Skip to content
View 07Codex07's full-sized avatar
💭
Building, Building and Building
💭
Building, Building and Building

Block or report 07Codex07

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
07Codex07/README.md

Vinayak Sahu

AI Research Associate at Vidur Research, working on production RAG systems, LLM fine-tuning, and agentic workflows.

LinkedIn · Portfolio · Medium · The Vector Daily


About

  • Role: AI Research Associate @ Vidur Research
  • Education: B.Tech CSE, KIIT University (2023–2027)
  • Location: India
  • Focus: Production RAG systems, LLM fine-tuning, agentic workflows
  • Currently: Building financial intelligence systems with CRAG and RAGAS at scale

Experience

AI Research Associate — Vidur Research (Subsidiary of Dreamskrin) Oct 2025 – Present · Remote · India

  • Implemented a Corrective RAG (CRAG) pipeline with a retrieval evaluator and knowledge refinement layer, cutting hallucinations 30% across 50+ financial instruments
  • Added evidence gating and contradiction detection ahead of generation, reaching 95%+ temporal accuracy with full citation provenance
  • Built an autonomous financial research agent performing multi-step retrieval and source-grounded analysis
  • Integrated the RAGAS evaluation suite, driving 10–20% retrieval quality gains per iteration across 130+ LLM calls per analysis session
  • Reduced inference cost 25% through caching and batching

Projects

Project Description Results
PrepGraph RAG chatbot with hybrid BM25 + FAISS retrieval, semantic cache, and a query router that selects between Llama 8b and 70b based on query complexity ↓40% LLM calls · ↓25% latency · ↓30% inference cost
Command Copilot Fine-tuned Phi-2 (2.7B params) with LoRA to translate plain English into Linux commands, running fully offline via Ollama 85% command accuracy · ↓40% inference time
ChatGPT Memory From Scratch Three-layer conversational memory system (short-term dict, FAISS long-term store, LLM summarization) built without LangChain No external memory framework used
FinVector Research Embeds financial news with FinBERT and clusters the resulting vector space to detect market regime shifts Applied on NIFTY 50 · 768-dim vectors · regime transition matrices
Reel2Retail End-to-end CV + NLP pipeline: YOLOv8 detects clothing in video frames, CLIP embeds them, FAISS matches to a product catalog >75% match confidence threshold
The Vector Daily Automated AI newsletter pipeline — scrapes arXiv, Medium, and HuggingFace, summarizes with an LLM, and ships as HTML daily 100+ articles/day, live in production
SecuFlow SSH intrusion detection with LLM-based threat analysis, Telegram-based human approval, and automatic UFW blocking Real-time blocking with explainable threat reports

Tech Stack

LangChain LangGraph FAISS PyTorch LoRA/QLoRA FastAPI Docker Python


GitHub Activity

github-snake

Writing


Contact

LinkedIn · Portfolio · vinayak1672006@gmail.com

Pinned Loading

  1. PrepGraph PrepGraph Public

    AI-powered conversational chatbot using LangGraph + Hybrid RAG (FAISS + BM25) with persistent memory and Groq LLaMA-3 for fast, context-aware document understanding.

    Python 1

  2. local_smart_linux_assistant local_smart_linux_assistant Public

    Offline AI-powered Linux assistant using a fine-tuned Phi-2 model with Ollama, enabling natural language interaction and command suggestions directly in the terminal.

    Jupyter Notebook 1

  3. FinVector_Research FinVector_Research Public

    Detects financial market regimes using semantic geometry of news embeddings (FinBERT) with clustering and statistical modeling to predict volatility and regime shifts ahead of price action.

    Python 1

  4. vector-daily-api vector-daily-api Public

    Personal Newsletter "TheVectorDaily"

    Python 1

  5. HIVE_Big_Data HIVE_Big_Data Public

    Data engineering pipeline for large-scale analytics using Hadoop + Hive

  6. _Portfolio_ _Portfolio_ Public

    Me, Myself and I

    TypeScript 1