{"id":28140155,"url":"https://github.com/mihirchhiber/topicresearcherbot","last_synced_at":"2026-04-24T20:35:56.431Z","repository":{"id":289704233,"uuid":"972132682","full_name":"mihirchhiber/TopicResearcherBot","owner":"mihirchhiber","description":"AI-powered topic research assistant that automates article discovery, extraction, and summarization. Built with FastAPI, LangChain, Ollama (LLama3), and MongoDB, it scrapes topic-specific content using Google Custom Search, cleans noisy text with an LLM, and generates concise summaries using LLM. Ideal for analysts and researchers seeking fast.","archived":false,"fork":false,"pushed_at":"2025-05-22T15:58:54.000Z","size":96,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-06-15T16:46:13.628Z","etag":null,"topics":["agentic-ai","ai","fastapi","langchain","large-language-models","llama3","llm","mongodb","ollama","python","summarization","webscraping"],"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/mihirchhiber.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,"zenodo":null}},"created_at":"2025-04-24T15:28:34.000Z","updated_at":"2025-05-22T15:58:57.000Z","dependencies_parsed_at":null,"dependency_job_id":"abed1db8-044b-4cd2-92e3-a3321d60b625","html_url":"https://github.com/mihirchhiber/TopicResearcherBot","commit_stats":null,"previous_names":["mihirchhiber/topicresearcherbot"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/mihirchhiber/TopicResearcherBot","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mihirchhiber%2FTopicResearcherBot","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mihirchhiber%2FTopicResearcherBot/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mihirchhiber%2FTopicResearcherBot/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mihirchhiber%2FTopicResearcherBot/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mihirchhiber","download_url":"https://codeload.github.com/mihirchhiber/TopicResearcherBot/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mihirchhiber%2FTopicResearcherBot/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":32240120,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-24T13:21:15.438Z","status":"ssl_error","status_checked_at":"2026-04-24T13:21:15.005Z","response_time":64,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["agentic-ai","ai","fastapi","langchain","large-language-models","llama3","llm","mongodb","ollama","python","summarization","webscraping"],"created_at":"2025-05-14T18:10:50.016Z","updated_at":"2026-04-24T20:35:56.415Z","avatar_url":"https://github.com/mihirchhiber.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Topic Researcher Bot\n\n**Topic Researcher Bot** is an intelligent assistant designed to streamline the process of researching and analyzing online content. It uses LLMs (via LangChain and Ollama) to automate topic-based article discovery, content cleaning, and summarization. This tool is ideal for researchers, analysts, and content teams who want fast, structured insights from recent web articles.\n\n---\n\n## Features\n\n- **Automated Web Search:** Uses Google Custom Search API to find recent articles related to specific topics and sites.\n- **Article Scraping:** Extracts content from article pages using BeautifulSoup and custom rules to avoid noisy or irrelevant data.\n- **LLM-based Cleaning:** Leverages LLMs to isolate and retain only the core article body, removing ads, UI elements, and boilerplate.\n- **Summarization:** Uses a second LLM pass to generate concise summaries of the cleaned content.\n- **Structured Storage:** Articles are stored in a MongoDB database for easy retrieval, filtering, and deletion.\n- **Batch Article Retrieval:** Supports multi-week historical searches and batch retrieval per topic-site pair.\n- **Backend:** Developed using FastAPI\n\n---\n\n## Components\n\n### `article.py`\nDefines the `Article` class with fields like:\n- `id`\n- `topics`\n- `sites`\n- `title`\n- `url`\n- `source`\n- `content`\n- `clean_content`\n- `summary`\n\n### `database.py`\nHandles MongoDB operations for:\n- Storing new articles\n- Retrieving and deleting existing ones\n- Removing duplicates based on title and content hash\n\n### `llmarticles.py`\nCore script that:\n- Searches and scrapes articles via Google CSE\n- Cleans noisy text using LLM prompts\n- Summarizes content with LangChain + Ollama\n- Manages LLM memory and prompts for efficiency\n\n---\n\n## Usage\n\n1. **Define Topics \u0026 Sites**  \n   Configure your topics and target news sites.\n\n2. **Run Retrieval**  \n   Use `get_recent_articles(topics, sites)` to perform the search and scraping.\n\n3. **Clean \u0026 Summarize**  \n   Each article goes through `clean_article_text()` and `summarize_article_text()` functions for post-processing.\n\n4. **View/Manage Data**  \n   Use database functions to filter or delete articles as needed.\n\n---\n\n## Tech Stack\n\n- FastAPI\n- LangChain\n- Ollama or Groq AI (LLM backend)\n- MongoDB\n- Google Custom Search API\n- BeautifulSoup\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmihirchhiber%2Ftopicresearcherbot","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmihirchhiber%2Ftopicresearcherbot","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmihirchhiber%2Ftopicresearcherbot/lists"}