Showing results for Gemini Vector Art
GitHub Repo
https://github.com/RohitKModi777/Investment_Analysis_RAG_Cb_on_largesize_pdf
RohitKModi777/Investment_Analysis_RAG_Cb_on_largesize_pdf
A high-performance Retrieval-Augmented Generation (RAG) system designed for academic and professional investment analysis. This system utilizes Google Gemini for state-of-the-art text embeddings and intelligent generation, with MongoDB serving as the vector-compatible metadata store.
GitHub Repo
https://github.com/azizmabrouk11/job-candidate-semantic-matching
azizmabrouk11/job-candidate-semantic-matching
A cutting-edge hybrid matching system that fuses state-of-the-art semantic search with intelligent rule-based evaluation to revolutionize job-candidate pairing. Built with Google Gemini embeddings, Qdrant vector database, MongoDB, and a custom rule engine.
GitHub Repo
https://github.com/ADP-1/RAG-PROJECT-Code-Documentation-Helper
ADP-1/RAG-PROJECT-Code-Documentation-Helper
Code Documentation Helper is a RAG-based system that allows developers to ask natural language questions and receive context-aware answers from the official requests library documentation. The project leverages LangChain and FAISS vector storage alongside state-of-the-art LLMs like Google Gemini or FLAN-T5 to provide accurate,.
GitHub Repo
https://github.com/Jenisis-03/Vector
Jenisis-03/Vector
🚀 Production-grade RAG system leveraging Neural Search & Gemini Pro LLM to transform static documents into intelligent conversations. Powered by state-of-the-art semantic embeddings & vector search technology. 98% accuracy in context retrieval.
GitHub Repo
https://github.com/honcyeung/Automated-News-Article-Analysis
honcyeung/Automated-News-Article-Analysis
This project is an automated pipeline that fetches news articles, enriches them with AI-generated insights from the Google Gemini API, and stores the data in a vector database for analysis.
GitHub Repo
https://github.com/Behz4dH/Advanced-Retrieval-Augmented-Generation-System
Behz4dH/Advanced-Retrieval-Augmented-Generation-System
Advanced RAG pipeline that combines custom PDF parsing with Docling, hybrid vector search with parent document retrieval, and intelligent LLM reranking to deliver state-of-the-art document question-answering capabilities. Features multi-model integration (OpenAI, Gemini), chain-of-thought reasoning, query routing for complex comparisons.
GitHub Repo
https://github.com/Vishwa-201105/InfoGopher--News-Letter-Article-Research-Tool