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

Retrieval Augmented Generation For News

Retrieval Augmented Generation For News is an open-source Python application that collects New York Times RSS/API content, embeds article headlines and descriptions, stores them in persistent ChromaDB collections, retrieves related articles and generates summaries.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Retrieval Augmented Generation For News — 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 building or examining a news retrieval and summarization pipeline based on New York Times RSS/API content.

Who it is for

  • Developers exploring retrieval-augmented generation for news.
  • Builders who want a starting point for organizing and summarizing articles by topic or source.

Documented uses

  • Collect news content from the documented New York Times feeds.
  • Embed and store article information in separate ChromaDB collections by domain.
  • Retrieve related articles and summarize their available text.
Before you choose

Requirements & limits

The documented setup requires New York Times API and Replicate API keys. The public repository is MIT-licensed.

  • The collection path is documented for New York Times RSS/API content; other publishers would need changes to the collection pipeline.
  • The README says the scraper provides about 40–60 words per article, which limits the available source text for summarization.
  • The documented stack includes sentence-t5-base embeddings, persistent ChromaDB collections, Mixtral through Replicate and a fine-tuned BART summarizer.

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

Configure the documented news application

Set the required service API keys in the named project files and start the application using its documented entry point.

Before you start

  • The project repository
  • A New York Times API key
  • A Replicate API key

Steps

  1. Obtain API keys for the New York Times API and Replicate.

  2. Place the New York Times API key in web_scrape_nyt.py.

  3. Place the Replicate API key in categorize_prompt.py.

  4. Run main.py.

Expected outcome

The documented application startup sequence is initiated with the required API keys configured.

Guide limitations

  • The New York Times API scraper is described as returning about 40–60 words per article.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Retrieval-augmented applications

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
Retrieval Augmented Generation For NewsCollect news content from the documented New York Times feeds.CLI, ServerThe documented setup requires New York Times API and Replicate API keys. The public repository is MIT-licensed.
Rag Powered AI Assistant Transforming Data Retrieval And Analysis Across The Web And PdfsRetrieve relevant passages from web and PDF content to answer a question.Web
LangChain in Supabase Edge FunctionsInitialize and start a Supabase project locally.Cloud, Server
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
dhivyeshrk/Retrieval-Augmented-Generation-for-news · Official homepage title · retained in its source language
How we review sourcesSuggest a correction