This file contains a set of questions data representing possible errors that users might inquire about. It is used for training and retrieval purposes in the application.
This file contains a set of questions data related to the user guide that users might ask. It is used for training and retrieval in the system to provide users with relevant answers based on the user guide.
This is the Python environment required for running the model. To activate the environment, use the following command: source model-env/bin/activate . Once activated, run the model using python3.9 model.py
This is the main model code which includes:
- Flask API for serving requests.
- Retrieval-Augmented Generation (RAG) mechanism.
- Deepseek R1 Model for generating responses.
This file lists all the required libraries and dependencies for running the project. To install the dependencies, use the following command: pip install -r requirements.txt
This will install all the necessary libraries for running the model and Flask API.
This is the cache of the JSON files used for storing the vector index. It speeds up the process of chunking documents into the vector database, which is used by the RAG retriever for improved performance in document retrieval.
