbJyuw&t=480sKarpathy OS: https://medium.com/@marcelheinz/the-llm-os-a-glimpse-into-the-future-of-tech-with-andrej-karpathy-3bcbc0baf339Brockman Checkpoints: https://twitter.com/gdb/status/1646183424024268800?lang=en-GBLet’s Verify: https://arxiv.org/pdf/2305.20050.pdfMy Original Video on Verify: https://www.youtube.com/watch?v=hZTZYffRsKIThought Unfaithfulness: https://arxiv.org/abs/2307.13702Deepmind Original: https://arxiv.org/pdf/2211.14275.pdfOpenAI Data: https://openai.com/blog/data-partnershipsEtched AI 100T Video: https://www.youtube.com/watch?v=K0XZ_ShxWkIFrench Dataset: https://twitter.com/Dorialexander/status/1750810261856866783Peter Wildeford: https://twitter.com/peterwildefordGPT-4 Typos: https://openreview.net/pdf?id=STHKApXVMHOpenAI Redteaming: https://openai.com/blog/red-teaming-networkBrockman Unpredictable: https://www.youtube.com/watch?v=3sWH2e5xpdo&t=126sOpenAI Elections: https://openai.com/blog/how-openai-is-approaching-2024-worldwide-electionsBiden Robocall: https://www.youtube.com/watch?v=Yki1UNBTJ-AAnthropic Amodei Interview: https://www.youtube.com/watch?v=gAaCqj6j5sQLaziness: https://www.theverge.com/2024/1/25/24050829/openai-gpt-4-turbo-lazy-ai-modelAI Insiders: https://www.patreon.com/AIExplained Non-Hype, Free Newsletter: https://signaltonoise.beehiiv.com/

In this video, we are installing two user-friendly tools that make downloading, running, and managing a powerful local LLM to replace ChatGPT. Seriously.Today, with only a desktop computer with a retail GPU, and two free applications you will get a fully private Local LLM + RAG chatbot running in less than 5 minutes!This is no joke - the teams at LM Studio and AnythingLLM are now fully integrated for your convenience. Run models like LLama-2, Mistral, CodeLLama, and more to make your dreams a reality at no expense of privacy.LMStudio: https://lmstudio.aiAnythingLLM: https://useanything.com/downloadChapters:0:00 Introduction to LMStudio x AnythingLLM0:57 What is AnythingLLM?1:20 Installing LMStudio1:53 Installing AnythingLLM2:10 LMStudio Basic use tutorial4:28 Testing out our model5:32 How to level up your LLM chat abilities6:00 Connecting LMStudio to AnythingLLM7:53 Send a basic chat on AnythingLLM to our custom model8:26 Adding knowledge to our LMStudio model10:08 What the future of chat with local LLMs is going to look like

Hey everyone,Recently in AnythingLLM Desktop, we merged in AI Agents. AI Agents are basically LLMs that do something instead of just replying. We support both tool-call-enabled models like OpenAI but have even now have a no-code way to bring AI agents to every open-source LLMs like with Ollama or LMStudio.Now, with no code required, you can take any LLM and get automatic web scraping, web-browsing, chart generation, RAG memory, and summarization all autonomously and running locally.If the future of AI is agents, AnythingLLM is where it is going to happen!.Download AnythingLLM: https://useanything.com/downloadStar on Github: https://github.com/Mintplex-Labs/anything-llmChapters:0:00 Introduction to adding agents to Ollama0:45 What is Ollama?1:08 What is LLM Quantization?1:28 What is an AI Agent?2:54 How to pick the right LLM on Ollama5:11 Pulling Ollama models and running the server5:45 Downloading AnythingLLM Desktop6:17 AnythingLLM - Initial setup7:21 Sending our first chat - no RAG8:22 Uploading a document privately8:43 Sending a chat again but with RAG9:10 How to add agent capabilities to Ollama10:45 Add live web-searching to Ollama LLMs (Free)11:41 Using agents in AnythingLLM demonstration13:24 Agent document summarization and long-term memory14:35 Why you should use AnythingLLM x Ollama15:00 Star on Github, please!15:06 Thank you