Geetanjali
RAG-powered ethical guidance from the Bhagavad Gita
Details
- External ID
- 46179344
- Source
- HN
- Company
- —
- Product
- Geetanjali
- Website domain
- geetanjaliapp.com
- Launched
- Dec. 7, 2025
- Cohort
- —
- Upvotes
- 7
- Upvotes percentile
- 0.35877862595419846
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:25 p.m.
- Updated at
- Sept. 7, 2026, 9:25 p.m.
Description
I built a RAG application that retrieves relevant Bhagavad Gita verses for ethical dilemmas and generates structured guidance.The problem: The Gita has 701 verses. Finding applicable wisdom for a specific situation requires either deep familiarity or hours of reading.How it works: 1. User describes their ethical dilemma 2. Query is embedded using sentence-transformers 3. ChromaDB retrieves top-k semantically similar verses 4. LLM generates structured output: 3 options with tradeoffs, implementation steps, verse citationsTech stack: - Backend: FastAPI, PostgreSQL, Redis - Vector DB: ChromaDB with all-MiniLM-L6-v2 embeddings - LLM: Ollama (qwen2.5:3b) primary, Anthropic Claude fallback - Frontend: React + TypeScript + TailwindKey design decisions: - RAG to prevent hallucination — every recommendation cites actual verses - Confidence scoring flags low-quality outputs for review - Structured JSON output for consistent UX - Local LLM option for privacy and zero API costsWhat I learned: - LLM JSON extraction is harder than expected. Built a three-layer fallback (direct parse → markdown block extraction → raw_decode scanning) - Semantic search on religious texts works surprisingly well for ethical queries - Smaller models (3B params) work fine when constrained by good prompts and retrieved contextGitHub: https://github.com/geetanjaliapp/geetanjaliHappy to discuss the RAG architecture or take feedback.
Enrichment
- Theme
- developer tools and programming utilities
- Vertical
- Education
- Function
- Agent / copilot
- Audience
- B2C
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- rag-powered bhagavad gita guidance
- Manually corrected
- False
Could you build this?
Yes A textbook Retrieval-Augmented Generation (RAG) application indexing 701 text verses with vector embeddings and prompting an LLM to provide philosophical advice.
Discussion
4 comments analyzed.
Competitors
Other products that read as similar to this one — 39 launches clear the similarity bar, closest 8 shown.
Attention rank: #27 of 40 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 30 days after the earliest competitor.
- OpenFable · hn · 2026-04-08 · 5 upvotes · similarity 0.41
- Bible as RAG Database · hn · 2026-06-25 · 166 upvotes · similarity 0.41
- Bhagavan · hn · 2026-02-08 · 5 upvotes · similarity 0.38
- Ragnerock, an AI data analysis tool · hn · 2026-04-28 · 13 upvotes · similarity 0.38
- GibRAM an in-memory ephemeral GraphRAG runtime for retrieval · hn · 2026-01-18 · 60 upvotes · similarity 0.37
- I built a RAG engine to search Singaporean laws · hn · 2026-02-07 · 5 upvotes · similarity 0.37
- RAG-based Tutoring Chatbot · ph · 2026-09-17 · 2 upvotes · similarity 0.35
- QuranKu · github · 2026-09-13 · 21 upvotes · similarity 0.35
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a agent / copilot tool for Agriculture yet.