Inspiration
Create an easily configurable AI assistant that can help with correct filling of documents and save time.
What it does
docMaster analyzes a document using given instructions about the document's structure. These instructions can be predefined by us, defined by an organization for its employees or defined by the user themselves. Once analysis is done, the user receives a report of what data is missing or inconsistent or if there are any grammatical errors and how it can be improved. The user can also chat with docMaster and have multiple conversations about different document types.
How we built it
docMaster was built using python with OpenAI's python library for communication with the assistant model, MongoDB for storing information and threads and flask for the REST API. The frontend was built using React.
Challenges we ran into
Our biggest challenges were learning about OpenAI's assistants and how to utilize them using the API and integrating the frontend with the backend.
Accomplishments that we're proud of
What we learned
What's next for AI Generated - 03
If we were to continue with the project, we would like to improve our backend architecture and add features like user and organizational login, ability to edit the user's instructions, have the assistant create templates based on the provided instructions, organizing user's/organizational's instructions into folders and make a public API so docMaster would be usable without a frontend or with a custom one. Everything part of a subscription of course :)
Log in or sign up for Devpost to join the conversation.