Inspiration
We were inspired by OpenAI's ChatGPT and wanted to create its coding generative abilities in a project of our own.
What it does
AI Coding Assistant, as the name suggests, is an AI chatbot to help users with all programming and coding-related queries, providing code snippets in any programming language, along with answering questions from your code files. It also has a RAG model enabled, that allows user to input their source code files directly so that they can get tailored answers from AI Coding Assistant.
How we built it
We used LangChain and the OpenAI API system to use the latest GPT4o model to leverage ChatGPT's generative features, with a few embedding and vector store systems to manage the custom file inputs. All this is under a slick-looking dark-themed Streamlit user interface.
Challenges we ran into
We ran into challenges with LangChain while trying to get the chatbot to remember conversations and store chats. Due to several deprecated functions and updates in the LangChain library, we had to read the LangChain docs heavily during the dev process to fix the issues.
Accomplishments that we're proud of
We're very proud of the way AI Coding Assistant works, it handles all the functionalities quite neatly without any under-the-hood issues. We're also very proud of our hybrid RAG model, allowing the user to converse with their code files.
What we learned
We learned a lot about the potential OpenAI, GPT4o and LangChain hold in the future of AI app development. We've also definitely learned a lot about ourselves as developers and as a team.
What's next for AI Coding Assistant
Future of AI Coding Assistant: IDE integration into popular IDEs (VS Code, XCode, etc.) like Amazon Q and GitHub Copilot. Adding more GPT models for genre-specific tasks like UI development, game development, etc.
Built With
- langchain
- openai
- python
- streamlit
Log in or sign up for Devpost to join the conversation.