How does RagWiser work?

RagWiser extracts text from PDFs, splits it into chunks, and stores embeddings in a vector database. When you ask a question, it retrieves relevant document chunks, combines them with your query, and uses OpenAI's GPT models to generate an answer.

What technologies does RagWiser use?

RagWiser is built with Java 21, Spring Boot 3.3.2, Spring AI 1.0.0-M1, PostgreSQL with pgvector extension, Docker, and OpenAI GPT-4.

How do I upload a PDF document to RagWiser?

You can upload a PDF document using the `/api/rag/upload` REST API endpoint with a multipart/form-data request, including the PDF file as the `file` parameter.

What database does RagWiser use?

RagWiser uses a PostgreSQL database with the pgvector extension to efficiently store and retrieve document embeddings for semantic search.

RagWiser

Name: RagWiser
Author: RobertoDure

0•

Enables users to upload PDF documents, process them, and ask questions about their content using natural language, powered by Retrieval Augmented Generation (RAG).

RagWiser is a Spring Boot-based Retrieval Augmented Generation (RAG) system designed for document question-answering. It allows users to upload PDF documents, which are then processed to extract text, split into chunks, and have their vectorized representations stored in a PostgreSQL database using the pgvector extension. Users can then ask questions about the document content using natural language, and the system retrieves relevant context to generate accurate answers using OpenAI's GPT models. RagWiser leverages Spring AI for vector store and LLM integration, making it an advanced solution for knowledge retrieval and question answering from documents.

主な機能

01Automatically extract text from PDFs, split it into chunks, and store embeddings

02Generate accurate answers based on document content using RAG

03Leverages Spring AI for vector stores and LLM integration

04Query documents using natural language with semantic search

050 GitHub stars

06Upload and process PDF documents via REST API

ユースケース

01Integrate RAG capabilities into other AI systems using Spring AI's Tool Callbacks

02Quickly find answers within large PDF document collections

03Build a question-answering system on top of a knowledge base of PDF documents