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

Medical Chatbot

Medical Chatbot is a Flask web application that uses retrieval-augmented generation to answer questions about user-uploaded PDF documents, with Gemini-generated responses, Pinecone vector search, source citations and saved conversations.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Medical Chatbot — 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 need a self-hosted chat interface for querying supplied PDFs and want answers connected to source passages.

Who it is for

  • People who want to ask questions across medical PDFs they provide.
  • Developers seeking a Docker-based Flask RAG application to run and adapt.

Documented uses

  • Upload and manage multiple PDF documents.
  • Ask questions grounded in uploaded documents and inspect clickable citations with document names, page numbers and content previews.
  • Continue follow-up questions using persistent conversation history.
  • Use query rewriting in standard RAG or enable multi-hop reasoning for complex questions.
Before you choose

Requirements & limits

The README’s local setup requires Docker Desktop, Pinecone and Google Gemini API keys, and account registration before chatting. The repository identifies an Apache-2.0 license.

  • The app works from PDFs uploaded by the user rather than presenting itself as a general medical knowledge service.
  • Pinecone handles vector search, Gemini generates responses, and Hugging Face sentence-transformers provide embeddings.
  • PostgreSQL stores application records, including users, documents, conversations, messages, citations and feedback.
  • The README specifies Python 3.10, PostgreSQL 15 and 384-dimensional Pinecone embeddings.

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 the application with Docker Compose

Prepare and start the documented local application so it can be opened in a browser.

Before you start

  • Docker Desktop
  • Pinecone API key
  • Google Gemini API key
  • The project files

Steps

  1. Create a project-root .env file with PINECONE_API_KEY, GOOGLE_API_KEY and SECRET_KEY; GEMINI_MODEL may be set to gemini-2.5-flash.

  2. Run docker-compose up --build from the project.

  3. Open http://localhost:8080 in a browser.

  4. Register an account to begin using the chat.

Expected outcome

The README’s setup flow leads to the application’s browser chat, where a registered user can begin chatting.

Guide limitations

  • The setup requires credentials for both Pinecone and Google Gemini.
  • This recipe reflects the repository README; it is not an execution or compatibility test.
Documentation 1 ↗Documentation 2 ↗
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
Medical ChatbotUpload and manage multiple PDF documents.Cloud, Docker, WebThe README’s local setup requires Docker Desktop, Pinecone and Google Gemini API keys, and account registration before chatting. The repository identifies an Apache-2.0 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 ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
nazarli-shabnam/medical-chatbot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction