# leptonai/search_with_lepton

Building a quick conversation-based search demo with Lepton AI.

Repository: https://github.com/leptonai/search_with_lepton
Canonical: https://ross.abutalabs.com/products/search_with_lepton
Homepage: https://search.lepton.run
Language: TypeScript
License: Apache-2.0
License Family: permissive
Topics: ai, ai-applications, leptonai, llm
Archived: true
Last push: 2025-12-02T03:48:24+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 55, release rhythm 35, longevity 68
- inputs: {"age_days": 953, "days_push": 274, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 8070, forks 992 (observed 2026-08-28T04:10:12.476686+00:00)

## What it is
A demo application for building a conversational AI search engine (Perplexity-style) in under 500 lines of code, combining LLMs with search engine APIs like Bing and Google. It includes a customizable web UI, shareable cached results, and one-click deployment to Lepton AI.

## Use cases
- build a conversational AI search engine
- create a Perplexity-like search demo
- combine LLM answers with web search results
- deploy a self-hosted AI search app
- learn to build RAG search applications
- add shareable cached search results to an LLM app

## When to choose
- you want a minimal, readable codebase to learn conversational search
- you already have a Lepton AI workspace or Bing/Google search API keys
- you need a quick demo rather than a production search product

## When to avoid
- you need a production-grade, scalable search engine
- you want to avoid dependency on Lepton AI's platform or paid search APIs
- you need deep customization of retrieval or ranking pipelines

## Facets
- artifact type: application
- maturity: active
- function: search-engine, rag, chatbot, llm-inference, web-framework, caching
- domain: artificial-intelligence, large-language-models, web-development
- platform: python, self-hosted, cross-platform
- tags: conversational-search, perplexity-clone, lepton-ai, demo-app, typescript-frontend, search, retrieval-augmented-generation, nodejs, web-server

## Member repositories
- leptonai/search_with_lepton (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:12.476686+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:31:21.709503+00:00, confidence not recorded.
  - readme: https://github.com/leptonai/search_with_lepton (fetched 2026-08-28T04:10:12.476686+00:00, sha acfdee72e1b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.