{"data":{"slug":"leptonai-search-with-lepton","name":"search_with_lepton","tagline":"Building a quick conversation-based search demo with Lepton AI.","github_url":"https://github.com/leptonai/search_with_lepton","owner":"leptonai","repo":"search_with_lepton","owner_avatar_url":"https://avatars.githubusercontent.com/u/124112888?v=4","primary_language":"TypeScript","stars":8081,"forks":998,"topics":["ai","ai-applications","leptonai","llm"],"archived":true,"github_pushed_at":"2025-12-02T03:48:24+00:00","maintenance_label":"Archived","url":"https://www.graphcanon.com/tools/leptonai-search-with-lepton","markdown_url":"https://www.graphcanon.com/tools/leptonai-search-with-lepton.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/leptonai-search-with-lepton","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=leptonai-search-with-lepton","description":"Building a quick conversation-based search demo with Lepton AI.","homepage_url":"https://search.lepton.run","license":"Apache-2.0","open_issues":44,"watchers":1,"ai_summary":"A conversational search engine demo built using TypeScript, supporting integration with Lepton AI's LLM and various search engines like Bing and Google, offering customizable UI and shareable cached results.","readme_excerpt":"
\n

Search with Lepton

\nBuild your own conversational search engine using less than 500 lines of code.\n
\n Live Demo \n
\n\n
\n\n\n## Features\n- Built-in support for LLM\n- Built-in support for search engine\n- Customizable pretty UI interface\n- Shareable, cached search results\n\n## Setup Search Engine API\nThere are two default supported search engines: Bing and Google.\n \n### Bing Search\nTo use the Bing Web Search API, please visit [this link](https://www.microsoft.com/en-us/bing/apis/bing-web-search-api) to obtain your Bing subscription key.\n\n### Google Search\nYou have three options for Google Search: you can use the [SearchApi Google Search API](https://www.searchapi.io/) from SearchApi, [Serper Google Search API](https://serper.dev) from Serper, or opt for the [Programmable Search Engine](https://developers.google.com/custom-search) provided by Google.\n\n## Setup LLM and KV\n\n> [!NOTE]\n> We recommend using the built-in llm and kv functions with Lepton. \n> Running the following commands to set up them automatically.\n\n```shell\npip install -U leptonai openai && lep login\n```\n\n## Obtain Your Lepton AI Workspace Token\nYou can copy your workspace toke from the Lepton AI Dashboard → Settings → Tokens.\n\n\n## Build\n\n1. Set Bing subscription key\n```shell\nexport BING_SEARCH_V7_SUBSCRIPTION_KEY=YOUR_BING_SUBSCRIPTION_KEY\n```\n2. Set Lepton AI workspace token\n```shell\nexport LEPTON_WORKSPACE_TOKEN=YOUR_LEPTON_WORKSPACE_TOKEN\n```\n3. Build web\n```shell\ncd web && npm install && npm run build\n```\n4. Run server\n```shell\nBACKEND=BING python search_with_lepton.py\n```\n\nFor Google Search using SearchApi:\n```shell\nexport SEARCHAPI_API_KEY=YOUR_SEARCHAPI_API_KEY\nBACKEND=SEARCHAPI python search_with_lepton.py\n```\n\nFor Google Search using Serper:\n```shell\nexport SERPER_SEARCH_API_KEY=YOUR_SERPER_API_KEY\nBACKEND=SERPER python search_with_lepton.py\n```\n\nFor Google Search using Programmable Search Engine:\n```shell\nexport GOOGLE_SEARCH_API_KEY=YOUR_GOOGLE_SEARCH_API_KEY\nexport GOOGLE_SEARCH_CX=YOUR_GOOGLE_SEARCH_ENGINE_ID\nBACKEND=GOOGLE python search_with_lepton.py\n```\n\n\n\n## Deploy\n\nYou can deploy this to Lepton AI with one click:\n\n\n\nYou can also deploy your own version via\n\n```shell\nlep photon run -n search-with-lepton-modified -m search_with_lepton.py --env BACKEND=BING --env BING_SEARCH_V7_SUBSCRIPTION_KEY=YOUR_BING_SUBSCRIPTION_KEY\n```\n\nLearn more about `lep photon` [here](https://www.lepton.ai/docs/references/lep_photon).","github_created_at":"2024-01-23T05:51:43+00:00","created_at":"2026-07-11T10:39:37.211922+00:00","updated_at":"2026-08-07T18:01:38.694558+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"ai-applications","name":"ai-applications"},{"slug":"bing-api","name":"bing-api"},{"slug":"conversational-search","name":"conversational-search"},{"slug":"google-search","name":"google-search"},{"slug":"leptonai","name":"leptonai"}],"trust":{"provenance":{"is_fork":false,"github_id":747030811,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-07T18:01:37.612Z","maintenance":{"label":"Archived","score":8,"methodology":"github_public_v1","releases_90d":0,"days_since_push":248,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T10:39:38.645Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-07T18:01:38.101Z"},"languages":{"value":["typescript"],"source":"github.language","observed_at":"2026-08-07T18:01:38.101Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-07T18:01:38.101Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["- When you need a quick prototype of a conversation-driven search engine leveraging Lepton AI.","- For developers preferring **TypeScript** who want to integrate with multiple search engines via API keys in a conversational interface.","- Ideal for scenarios requiring shareable cached results and customizable UI, suitable for both personal projects and small teams."],"when_not_to_use":["- Avoid if your project strictly requires only native integration with other LLMs besides Lepton AI as this tool is tightly coupled with it.","- Not recommended if you aim to build a large-scale production system as the demo focuses on rapid development rather than high throughput or enterprise-level robustness."],"source":"enrich:decision_facts","observed_at":"2026-07-12T11:19:54.811Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Adopt for","value":"**search_with_lepton** is a TypeScript-based conversational search demo integrating Lepton AI's LLM and offering flexible backend options like Bing, Google SearchAPI, Serper, or Programmable Search Engine."},{"label":"License detail","value":"Apache-2.0 license, providing freedom to use, modify and distribute the software while requiring preservation of copyright notices."}]}}