Document retrieval from Wikipedia data using graph-lab
-
Updated
Sep 24, 2018 - Jupyter Notebook
Document retrieval from Wikipedia data using graph-lab
The "Questions" project, part of Harvard's CS50 AI course, develops an AI system for answering questions by retrieving documents and passages from a text corpus using tf-idf. It aids in understanding natural language processing (NLP) and information retrieval techniques.
A NLP based project to get the relevant documents from a bundle of large number of documents
An attempt of creating a model and pipeline for retrieving italian legal documents given a prompt from the user.
The Intelligent "ASKDOC" project combines the power of Langchain, Azure, OpenAI models, and Python to deliver an intelligent question-answering system, that scans your PDF documents and answer queries based on its contents. It can be queried using Human Natural Language.
Client SDK for starpoint.ai
Document Querying with LLMs - Google PaLM API: Semantic Search With LLM Embeddings
Implement Document Retrieval techniques to find who is closest to whom based on wikipedia data.
Run text embeddings with Instructor-Large on AWS Lambda.
course slides for Multimedia Information Retrieval
Chat-Bot made using whisper live, speechbrain and open AI API
"LangChat Explorer: Your intuitive document companion. Effortlessly explore vast information with natural language conversations. Simplify queries, gain insights, and embark on a seamless journey of knowledge discovery. Unleash the power of language with LangChat Explorer."
Kmeans, Kmeans++, Gaussian Mixtures
This repositiory implements various concepts and algorithms of Information Retrieval such as document classification, document retrieval, positional and logical text queries, Rocchio algorithm, retrieval evaluation metric etc.
Dive into LangChain, a powerful platform that lets you interact with your data like never before. This guide offers insights on its unique capabilities, helping you tap into your data in conversational ways.
An out-of-the-box, corpus-agnostic query expansion tool for lexical retrieval systems.
a minimal local embedding database.
These individiual projects are part of the coursework for the Coursera University of Washington course. I've also tried some fun new experiments with the data. Have fun checking them out !!
A basic and intuitive Python module for (Vector Space) IR system. (Focuses on simplicity and understandability)
Add a description, image, and links to the document-retrieval topic page so that developers can more easily learn about it.
To associate your repository with the document-retrieval topic, visit your repo's landing page and select "manage topics."