AI Models
Whatβs exciting?
PrivateGPT is powered by LangChain, LlamaCpp, Chroma, SentenceTransformers, and GPT4All itself. Use the power of AI to upgrade the document interaction experience today!
Run the Model Offline
- You can enjoy the freedom of running the entire pipeline locally, without any reliance on an internet connection. Well, no need to worry about data leaving your environment.
Ask questions to your docs locally
- Utilizing LangChain tools and HuggingFaceEmbeddings (SentenceTransformers), you can generate embeddings and store them in a local vector database using the Chroma vector store. All the information you need is at your fingertips.
100% privacy and safety
- Your privacy matters. PrivateGPT and GPT4All allow your data to stay completely secure and private. Feel confident knowing that your documents and questions remain in the utmost safety!
PrivateGPT Model
PrivateGPT supports a wide range of file types including CSV, docx, HTML, md,PDF, pptx, and txt and more. Ingest your files into the source_documents directory and enjoy seamless document interaction without an internet connection!
π Set Up the Environment
π Get started with asking questions to your docs locally
π Learn how does the model work
The list of supported extensions
GPT4All Model
Experience the revolution of language models with GPT4All. Open-source, on-edge, and ultra-powerful. Train, deploy, and dominate!
Your Challenge
π Over 24 hours of the Hackathon, you are challenged to build your ready-to-play solution utilizing the PrivateGPT model. In addition you can use other AI models to power-up your solution! Important! Your project should be developed during the Hackathon (within 24 hours from the Kick-Off Stream). Last but not least, be sure to have fun while you are creating!
As a reward
π₯ The winner will get virtual coffee with one of New Native founders to discuss the project, plans and just have a great time chatting. π The best solution will be to be invited to give a Talk at a lablab.ai Hackathon and be promoted across lablab.ai social media and the blog.
Additionally, finalists will receive lablab.ai SWAG!

More AI Models Available!
LangChain
The LangChain library has been developed to assist developers in building applications that combine LLMs with other technologies, allowing them to create truly intelligent and innovative products. π LangChain GitHub repo
Alpaca
Alpaca is designed to understand and execute tasks based on user instructions. The project provides a dataset, data generation process, and fine-tuning code for reproducibility. π GitHub repo
LLaMA
LLaMA is developed by the FAIR team of Meta AI and has been trained on a large set of unlabeled data, making it ideal for fine-tuning for a variety of tasks. π GitHub repo
CAMEL
Have multiple agents communicate with each other through role playing. π LangChain Implementation π GitHub repo
Stable Diffusion
Stable Diffusion is a latent text-to-image diffusion model capable of generating stylized and photo-realistic images. π Github repo
Whisper
An encoder-decoder architecture model is a powerful speech recognition and translation model trained on massive amounts of multilingual data. It can also identify languages, provide phrase-level timestamps, and transcribe multilingual speech to text.
Multilingual Semantic Search
A text embedding model, represents text meaning as numbers, which can effectively handle multiple languages.
Beginner-friendly Tutorials
PrivateGPT Overview
Learn how to setup and install PrivateGPT on your computer to chat to your PDFs (and other documents) offline and for free in just a few minutes.
GitHub guide for non-tech participants
Discover how to create your GitHub account, create a repo, add collaborators and start your project.
PrivateGPT & GPT4All Hackathon details
Join lablab.ai for 24 hours of fun building the new generation of NLP powered apps. Find all the relevant details below.
ποΈ Where and when
The hackathon starts on May 24 and ends on May 25. Over the weekend, you'll have the opportunity to learn from Cohere and lablab experts during workshops, keynotes, and mentoring sessions. The hackathon will take place on the lablab.ai platform.
π¦ΈπΌββοΈ Who should participate?
Previous experience in AI is not required but welcomed. While many participants are industry experts, we also welcome people with other types of domain knowledge that want to understand & explore how AI can be used in their fields.
π How about teams?
If you donβt have a team you will be able to match and team up with other participants around the world. Finding & creating teams can be done from the dashboard you can access after you enroll. We also recommend checking our Discord server to find teammates and discuss ideas. You can join it here
π οΈ How to participate in the hackathon
The hackathon will take place online on lablab.ai platform and lablab.ai Discord Server. Please register for both in order to participate. To participate click the "Enroll" button at the bottom of the page and read our Hackathon Guidelines.
π§ Get prepared
To get prepared for the hackathon, we recommend you to start at our Cohere technology page where you can find all the relevant information about the API and how to use it plus cohere tutorials and cohere boilerplates.
Hackathon FAQ
Who can join the Hackathon?
We welcome domain experts from all industries, not just AI or tech. Successful AI solutions require a combination of technical expertise and domain knowledge. Coding experience is recommended.
Do I need a team?
You are welcome to join as a team or solo, if solo. We encourage you to look for a team before the event. We recommend you to join the Deep Learning Labs Discord channel: https://discord.gg/gCuBwBB35k and posting in the #looking-for-team channel to get to know your potential future team members.
Do I need a Github account?
It is recommended, that at least one team member has a Github account. You can create one for free if you don't already have one.
I have other questions.
Feel free to reach us on social media, or through our Discord channel.
Event Schedule
- To be announced
Submitted concepts, prototypes and pitches
Submissions from the teams participating in the PrivateGPT & GPT4All Hackathon event and making it to the end π

GDOFP
Tech for good > Lack of information about moments that could suddenly start a war, rebellion, natural disaster, or even a new pandemic. Geo-political tensions are creating hostile and dangerous places to stay; the ambition of pharmaceutic industry could generate another pandemic "man-made"; channels of safe news are necessary that promote more hope than fear. Create a trend system identification that forecast where and when will happen rebellions, a pandemic, natural catastrophe, or war, combining different subjects like geo-political, environmental, and social development - collecting and crossing data like emotional factors, laws creation, government satisfaction, local and international news, and many others. The main point is to move the population before happening disasters or offer proper informational tools to decide where/when go out!
Innovaotve Geeks
Teams: PrivateGPT & GPT4All Hackathon
Check out the rooster and find teams to join at PrivateGPT & GPT4All Hackathon