hoangsonww/AI-Gov-Content-Curator

Multi-Language Summarization Support

Open

#41 opened on Sep 20, 2025

View on GitHub
 (1 comment) (1 reaction) (2 assignees)TypeScript (18 forks)auto 404
backendci/cdcrawlerdeploymentdocumentationenhancementfrontendgood first issuehelp wantednewsletterquestion

Repository metrics

Stars
 (29 stars)
PR merge metrics
 (PR metrics pending)

Description

Summary Enable AI-powered multi-language summarization and translation so that articles fetched by the crawler can be summarized in both their original language and English. This will make the tool more inclusive for international audiences and government staff dealing with multilingual sources.

🔍 Problem

Currently, the summarization pipeline only generates summaries in English. However, many government-related sources (EU, UN, ASEAN, etc.) publish content in multiple languages. Limiting summaries to English:

  • Reduces accessibility for non-English speakers.
  • Prevents analysts from comparing original tone vs AI-translated version.
  • Leaves out potentially important sources in non-English contexts.

💡 Proposed Solution

  • Extend summarization to support multiple languages:

    • Step 1: Detect article language during crawling (using libraries like franc, langdetect, or Google Translate API).
    • Step 2: Generate summaries in the original language.
    • Step 3: Provide optional AI translation to English (and vice versa).

  • Store both versions (summary_original and summary_translated) in MongoDB.

  • Frontend toggle: allow users to switch between original-language and translated summaries.

📐 Technical Notes

  • Crawler:

    • Add language detection before storing raw article content.

  • Backend (Express/Next.js API):

    • Update schema with language, summary_original, summary_translated.
    • Add ?lang=en query param to /api/articles for filtering summaries.

  • Frontend (Next.js):

    • Add toggle/switch on article detail page for “View Original / View English”.
    • Display a flag/language indicator on each article card.

  • AI Provider:

    • Use Google Generative AI (Gemini) multilingual summarization or fallback to Translate API if needed.

✅ Benefits

  • Expands reach to multilingual government staff.
  • Increases accuracy by preserving original summaries.
  • Provides a better comparative analysis experience.
  • Makes SynthoraAI a global-ready solution.

📊 Priority

High – critical for adoption in international/multilingual environments.

Contributor guide

Research direction
Implement language detection in the crawler using a library like franc or langdetect. Extend the MongoDB schema to store language, summary original, and summary translated. Update the backend API to accept a language query parameter and generate summaries using Gemini's multilingual capabilities. Add a frontend toggle to switch between original and translated summaries.
Tech stack
typescriptnodejsnextjsexpressmongodb
Domain
aiapibackendfrontend
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
Half day
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
MongoDBNode.jsNext.jsExpress
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
70