{"id":17736613,"url":"https://github.com/shivendrra/Seeker","last_synced_at":"2025-12-30T20:15:11.105Z","repository":{"id":214982194,"uuid":"737723929","full_name":"shivendrra/YouTubeVideoScripter","owner":"shivendrra","description":"This project will help to write new scripts for YouTube videos from scratch using fine-tuned Llama-7B","archived":false,"fork":false,"pushed_at":"2024-01-27T19:07:08.000Z","size":37580,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2024-10-18T22:13:00.408Z","etag":null,"topics":["ai","artificial-intelligence","finetuning","google-custom-search-api","google-custom-search-engine","llama2","llm","numpy","pandas","python","pytorch","react-native","reactjs","transformers","youtube-api"],"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/shivendrra.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":"2024-01-01T08:38:18.000Z","updated_at":"2024-03-10T07:22:15.000Z","dependencies_parsed_at":"2024-01-17T19:15:07.093Z","dependency_job_id":"80a02af1-9e8c-4a7c-afd3-1ca9f3bd3735","html_url":"https://github.com/shivendrra/YouTubeVideoScripter","commit_stats":{"total_commits":32,"total_committers":2,"mean_commits":16.0,"dds":0.0625,"last_synced_commit":"a71e6fd1fd18a2c74d42ee00a87f3842518a6e0c"},"previous_names":["shivendrra/youtubevideoscripter"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivendrra%2FYouTubeVideoScripter","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivendrra%2FYouTubeVideoScripter/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivendrra%2FYouTubeVideoScripter/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/shivendrra%2FYouTubeVideoScripter/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/shivendrra","download_url":"https://codeload.github.com/shivendrra/YouTubeVideoScripter/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246523847,"owners_count":20791444,"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":["ai","artificial-intelligence","finetuning","google-custom-search-api","google-custom-search-engine","llama2","llm","numpy","pandas","python","pytorch","react-native","reactjs","transformers","youtube-api"],"created_at":"2024-10-26T00:23:44.604Z","updated_at":"2025-12-30T20:15:11.101Z","avatar_url":"https://github.com/shivendrra.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\n# Seeker: AI Agent-based Research Application\n\n\u003ch3 align=\"center\"\u003eAn autonomous AI agent to assist journalists, lawyers, and academic researchers with complex research tasks, providing structured answers with clear citations and provenance.\u003c/h3\u003e\n\n## Introduction\n\nIn professions like journalism, law, and academic research, the ability to quickly gather, synthesize, and cite information from vast sources is critical. Traditional search methods are often time-consuming and linear. **Seeker** is an advanced research assistant powered by the Google Gemini API, designed to automate and enhance this process.\n\nSeeker acts as an autonomous agent that interprets complex user queries, plans a multi-step research workflow, utilizes various tools (like document and web search), and synthesizes the findings into a structured, well-cited response. It's built to be a reliable partner for professionals who demand accuracy, transparency, and efficiency in their research.\n\n## Key Features\n\n-   **Autonomous AI Agent**: Interprets natural language requests and plans a multi-step research strategy.\n-   **Cited \u0026 Verifiable Answers**: Provides answers with clear citations, including source, page/paragraph, and date, to ensure provenance and trust.\n-   **Transparent Process**: Features a **Trace View** that shows the AI's exact plan and execution steps, allowing for full auditability of the research process.\n-   **Long-Term Memory**: Remembers context across sessions to personalize the experience and build upon previous research.\n-   **Multi-Tool Capability**: Designed to use a suite of tools, including internal document retrieval and external web searches, to gather comprehensive information.\n-   **Secure \u0026 Private**: Built on Firebase for secure user authentication and data storage.\n-   **Modern UI/UX**: A clean, responsive, and intuitive interface with both **Light and Dark modes**, designed for focus and productivity.\n-   **Session Management**: Organizes research into distinct, titled sessions that can be revisited or deleted.\n\n## Tech Stack\n\n-   **Frontend**: [React](https://reactjs.org/), [TypeScript](https://www.typescriptlang.org/), [Tailwind CSS](https://tailwindcss.com/)\n-   **Backend \u0026 Database**: [Firebase](https://firebase.google.com/) (Authentication, Firestore for data storage)\n-   **AI Model**: [Google Gemini API](https://ai.google.dev/) (using `gemini-2.5-pro`)\n-   **Development/Build**: [Vite](https://vitejs.dev/)\n\n## Project Structure\n\nThe project is organized into a standard React application structure:\n\n```\n/\n├── app/\n│   ├── components/      # Reusable React components\n│   ├── services/        # Modules for external services (Firebase, Gemini)\n│   ├── hooks/           # Custom React hooks (e.g., useAuth)\n│   ├── utils/           # Helper functions (e.g., response parsing)\n│   ├── App.tsx          # Main application component\n│   ├── index.tsx        # Entry point of the React app\n│   ├── types.ts         # TypeScript type definitions\n│   └── constants.ts     # Core constants, including the main system prompt\n├── .gitignore\n└── package.json\n```\n\nvibe coded using GoogleAI Studio","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivendrra%2FSeeker","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fshivendrra%2FSeeker","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fshivendrra%2FSeeker/lists"}