Showing results for knowledge based Vector Product Vector
GitHub Repo
https://github.com/KushagraKatiyar06/Riva
KushagraKatiyar06/Riva
Riva lets you paste two URLs: your product and a competitor. Riva then dispatches autonomous browser agents to research both in parallel. It extracts pricing, features, and documentation, vectorizes everything into Cloudflare's knowledge base, and gives you an AI chat interface to interrogate the data, and generate PDFs/PPTs.
GitHub Repo
https://github.com/Zyl0812/ShopSage-KB
Zyl0812/ShopSage-KB
A RAG-powered knowledge base QA system for product manuals, featuring multi-source hybrid retrieval (dense vector, HyDE, knowledge graph, web search), BGE reranking, and streaming answer generation via LangGraph orchestration.
GitHub Repo
https://github.com/appsec2008/librarian-landing
appsec2008/librarian-landing
A polished landing page for Project Librarian — an LLM-compiled knowledge base that replaces vector databases and RAG pipelines with a self-healing Markdown wiki. The page should showcase the product overview, architecture pipeline, usage instructions, CLI reference, API docs, and competitive differentiation. · Built with Manus
GitHub Repo
https://github.com/Sanujen/TransFi-RAG-System
Sanujen/TransFi-RAG-System
This project implements a Retrieval-Augmented Generation (RAG) pipeline to answer questions about TransFi’s products and solutions. It uses asynchronous scraping, semantic embeddings, and vector-based retrieval to build a local knowledge base of TransFi’s website content.
GitHub Repo
https://github.com/thekunalanand/Lexicon-Based-Twitter-Sentiment-Analysis
thekunalanand/Lexicon-Based-Twitter-Sentiment-Analysis
Sentiment analysis deals with identifying and classifying opinions or sentiments expressed in source text. Social media is generating a vast amount of sentiment rich data in the form of tweets, status updates, blog posts etc. Sentiment analysis of this user generated data is very useful in knowing the opinion of the crowd. Twitter sentiment analysis is difficult compared to general sentiment analysis due to the presence of slang words and misspellings. The maximum limit of characters that are allowed in Twitter is 140. Knowledge base approach and Machine learning approach are the two strategies used for analyzing sentiments from the text. In this paper, I try to analyze the twitter posts about electronic products like mobiles, laptops etc using Machine Learning approach. By doing sentiment analysis in a specific domain, it is possible to identify the effect of domain information in sentiment classification. I present a new feature vector for classifying the tweets as positive, negative and extract peoples' opinion about products
GitHub Repo
https://github.com/suy1968/Movie_Recommendation-Engine
suy1968/Movie_Recommendation-Engine
Movie_Recommendation-Engine Introduction: Recommender System are widely used today in all most all the applications.The purpose of a recommender system is to suggest users something based on their interest or usage history.Two most ubiquitous types of personalized recommendation systems are Content-Based and Collaborative Filtering. Collaborative filtering produces recommendations based on the knowledge of users� attitude to items, that is it uses the �wisdom of the crowd� to recommend items. In contrast, content-based recommendation systems focus on the attributes of the items and give you recommendations based on the similarity between them. We have created a Recommender sysem using Spotify We have Scrapped dataset from SPOTIFY using our custom scraper, "Scrapify". The Scrapped data is converted to as csv file and used for further processing.The dataset contains appromixately 11k observations Data Description: -name : Name of the user -artist : Name of the artist -danceability : Ranges from 0 to 1 -key : Ranges from 0 to 11 -mode : Ranges from 0 and 1 -instrumentalness : Ranges from 0 to 1 -duration : Duration of the song in minutes -energy : Ranges from 0 to 1 -loudness : Float typically ranging from -60 to 0 -speechiness : Ranges from 0 to 1 -acousticness : Ranges from 0 to 1 -tempo : Float typically ranging from 0 to 150 -liveness : Ranges from 0 to 1 -valence : Ranges from 0 to 1 -popularity : Ranges from 0 to 100 -hollywood : Hollywood song 1 | Bollywood song 0 Project Goals The goals for this project are: -Scrap the website and collect the required data -Organise the data into a Structured format Gather insights from data analysis about the columns used Perform EDA and remove unwanted columns -Use the Cosine Similarity to calculate a numeric quantity that denotes the similarity between two songs. Since we have used the vectors, calculating the Dot Product will directly give us the Cosine Similarity Score. Ouput the top 5 recommended songs Technologies Used: Python Google Colab Spotify API & custom scraper
GitHub Repo
https://github.com/pratyushcodes-source/PANASONIC-CHATBOT
pratyushcodes-source/PANASONIC-CHATBOT
The Panasonic Self-Help Chatbot is an AI-powered assistant designed to provide instant, accurate, and context-aware answers to user queries about Panasonic products. By leveraging local LLMs (Ollama) and vector embeddings (ChromaDB), the chatbot transforms Panasonic product manuals and customer reviews into a searchable knowledge base.
GitHub Repo
https://github.com/Wasim7x/AssistPro
Wasim7x/AssistPro
AssistPro — An AI-powered RAG chatbot that retrieves and generates context-aware answers to assist users with project-related queries. Built using vector search, LLMs, and Flipkart product data as the knowledge base.
GitHub Repo
https://github.com/thakoreh/Cannondale-Business-Intelligence-Agent
thakoreh/Cannondale-Business-Intelligence-Agent
An AI-powered business intelligence agent that answers questions about Cannondale Synapse bicycles. It scrapes product data from the Cannondale website, builds a vector knowledge base, and provides text-based insights through a Chatbot using Retrieval-Augmented Generation (RAG).
GitHub Repo
https://github.com/AnshuVairagade/Flipkart_Product_Recommendation_Chatbot