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

Simple Rag

Simple RAG is a Python retrieval-augmented generation application that processes documents into contextualized chunks, stores sparse and dense vectors in Milvus, and supports multi-turn question answering through a Streamlit interface or an included Telegram bot script.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Simple Rag — 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 it when you want a Python project for indexing documents in Milvus and building a multi-turn, document-grounded Q&A experience, and can configure the database, Ollama models, and application dependencies.

Who it is for

  • Developers building a document-grounded question-answering application with Milvus and Ollama.
  • Teams or individuals adapting the sample ingestion flow to their own document collection.
  • Builders who want a multi-turn assistant with coreference resolution and a choice of Streamlit or Telegram interaction.

Documented uses

  • Index a folder of documents as contextualized chunks in a Milvus vector database.
  • Ask questions grounded in the indexed content through a Streamlit application.
  • Maintain conversational context across multiple turns and resolve references in chat history.
  • Adapt the interaction layer to the included Telegram bot script.
  • Replace the configured Ollama models in the ingestion and Streamlit scripts.
Before you choose

Requirements & limits

The public GitHub repository states that the project is open-source under the MIT License.

  • The project requires a Milvus database; the README recommends Zilliz Cloud as a convenient option but also allows self-hosted Milvus.
  • The documented model setup uses Ollama, with Llama 3.1 8B for contextual chunking and Qwen2.5 14B for user interaction; the scripts allow these choices to be changed.
  • The sample data is Al-Manar English news. The README describes processing a folder of documents but does not specify collection-specific preprocessing.
  • The repository includes a pre-written Telegram bot script, but its runtime configuration and integration details are not specified.
  • The README recommends a non-reasoning model for general use.

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 and launch the Streamlit document Q&A app

Prepare the documented Milvus and Ollama prerequisites, index a folder of documents, and start the Streamlit interface.

Before you start

  • A Milvus database, either self-hosted or on Zilliz Cloud, with the schema described in insertDataChunks.py.
  • Python and the repository's requirements, installed with pip install -r requirements.txt.
  • Ollama configured with the models used by the scripts, or modified model settings in insertDataChunks.py and streamlit_app.py.
  • NLTK, installed with pip install nltk.
  • A folder of documents to process.

Steps

  1. Set up Milvus and review the schema in insertDataChunks.py.

  2. Install the repository dependencies and NLTK, then install and configure Ollama.

  3. Run python insertDataChunks.py and provide the path to the document folder when prompted.

  4. Run streamlit run streamlit_app.py to start the interface.

Expected outcome

A Streamlit interface connected to document chunks processed and inserted into Milvus for retrieval-augmented question answering.

Guide limitations

  • The README uses the repository's sample folder for testing and does not specify collection-specific preprocessing for other document sets.
  • The README does not detail runtime configuration for the optional Telegram bot.
  • Changing Ollama models may change resource requirements.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Simple RagIndex a folder of documents as contextualized chunks in a Milvus vector database.Server, WebThe public GitHub repository states that the project is open-source under the MIT License.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
husaynirfan1/simple-rag · Official homepage title · retained in its source language
How we review sourcesSuggest a correction