Pocket LLM
p/pocket-llm
The fastest neural search for your documents
Vinod Iyengar
ThirdAI PocketLLM — Personalized search and Q&A with AI on your own documents
Featured
23
ThirdAI PocketLLM is your personal knowledge search engine powered by AI. Memorize 1000s of pages from PDFs & Documents, scrape URLs, index through your inbox and more. Chat with your personal knowledge. Fully private. Trained on your laptop.
Replies
Vinod Iyengar
Hey Product Hunters! 🎉 We're beyond excited to introduce the all-new PocketLLM – your ultimate solution for private, AI-powered knowledge management. Whether you're a journalist, lawyer, student, or a prolific knowledge worker, PocketLLM is designed to supercharge your productivity while keeping your data secure. What's New in PocketLLM? 1. Native Gmail Integration: Say goodbye to cluttered inboxes and hello to streamlined email management. Sync, search, and manage your Gmails directly from PocketLLM, with unparalleled privacy. 2. Full PDF & DOC Search: Access and interact with every document on your laptop like never before. Ask questions, get AI-driven insights, and find exactly what you need without combing through files manually. 3. URL Indexing and Web Scraping: Keep track of important online resources by importing Chrome bookmarks or URLs. PocketLLM turns your browsing history into a searchable database, ensuring you never lose track of that crucial article again. 4. Coming Soon - Outlook, Slack, and GitHub: We're expanding our integrations to include your most-used platforms, making PocketLLM the center of your digital universe. Why PocketLLM? With the new version of PocketLLM, we've dramatically simplified the UX/UI to make it even more user-friendly. Our goal remains the same: to provide the only fully private personal knowledge management tool with AI capabilities. PocketLLM isn't just about storing information; it's about making that information work for you. Draft replies with AI, search across all your documents privately, and ask questions of your content as if you're chatting with a smart assistant. All this, while ensuring your data stays on your device, protected and private. Join Us on This Journey: We're thrilled to invite the Product Hunt community to try PocketLLM and see how it can transform the way you manage information. Your feedback is crucial to us as we continue to refine and expand PocketLLM's capabilities. Download now and start managing your knowledge smarter, not harder: [Download PocketLLM](https://www.thirdai.com/pocketllm/) We're offering 1 month of free premium access with the promo code: THIRDAI-POCKETLLM-PROMO We can't wait to hear what you think! Let's take the first step towards more efficient and secure knowledge management together. Happy Hunting! 🚀 - The ThirdAI Team
Harrison Johnson
Hey Vinod - this looks super cool! Would you recommend using this in a business use case for a help center like this? https://docs.flat.app/welcome/in... to help their customers? Or is this more like for individuals and personals? I could also imagine an individual use case within companies :thinking-face: maybe with employee onboarding or something like that
Vinod Iyengar
@harrisonjohnson we absolutely have an enterprise version of this caused NeuralDB that is suited contact center or help desk type use cases. https://www.thirdai.com/neuraldb...
Robiul Islam
This seems fantastic! It says you can also search URLs. So Will open the URL directly from the search or will just point to the URL?
Ye Cao
@robiul10 For example, you can export your browsing history as a CSV file. Then feed that CSV into the URL workspace you created in PocketLLM. You can then search the past browsing history and get a Reference to the exact URL! So, yes, you can get the Reference to the specific URL you are looking for!
Lyndon
This is a great idea, Nvidia VP is working on a os based product which is similar, but there are too many problems to subscribe and a few showstopper bugs and fb I need to report. I believe you're still in Alpha. Not sure I want to expose them or that feedback here. How do you prefer to receive that feedbac? Is there a discord or support email or contact form you prefer for bug reports.
Ye Cao
@lyndon1 The software by Nvidia requires a very high standard of hardware, so currently it's not for mainstream adoption. We believe that AI should be accessible to every hardware at the earliest possible time. Any feedbacks are more than welcome! Please join our discord community: https://discord.com/invite/thirdai
Lyndon
I have a large but too large chrome bookmark list exported them a a csv and when I tried to load the file, the app hung and then was using 6 GB of memory at one point before I killed it. Now it has been resource limited by windows and hangs loading the csv with bookmarks. The mail reading function is not useful, I have many gmails with non text characters at the beginning of the descriptive text, making this pretty much useless. Limiting the mail to 200 on a trial isn't that great either. Pricing is missing on your page the only way I found it was attempting to start a subscription. UI is needs a lot of work as well. Just a blank page with 2 or three sentences and an input line. Needs to be able to search all files on the machine and index them not individually add them.
Ye Cao
@lyndon1 Really appreciate for the feedbacks. As you can see, PocketLLM is the optimized for privacy: everything is done on user's computer without any of private data going to the cloud. In other words, the AI model training and inferencing all take place on users' computer. Therefore, it's possible that you could face large memory resource usage sometimes. One simple solution to address your concern is to tune some hyper-parameter of the AI model. I will ensure that the issues will be resolved in a timely manner. I want to invite you to our discord channel or connect with me in private: https://discord.com/invite/thirdai
Joly Llb
Really good work dear developer it's really helpful launch 💯
rylopa
lovely 💯💯
Immanuel Abbey
Congratulations to you guys. This took is very useful. Especially to those who use Pdf
Muhammad Yakubu
Congratulations to lunch This application wow its amazing
King's maker bjorn
Hi sir I am Hunter from Nigeria to be a part of your team to
Baba
Good product
Maina Madu
Thats awesome
Syed Azhan
I'm every time ready to learn about product Hunt.
Bob WIlsey
Just curious how are your going to differentiate from your competitors?
muhammad abubakar arabi
Great job I like this product
Prateek Kapoor
Congratulations on the launch! 🎉 This tool sounds incredibly useful for someone like me who constantly juggles through piles of documents, PDFs, and emails in search of valuable information. The ability to chat with my own personal knowledge assistant is a game-changer. Great work!
TA
Before PocketLLM I tried to use DocFetcher which has issues with PDFs which are over 80MB in size. You can change the RAM size limit of DocFetcher but throwing gigabytes upon gigabytes of data I never dared to do with it. Paperless is another tool, good in theory but it´s search engine called "Whoosh" is too fuzzy for my liking. NVIDIAs Chat with RTX gave surprisingly good search results. Having the ability to make use of the GPU is neat if you have the system for that and can stomach the electricity bills. Pitfalls of Nvidias solution are; it needs your browser for it´s GUI. It takes a lot of space and installs a couple dependencies. There is no apparent import export solution for already build indexes. Nvidias solution does not let you open the found result at the page it was found inside your PDFs. PocketLLM comes in and does things better. I recommend it if you want an easy to use "grep"or RAG (Retrieval Augmented Generation) solution which opens up indexed PDFs and highlights the searched result. PocketLLM is using less space and thanks to its usage of CPU + RAM can be used on cheaper hardware. It´s lovely that PocketLLM doesn´t rely on Acrobat reader. PocketLLM as well as its viewer can easily handle ~270Mb big PDF files. When I contacted the Third AI team regarding privacy and handling of data for business cases, they helped me out.