OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Ragbase

Ragbase is a Python application with a Streamlit interface for asking questions about PDF documents. It extracts PDF text, creates semantic and character-based chunks, stores them for vector retrieval, reranks relevant passages and uses an LLM chain to produce answers. Its documented local stack includes Ollama, LangChain and Qdrant; a Groq API option provides remote inference.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Ragbase — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Ragbase when you want a Streamlit PDF question-answering workflow and can choose between a documented local Ollama setup and the Groq API option.

Who it is for

  • People who want to question a collection of PDFs through a locally run interface.
  • Developers prototyping a retrieval-augmented question-answering workflow with chunking and reranking.

Documented uses

  • Extract and organize PDF text into searchable chunks.
  • Retrieve and rerank relevant passages for a user query.
  • Generate an LLM-based answer from retrieved document content.
Before you choose

Requirements & limits

The repository documents a local setup and a Streamlit Cloud demo that runs with Groq API. Local setup requires Poetry and Ollama; using Groq requires an API key.

  • The documented default local model is gemma2:9b.
  • Groq is documented as an alternative to the local LLM; the Streamlit Cloud demo uses Groq API.
  • The application stack assigns separate roles to Streamlit for the interface, Qdrant for vector storage and search, FlashRank for reranking, and PDFium for text extraction.
  • The repository metadata lists an MIT license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Ragbase locally with Ollama

Install the documented local application and launch its Streamlit interface.

Before you start

  • The Ragbase Git repository
  • Poetry
  • Ollama

Steps

  1. Clone the repository and change into the ragbase directory.

  2. Install dependencies with Poetry.

  3. Fetch the default gemma2:9b model using Ollama.

  4. Start the Ollama server.

  5. Launch the app with Poetry and Streamlit.

Expected outcome

The documented local setup sequence launches the Ragbase Streamlit interface with Ollama serving the default model.

Guide limitations

  • The instructions describe setup and launch; they do not specify a separate PDF-upload or question-submission procedure.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
curiousily/ragbase · Official homepage title · retained in its source language
How we review sourcesSuggest a correction