Inspiration
I was recently working with some research papers and realized the amount of effort and time it takes to extract precise answers from huge research papers, so thought to build something to tackle this.
What it does
It extracts all the text from the research paper uploaded by the user and then uses LangChain Model and Open AI's API to get answers to the question asked by the user.
How I built it
It has been built using Python -Streamlit for web development, Open AI's GPT-3 model, LangChain Model to get the answer and Courier's API to send the email to the user.
Challenges I ran into
GPT-3 model can accept a max of 4096 tokens(8000 words) due to which big research papers couldn't be processed so I decided to use LangChain Model.
Accomplishments that we're proud of
I am proud that I could integrate multiple APIs into this project and make something that can impact the lives of so many research scholars around the world.
What's next for Research Buddy
Future Scope of Research Buddy would include auto-suggestion of research papers that would contain more information related to the question asked.
Built With
- courier
- langchain
- lottie-animations
- openai
- python
- streamlit
Log in or sign up for Devpost to join the conversation.