Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/szymciem8/thesis-ai-assistant

Thesis Assistant powered by OpenAI, Langchain and Vector databases.
https://github.com/szymciem8/thesis-ai-assistant

docker docker-compose elasticsearch langchain nlp openai python

Last synced: about 2 months ago
JSON representation

Thesis Assistant powered by OpenAI, Langchain and Vector databases.

Awesome Lists containing this project

README

        

# Thesis-AI-Assistant

## Overview

Thesis-AI-Assistant is an application designed to assist users in the process of researching and analyzing PDF articles for academic purposes. The application provides a user-friendly interface for downloading PDF articles, conducting chat-based interactions for analysis, and generating summaries and keywords. Additionally, users can upload multiple PDFs and ask questions about them using a language model.

![Single article chat](/images/single_article_chat_screen.png)

## Features

### 1. PDF Article Analysis

- **Download PDF Articles:** Easily download PDF articles for analysis directly within the application.

- **Chat Interface:** Interact with the AI Assistant through a chat interface, enabling a natural conversation for analysis.

- **Elasticsearch or Chroma Integration:** Choose between Elasticsearch or Chroma for efficient and powerful search capabilities.

### 2. Summary and Keywords Generation

- **Generate Summaries:** Obtain concise summaries of the content within the PDF articles.

- **Extract Keywords:** Automatically extract keywords to provide a quick overview of the main topics covered.

### 3. Bulk PDF Analysis with Language Model

- **Upload Multiple PDFs:** Streamline your research process by uploading multiple PDFs at once.

- **Ask Questions with LLM (Large Language Model):** Utilize the power of a large language model to ask specific questions about the content of the uploaded PDFs.

## Getting Started

### Prerequisites

The app is built with Docker. Use the command below to start the app locally.
```
docker-compose up
```