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

Rag With Amazon Opensearch And Sagemaker

Rag With Amazon Opensearch And Sagemaker is a Python sample application for question answering over enterprise content. It creates document embeddings, stores them in Amazon OpenSearch, retrieves relevant passages for a question, and supplies those passages as context to a language model. SageMaker endpoints provide embeddings and text generation, while a Streamlit interface presents the application.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Rag With Amazon Opensearch And Sagemaker — 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 as a starting point when you want to build a cloud-based RAG question-answering workflow over enterprise content and can deploy its AWS resources.

Who it is for

  • Teams building question-answering applications over enterprise documents.
  • Developers working with Amazon SageMaker, Amazon OpenSearch Service, LangChain and Streamlit.

Documented uses

  • Ingest enterprise documents into a vector-search knowledge base.
  • Retrieve passages relevant to a user’s question.
  • Ground a language model’s response in retrieved enterprise content.
  • Build a Streamlit question-answering interface backed by SageMaker and OpenSearch.
Before you choose

Requirements & limits

The repository is public and licensed under MIT-0. The documented application workflow depends on AWS resources deployed through CDK stacks.

  • The CDK stacks create SageMaker endpoints for both text generation and embeddings, plus an OpenSearch cluster.
  • Document ingestion is performed through a Jupyter notebook before the Streamlit app is run.
  • OpenSearch access credentials are stored in AWS Secrets Manager.
  • The sample is implemented in Python and the repository is not marked archived.

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 sample’s ingestion and Q&A workflow

Deploy the documented AWS components, index enterprise content, and start the Streamlit question-answering app.

Before you start

  • AWS environment for deploying the project’s CDK stacks.
  • SageMaker Studio with JupyterLab.
  • SageMaker endpoints for text generation and embeddings, an Amazon OpenSearch cluster, and its credentials in AWS Secrets Manager; the CDK stacks create these resources.

Steps

  1. Deploy the CDK stacks to create the SageMaker endpoints and OpenSearch cluster.

  2. Open JupyterLab in SageMaker Studio and use a terminal to clone the repository.

  3. Open and run the data_ingestion_to_opensearch notebook to ingest documents into OpenSearch.

  4. Run the Streamlit application using the app instructions.

Expected outcome

An indexed enterprise knowledge base and a Streamlit question-answering interface using retrieved passages as model context.

Guide limitations

  • The guide does not specify the content formats accepted by the ingestion notebook.
  • The app’s separate README provides its run instructions; the main README does not include the app launch command.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
aws-samples/rag-with-amazon-opensearch-and-sagemaker · Official homepage title · retained in its source language
How we review sourcesSuggest a correction