OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Research Agents

Sample Bedrock Deep Researcher

Sample Bedrock Deep Researcher is a Python and Streamlit application that uses Amazon Bedrock, LangGraph, LangChain AWS libraries and Tavily web search to research topics and generate structured articles or reports. Its workflow includes outline review and human feedback, section drafting, compilation and header-image generation with Amazon Bedrock Nova Canvas.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Sample Bedrock Deep Researcher — OpenViST project profile in Research Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when a writing task benefits from web research, an editable outline and section-by-section drafting before a complete article or report is assembled.

Who it is for

  • Writers preparing researched blog posts or articles.
  • People drafting reports who want to shape an outline before full content generation.
  • Developers exploring a Python research-writing workflow built with Amazon Bedrock and LangGraph.

Documented uses

  • Gather web research for a chosen topic.
  • Create and refine an article outline with human feedback.
  • Generate article sections and compile them into a complete draft.
  • Create a header image and copy the finished article to the clipboard.
Before you choose

Requirements & limits

  • The setup requires Python 3.12 and Poetry.
  • AWS authentication and enabled Amazon Bedrock model access in us-east-1 are prerequisites.
  • Tavily API credentials are required for web research.
  • The repository identifies the code license as MIT-0.

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 local Streamlit application

Install the project, configure its required environment and start the Streamlit interface.

Before you start

  • Python 3.12
  • Poetry
  • AWS authentication and enabled Amazon Bedrock model access in us-east-1
  • A Tavily API key for web research

Steps

  1. Clone the repository and enter its directory.

  2. Activate the Poetry environment and install dependencies with Poetry.

  3. Add the Tavily API key to env.tmp, then copy the environment variables into .env.

  4. Start the application with streamlit run bedrock_deep_research.py.

Expected outcome

The Streamlit application starts for entering article details and generating an outline.

Guide limitations

  • The setup assumes the us-east-1 region.
  • Amazon Bedrock model access must be enabled in that region.
Documentation 1 ↗
Source-based practical guide

Create and refine an article

Use the application workflow to research a topic, revise its outline and export the completed article.

Before you start

  • A running application configured with AWS Bedrock access and a Tavily API key

Steps

  1. Enter a topic and writing guidelines, adjust search parameters, and request an outline.

  2. Review the outline, give feedback or edit it directly, then accept it.

  3. Review the completed article and header image, make final formatting adjustments, and copy the article to the clipboard.

Expected outcome

A researched article with a generated header image that can be copied to the clipboard.

Guide limitations

  • The documented workflow covers article generation and clipboard export; it does not describe publishing the result to an external site.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
aws-samples/sample-bedrock-deep-researcher · Official homepage title · retained in its source language
How we review sourcesSuggest a correction