{"id":25543858,"url":"https://github.com/mathyscogne/hackathon_kiln","last_synced_at":"2025-04-11T18:10:57.207Z","repository":{"id":275635799,"uuid":"925589961","full_name":"MathysCogne/hackathon_kiln","owner":"MathysCogne","description":"Solution for Hackathon Kiln 2025 | AI-powered assistant that both educates on blockchain concepts and can help advanced users quickly retrieve precise, real-time data using Kiln's API","archived":false,"fork":false,"pushed_at":"2025-02-04T14:39:12.000Z","size":19788,"stargazers_count":6,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-25T14:05:26.113Z","etag":null,"topics":["blockchain","chatbot","ia"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/MathysCogne.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-02-01T08:28:37.000Z","updated_at":"2025-02-17T16:57:47.000Z","dependencies_parsed_at":"2025-02-20T07:38:38.592Z","dependency_job_id":null,"html_url":"https://github.com/MathysCogne/hackathon_kiln","commit_stats":null,"previous_names":["mathyscogne/hackathon_kiln"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MathysCogne%2Fhackathon_kiln","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MathysCogne%2Fhackathon_kiln/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MathysCogne%2Fhackathon_kiln/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/MathysCogne%2Fhackathon_kiln/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/MathysCogne","download_url":"https://codeload.github.com/MathysCogne/hackathon_kiln/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248456365,"owners_count":21106603,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["blockchain","chatbot","ia"],"created_at":"2025-02-20T07:38:37.819Z","updated_at":"2025-04-11T18:10:57.198Z","avatar_url":"https://github.com/MathysCogne.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003c/br\u003e\n\u003c/br\u003e\n\n\u003cstrong\u003eHackathon - Kiln 🐧\u003c/strong\u003e\n\n\u003cp\u003e2nd Place WINNERS of the Kiln Connect category! 🏆\u003c/p\u003e\n\n\u003cp\u003eThis project was developed as a solution for a hackathon organized by Kiln, focusing on innovation and data accessibility in staking and blockchain technology 🏆\u003c/p\u003e\n\n\u003c/br\u003e\n\n\u003cp\u003e\n  \u003ca href=\"https://www.youtube.com/watch?v=MOEbBAgxb3Y\"\u003e\n    \u003cimg src=\"https://img.youtube.com/vi/MOEbBAgxb3Y/maxresdefault.jpg\" alt=\"Demo Video\" width=\"600\"\u003e\n    \u003cbr\u003e\n    \u003cstrong\u003eClick to watch the demo video\u003c/strong\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003c/div\u003e\n\n\n## 🚀 Project Objective\n\nThe goal is to provide an AI-powered assistant that both educates on blockchain concepts and can help advanced users quickly retrieve precise, real-time data using Kiln's API. Acting as a bridge to the blockchain, the AI makes information more accessible, and actionable.\n\n\u003c/br\u003e\n\n# Slide presentation\n\n\u003cimg src=\"asset/cover_1.png\" alt=\"Covers\" width=\"550\" /\u003e\n\u003cimg src=\"asset/cover_2.png\" alt=\"Covers\" width=\"550\" /\u003e\n\u003cimg src=\"asset/cover_3.png\" alt=\"Covers\" width=\"550\" /\u003e\n\u003cimg src=\"asset/cover_4.png\" alt=\"Covers\" width=\"550\" /\u003e\n\u003cimg src=\"asset/cover_5.png\" alt=\"Covers\" width=\"550\" /\u003e\n\n\n\n\u003c/br\u003e\n\n## 🔎 Sentiment analysis\nThe first step is to have the user's prompt go through a simple sentiment analysis using a python script, allowing it to narrow down which data is necessary and from there make the right API call to retrieve it. In a fully fledged version, a more thorough sentiment analysis using modified [Afinn](https://github.com/fnielsen/afinn) and allowing it to understand actionable words to enable it to make actions (such as handling: transactions, withdrawing, staking on behalf of the user).\n\n\u003c/br\u003e\n\n## 📡 Integration with Kiln\n\nThe aim of this project was to demonstrate a functional proof of concept, for this we decided to limit the data received through Kiln's API to what we thought would be necessary for a MVP. \nFor a fully operational version, all Kiln API endpoints should be integrated to maximize the chatbot's capabilities.\n\nThe AI is fed real-time data from Kiln's API to provide accurate responses. Currently supported endpoints:\n\n- `Get_Stakes`: Information on validators and associated wallets\n- `Get_Reward`: Reward details for a given wallet or validator\n- `Get_ETH_Stats`: Global Ethereum network statistics\n- `Get_Kiln_Stats`: Kiln-specific activity data on Ethereum\n- `Get_Transaction_Status`: Status of an Ethereum transaction\n\n\u003c/br\u003e\n\n## 🔮 Future Improvements\n\n- 🛠 **Blockchain Actions**: Integration of Kiln's UI widget for direct user actions\n- 📡 **Extended Kiln API Support**: Add new API endpoints for broader information coverage\n- 🤖 **AI Model Enhancement**: Use a blockchain-trained LLM model locally, to improve response quality, privacy and compliance\n\n\u003c/br\u003e\n\n## 🙏 Acknowledgments\n\nSpecial thanks to Kiln for organizing the hackathon!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmathyscogne%2Fhackathon_kiln","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmathyscogne%2Fhackathon_kiln","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmathyscogne%2Fhackathon_kiln/lists"}