Development - Python / ChromDB / MongoDB NodeJs
Budget: $250 – $750 AUD
Content cretion and Structured Data Management App with AI
Develop a feature in the React.js frontend for users to upload articles and structured data. The user interface must be intuitive and efficiently handle file uploads.
Ensure that uploaded content is appropriately categorized and stored in the database, making it easily retrievable for future use.
Automated Storage of Scraped Data:
Implement a backend system, likely using Python and FastAPI, to automatically store scraped data. This system should be capable of categorizing the content based on relevant keywords.
The backend should be robust and efficient, handling large volumes of data with ease.
Automating Embeddings/Vectorization of Database:
Develop a mechanism for automatic generation of embeddings or vectorizations for the data stored in the database.
Select an appropriate OpenAI Embeddings model that aligns with the type of content and the requirements of the RAG protocol.
Creating a Robust Database System:
Transition from using CSV files to a more advanced database system to store and manage various elements such as scraped content, written articles, outlines, and keywords.
This database will play a crucial role in linking content to initial prompts and managing the workflow.
Frontend Development in React.js:
Develop one or two screens using React.js for users to modify prompts and code. This feature will enhance user interaction and make the system user-friendly.
Building a Simple UI for Automation:
Design a UI that facilitates automation of the entire application. This UI should include:
An upload feature for CSV files for easy data input.
A function to automate the selection of the first 10 responses from the Google Search API.
Options to alter script settings from the frontend.
Coding a Retriever-Augmented Generation (RAG) Protocol App:
The RAG protocol app will utilize both existing scraped content and newly written articles. It will store this content in the database, serving as a reservoir for content creation and preventing content cannibalization.
Customer Login and Document Management:
Implement a customer login feature for personalized access and security.
Include functionality for customers to upload documents for content creation and receive the generated output.
Python Code Review:
Review and refine existing Python scripts to ensure they align with new functionalities and integrate smoothly with the overall application.
Application Deployment on a Server:
Deploy the application on a dedicated server, setting up the server environment and ensuring all components function correctly.
Server Access Assistance:
Provide necessary assistance for server access, including managing credentials and access rights.
Using the Provided Gist for Web App Development:
Utilize the structure from the provided Gist for scraping, data management, and writing content through prompts.
Develop UI components for prompt input, content generation, and displaying final content.
Integrate the RAG protocol into the app to store and create embeddings based on uploads and scraped data.
Proposed Timeline:
Hours 1: Frontend Development (Content Upload Feature)
Hours 2: Backend Development (Scraped Data Storage)
Hours 3: Embeddings/Vectorization Automation
Hours 4: Integration and Testing (Including RAG Protocol Implementation)
Develop a feature in the React.js frontend for users to upload articles and structured data. The user interface must be intuitive and efficiently handle file uploads.
Ensure that uploaded content is appropriately categorized and stored in the database, making it easily retrievable for future use.
Automated Storage of Scraped Data:
Implement a backend system, likely using Python and FastAPI, to automatically store scraped data. This system should be capable of categorizing the content based on relevant keywords.
The backend should be robust and efficient, handling large volumes of data with ease.
Automating Embeddings/Vectorization of Database:
Develop a mechanism for automatic generation of embeddings or vectorizations for the data stored in the database.
Select an appropriate OpenAI Embeddings model that aligns with the type of content and the requirements of the RAG protocol.
Creating a Robust Database System:
Transition from using CSV files to a more advanced database system to store and manage various elements such as scraped content, written articles, outlines, and keywords.
This database will play a crucial role in linking content to initial prompts and managing the workflow.
Frontend Development in React.js:
Develop one or two screens using React.js for users to modify prompts and code. This feature will enhance user interaction and make the system user-friendly.
Building a Simple UI for Automation:
Design a UI that facilitates automation of the entire application. This UI should include:
An upload feature for CSV files for easy data input.
A function to automate the selection of the first 10 responses from the Google Search API.
Options to alter script settings from the frontend.
Coding a Retriever-Augmented Generation (RAG) Protocol App:
The RAG protocol app will utilize both existing scraped content and newly written articles. It will store this content in the database, serving as a reservoir for content creation and preventing content cannibalization.
Customer Login and Document Management:
Implement a customer login feature for personalized access and security.
Include functionality for customers to upload documents for content creation and receive the generated output.
Python Code Review:
Review and refine existing Python scripts to ensure they align with new functionalities and integrate smoothly with the overall application.
Application Deployment on a Server:
Deploy the application on a dedicated server, setting up the server environment and ensuring all components function correctly.
Server Access Assistance:
Provide necessary assistance for server access, including managing credentials and access rights.
Using the Provided Gist for Web App Development:
Utilize the structure from the provided Gist for scraping, data management, and writing content through prompts.
Develop UI components for prompt input, content generation, and displaying final content.
Integrate the RAG protocol into the app to store and create embeddings based on uploads and scraped data.
Proposed Timeline:
Hours 1: Frontend Development (Content Upload Feature)
Hours 2: Backend Development (Scraped Data Storage)
Hours 3: Embeddings/Vectorization Automation
Hours 4: Integration and Testing (Including RAG Protocol Implementation)