You are browsing as a guest. Sign up (or log in) to start making projects!

revankotapati

@revankotapati

Joined June 1st, 2026

  • 5Devlogs
  • 4Projects
  • 1Ships
  • 15Votes
Open comments for this post

@revankotapati on Ascend - The One

17h 28m 13s logged

Update 2

Finished the world and arcade part of the game. After further consideration, I decided to add a story mode to the game and design more models. I also finished 2 out of 3 models for my enemies and add effects and scenes to the game screen. However, I will have to create a new project and start again with the world and characters to better organize my scenes and scripts in Godot.

This is my first attempt at game development, so I am attempting to figure out how I can improve my code and organization quality while improving my game.

Another feature that I have been able to add is the addition of special projectiles: 1. Projectiles that act as magnets and pull all enemies together
2. Projectiles that chain hit multiple enemies and stop them for a brief amount of time
3. Projectiles that explode and impact multiple enemies

Below is an image of my code for my new project. I will continue to update on my journey.

@revankotapati

Update 2

Finished the world and arcade part of the game. After further consideration, I decided to add a story mode to the game and design more models. I also finished 2 out of 3 models for my enemies and add effects and scenes to the game screen. However, I will have to create a new project and start again with the world and characters to better organize my scenes and scripts in Godot.

This is my first attempt at game development, so I am attempting to figure out how I can improve my code and organization quality while improving my game.

Another feature that I have been able to add is the addition of special projectiles: 1. Projectiles that act as magnets and pull all enemies together
2. Projectiles that chain hit multiple enemies and stop them for a brief amount of time
3. Projectiles that explode and impact multiple enemies

Below is an image of my code for my new project. I will continue to update on my journey.

Replying to @revankotapati
0
3
Open comments for this post

@revankotapati on RAG App

40m 8s logged

Added an OCR feature to allow handwritten text to be used. I also updated the user-query feature by allowing the user to select their own settings for the RAG pipeline. Moreover, I was able to allow the user to upload files and improved the UI to make it look better.

@revankotapati

Added an OCR feature to allow handwritten text to be used. I also updated the user-query feature by allowing the user to select their own settings for the RAG pipeline. Moreover, I was able to allow the user to upload files and improved the UI to make it look better.

Replying to @revankotapati
0
6
Open comments for this post

@revankotapati on Ascend - The One

7h 9m 18s logged

Created the environment, enemies, character and the basic UI. My next task is to work on enhancing the UI and improving the physics of the game, especially movement.

@revankotapati

Created the environment, enemies, character and the basic UI. My next task is to work on enhancing the UI and improving the physics of the game, especially movement.

Replying to @revankotapati
0
3
Ship

@revankotapati on RAG App

For this project, I engineered a containerized, cloud-native Retrieval-Augmented Generation (RAG) assistant deployed on Hugging Face Spaces that enables users to securely upload documentation and query it in real time through a Streamlit chat interface. Writing native code directly with the modern google-genai and Pinecone Python SDKs allowed me to bypass bulky orchestrator frameworks, resulting in a lightweight, zero-local-storage pipeline that uses text-embedding-004 and gemini-1.5-flash. Navigating this build came with distinct engineering challenges, particularly resolving rigid SDK endpoint routing mismatches and optimizing a vector dimensionality gap by implementing types.EmbedContentConfig to dynamically truncate embedding outputs down to 768 dimensions to match the Pinecone serverless index. I am incredibly proud of how fast, clean, and cost-effective this standalone architecture turned out, as well as the strict system prompt guardrails that prevent hallucinations by defaulting to a clean fallback response whenever a query falls outside the uploaded context. To thoroughly test the live application, users simply need to verify their API keys, paste a technical text block into the ingestion sidebar to index the cloud vectors, and then run a mix of specific domain questions and out-of-domain prompts to observe the system's precise retrieval performance and defensive constraints.

  • 3 devlogs
  • 2h
Try project → See source code →
Open comments for this post

@revankotapati on RAG App

44m 1s logged

Finished backend and frontend connection.

@revankotapati

Finished backend and frontend connection.

Replying to @revankotapati
0
10
Open comments for this post

@revankotapati on RAG App

1h 0m 28s logged

I built the frontend and backend of this RAG pipeline using Python, GoogleGenAI, and Pinecone

@revankotapati

I built the frontend and backend of this RAG pipeline using Python, GoogleGenAI, and Pinecone

Replying to @revankotapati
0
5

Followers

Loading…