Projects using Docker in BengaluruProjects using Docker in Bengaluru
Cover image for Renidy - AI-Powered Funeral Planning
Renidy - AI-Powered Funeral Planning & Concierge SaaS
0
89
Cover image for Built a full-stack online auction
Built a full-stack online auction platform using Flask, PostgreSQL, Docker and GitHub Actions. The system included role-based access, real-time bidding, REST APIs and a relational database, with automated CI/CD and 95% :unit and integration test coverage. Developed collaboratively in a five-person Scrum team.
0
28
Cover image for Self-hosted AI agent platform. The
Self-hosted AI agent platform. The same voice and chat agents, deployed inside the customer's own cloud or datacentre, with per-tenant encryption, audit logging and no data leaving their network. Built and run by Shielva Sense.
0
18
Cover image for Evaluting Agentic workflow (build with N8N) using Langfuse.
Evaluting Agentic workflow (build with N8N) using Langfuse.
0
22
Cover image for Autonomous Task Orchestration & Power
Autonomous Task Orchestration & Power Grid Simulation Engine:
0
89
Cover image for Ever watched an AI write
Ever watched an AI write bad SQL, instantly realize its mistake, and rewrite it perfectlyโ€”all without human intervention? Over the weekend, I built the Autonomous Data Analyst Agent. It doesnโ€™t just translate natural language to SQL; it actively debugs itself. ๐—ง๐—ต๐—ฒ ๐—ฃ๐—ฟ๐—ผ๐—ฏ๐—น๐—ฒ๐—บ: Enterprises want AI to query their proprietary databases, but LLMs often hallucinate columns or mess up syntax. ๐—ง๐—ต๐—ฒ ๐—ฆ๐—ผ๐—น๐˜‚๐˜๐—ถ๐—ผ๐—ป: I engineered a Self-Correcting Reflection Loop using LangGraph. Hereโ€™s what happens under the hood: 1๏ธโƒฃ You ask a complex question in plain English. 2๏ธโƒฃ The LLM generates DuckDB-flavored SQL. 3๏ธโƒฃ The Executor node runs it securely in a local container. 4๏ธโƒฃ ๐Ÿ”„ ๐—ง๐—ต๐—ฒ ๐— ๐—ฎ๐—ด๐—ถ๐—ฐ: If DuckDB throws a parser error, the Reflection node catches it, feeds the error trace back to the LLM, and auto-corrects the query. 5๏ธโƒฃ Once successful, a Python agent generates a Matplotlib visualization, streaming everything to a sleek Next.js dark-mode UI. Plus, I integrated LangGraph MemorySaver, allowing the agent to retain context for human-like follow-up questions. ๐—ง๐—ฒ๐—ฐ๐—ต ๐—ฆ๐˜๐—ฎ๐—ฐ๐—ธ: Next.js, FastAPI, LangGraph, DuckDB, Groq (Llama-3), Docker Compose. Everything is fully containerized and open-source. Drop a โญ on the repo and let me know what you think! ๐—š๐—ถ๐˜๐—›๐˜‚๐—ฏ ๐—ฅ๐—ฒ๐—ฝ๐—ผ: https://lnkd.in/ddnE9rgq (https://lnkd.in/ddnE9rgq)hashtag#AI (https://www.linkedin.com/search/results/all/?keywords=%23ai&origin=HASH_TAG_FROM_FEED) hashtag#LangGraph (https://www.linkedin.com/search/results/all/?keywords=%23langgraph&origin=HASH_TAG_FROM_FEED) hashtag#DataEngineering (https://www.linkedin.com/search/results/all/?keywords=%23dataengineering&origin=HASH_TAG_FROM_FEED) hashtag#Nextjs (https://www.linkedin.com/search/results/all/?keywords=%23nextjs&origin=HASH_TAG_FROM_FEED) hashtag#FastAPI (https://www.linkedin.com/search/results/all/?keywords=%23fastapi&origin=HASH_TAG_FROM_FEED) hashtag#Docker (https://www.linkedin.com/search/results/all/?keywords=%23docker&origin=HASH_TAG_FROM_FEED) hashtag#MachineLearning (https://www.linkedin.com/search/results/all/?keywords=%23machinelearning&origin=HASH_TAG_FROM_FEED) hashtag#OpenSource (https://www.linkedin.com/search/results/all/?keywords=%23opensource&origin=HASH_TAG_FROM_FEED)
1
56