privateGPT AI technology page Top Builders

Explore the top contributors showcasing the highest number of privateGPT AI technology page app submissions within our community.

PrivateGPT

PrivateGPT is a tool that enables you to ask questions to your documents without an internet connection, using the power of Language Models (LLMs). It is 100% private, and no data leaves your execution environment at any point. You can ingest documents and ask questions without an internet connection!

PrivateGPT is built with LangChain, GPT4All, LlamaCpp, Chroma, and SentenceTransformers.

demo

Setup and Usage

  1. Install all required packages by running pip3 install -r requirements.txt.
  2. Download an LLM model (e.g., ggml-gpt4all-j-v1.3-groovy.bin) and place it in a directory of your choice.
  3. Rename example.env to .env and edit the variables according to your setup.
  4. Run python ingest.py to ingest your documents.
  5. Run python privateGPT.py to ask questions to your documents locally.

Supported Document Formats

PrivateGPT supports the following document formats:

  • .csv: CSV
  • .docx: Word Document
  • .doc: Word Document
  • .enex: EverNote
  • .eml: Email
  • .epub: EPub
  • .html: HTML File
  • .md: Markdown
  • .msg: Outlook Message
  • .odt: Open Document Text
  • .pdf: Portable Document Format (PDF)
  • .pptx: PowerPoint Document
  • .ppt: PowerPoint Document
  • .txt: Text file (UTF-8)

How It Works

PrivateGPT leverages local models and the power of LangChain to run the entire pipeline locally, without any data leaving your environment, and with reasonable performance.

  • ingest.py uses LangChain tools to parse the document and create embeddings locally using HuggingFaceEmbeddings (SentenceTransformers). It then stores the result in a local vector database using Chroma vector store.
  • privateGPT.py uses a local LLM based on GPT4All-J or LlamaCpp to understand questions and create answers. The context for the answers is extracted from the local vector store using a similarity search to locate the right piece of context from the docs.

System Requirements

Python Version

To use this software, you must have Python 3.10 or later installed. Earlier versions of Python will not compile.

C++ Compiler

If you encounter an error while building a wheel during the pip install process, you may need to install a C++ compiler on your computer. Follow the instructions for your operating system to install the appropriate compiler.

privateGPT AI technology page Hackathon projects

Discover innovative solutions crafted with privateGPT AI technology page, developed by our community members during our engaging hackathons.

Nirmaan HR

Nirmaan HR

Nirmaan.HR: Revolutionizing Candidate Sorting, Hiring, and Selection Introduction Nirmaan.HR is an innovative HR portal developed by Team Nirmaan to transform the hiring process. In today's fast-paced world, efficiency and accuracy in HR tasks are crucial, and Nirmaan.HR is designed to deliver on these fronts. Problem Statement HR professionals often spend countless hours manually sorting through resumes and job descriptions. This process is not only time-consuming but also prone to errors, detracting from the valuable time that could be dedicated to more strategic tasks. Nirmaan.HR addresses these challenges by leveraging AI to streamline the hiring process. Solution Overview Nirmaan.HR allows HR teams to upload job descriptions and resumes, automatically sorting candidates and storing data in a centralized database. This approach saves time and ensures that the best candidates are identified quickly and accurately. Key Features Automatic Candidate Sorting: Upload job descriptions and resumes, and let our AI match the best candidates for the job role. Centralized Database: All data is stored in one place, making it easy to retrieve past information and manage candidates. Direct Chat with Database: Seamlessly interact with the database through a chat interface to quickly access necessary data. Custom Email Sending: Send personalized emails to candidates directly from the application without the need to open other email clients. Custom Exam Creation: Design tailored exams to test candidates on relevant skills, ensuring a more effective evaluation process. Analytics and Reporting: Gain insights into your hiring process with detailed analytics and reports.

Trading-Agent-

Trading-Agent-

A trading agent AI is an artificial intelligence system that uses computational intelligence methods such as machine learning and deep reinforcement learning to automatically discover, implement, and fine-tune strategies for autonomous adaptive automated trading in financial markets This project implements a Stock Trading Bot, trained using Deep Reinforcement Learning, specifically Deep Q-learning. Implementation is kept simple and as close as possible to the algorithm discussed in the paper, for learning purposes. Generally, Reinforcement Learning is a family of machine learning techniques that allow us to create intelligent agents that learn from the environment by interacting with it, as they learn an optimal policy by trial and error. This is especially useful in many real world tasks where supervised learning might not be the best approach due to various reasons like nature of task itself, lack of appropriate labelled data, etc. The important idea here is that this technique can be applied to any real world task that can be described loosely as a Markovian process. This work uses a Model-free Reinforcement Learning technique called Deep Q-Learning (neural variant of Q-Learning). At any given time (episode), an agent abserves it's current state (n-day window stock price representation), selects and performs an action (buy/sell/hold), observes a subsequent state, receives some reward signal (difference in portfolio position) and lastly adjusts it's parameters based on the gradient of the loss computed. There have been several improvements to the Q-learning algorithm over the years, and a few have been implemented in this project: Vanilla DQN DQN with fixed target distribution Double DQN Prioritized Experience Replay Dueling Network Architectures Trained on GOOG 2010-17 stock data, tested on 2019 with a profit of $1141.45 (validated on 2018 with profit of $863.41):