InstaIQ

Designed With 😇 :

• Flask
• Githubactions
• Nextjs
• Py
• TypeScript

InstaIQ is a query-driven platform that analyzes Instagram engagement data and delivers instant insights. Users can provide their Instagram handle, and the platform fetches detailed metrics such as likes, comments, and engagement rates. With a focus on answering user queries, InstaiQ allows users to ask specific questions like:

•“What is the max like count on a reel?”

•“Which type of post (static-image, reel, or carousel) gets the highest average likes?”

Using Hugging Face embedding models, Gemini, Langflow, and DataStax Astra DB, enabling seamless data analysis and retrieval. These technologies ensure fast, accurate, and scalable insights, making it a valuable tool for content creators, marketers, and businesses.

GitHub Link 🔗

• https://github.com/dvjsharma/Genz-AI

Deploy Link 🔗

• https://genz-ai.dvjshx.club/

Problem it solves 🙅‍♂️

• Analyzing Instagram engagement manually can be overwhelming, especially for users who want to extract specific insights quickly. Common challenges include: • Data Overload: Too much raw data with no actionable insights. • Specific Queries: Difficulty in finding answers like “Which post has the highest comments count?” • Efficiency: The time-consuming process of analyzing trends and performance.

Challenges I ran into 🙅‍♂️

• 1. Creating High-Quality Embeddings: • Generating embeddings that maintain context while processing large datasets. • Solution: Used Hugging Face embedding models for accurate and efficient embedding generation. 2. Fetching Real-Time Instagram Data: • Retrieve real-time Instagram data, such as likes, comments count, and other engagement metrics for various posts using an Instagram username. • Solution: Utilized the Instagram scraping API to efficiently extract the required data. 3. Scalable Data Storage and Retrieval: • Handling a growing database of user engagement metrics efficiently. • Solution: Leveraged DataStax Astra DB for robust vector storage and low-latency retrieval. 4. Efficient Query Processing: • Answering complex user queries with minimal latency. • Solution: Integrated Langflow and Gemini to build modular and scalable query pipelines.