{"id":19024476,"url":"https://github.com/danielstankw/wordwatchsummary","last_synced_at":"2026-03-10T10:02:26.275Z","repository":{"id":242484164,"uuid":"807448560","full_name":"danielstankw/WordWatchSummary","owner":"danielstankw","description":"Find, scrape , summarize (LLM) and deliver!","archived":false,"fork":false,"pushed_at":"2024-07-06T20:40:25.000Z","size":179,"stargazers_count":2,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-06T01:25:20.158Z","etag":null,"topics":["langchain","llm","ollama","python","scrapper","summarization"],"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/danielstankw.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":"2024-05-29T06:02:18.000Z","updated_at":"2024-10-01T22:10:32.000Z","dependencies_parsed_at":"2024-11-08T20:41:48.657Z","dependency_job_id":null,"html_url":"https://github.com/danielstankw/WordWatchSummary","commit_stats":null,"previous_names":["danielstankw/wordwatchsummary"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/danielstankw/WordWatchSummary","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielstankw%2FWordWatchSummary","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielstankw%2FWordWatchSummary/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielstankw%2FWordWatchSummary/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielstankw%2FWordWatchSummary/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/danielstankw","download_url":"https://codeload.github.com/danielstankw/WordWatchSummary/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/danielstankw%2FWordWatchSummary/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30329697,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T05:25:20.737Z","status":"ssl_error","status_checked_at":"2026-03-10T05:25:17.430Z","response_time":106,"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":["langchain","llm","ollama","python","scrapper","summarization"],"created_at":"2024-11-08T20:36:54.082Z","updated_at":"2026-03-10T10:02:26.234Z","avatar_url":"https://github.com/danielstankw.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# \"WordWatch Summary\"\nThe goal of this Python application is to streamline the process of finding, summarizing, and sharing news articles that mention a specific word of interest. Here’s how it works:\n\n1. **Search and Scrape:** The application searches for the specified word on Google, identifying occurrences in various articles, and collects the corresponding URLs.  \n2. **Summarization:** Using a chosen large language model (LLM), the application generates concise summaries of the scraped articles.  \n3. **Editing:** The summaries are reviewed and edited for clarity and coherence.  \n4. **Email Delivery:** The edited summaries are embedded into an email and sent to the user via SMTP.\n\n\n*An example of email*\n\n\u003cimg src=\"images/smtp.png\" alt=\"alt text\" width=\"1000\"\u003e\n\nThis application is a proof of concept and can be easily expanded.\n\n\n\n\n## Installation\n**a. Ollama (Local LLM)** - for details check [Video](https://www.youtube.com/watch?v=ZoxJcPkjirs\u0026t=549s\u0026ab_channel=MattWilliams)  \n\nTo provide summarization an [Ollama](https://github.com/ollama/ollama) framework was used, together with the `gemma:2b` model.  \n\n```bashrc\ndocker run -d --gpus=all -v \u003cpath_where_volume_is_mounted\u003e:/root/.ollama -p 11434:11434 --name ollama ollama/ollama\n```\n\nTo stop or start a container  \n```bashrc\ndocker stop ollama\ndocker start ollama\n```\n\nTo run the `gemma:2b` model - see the [list of models](https://github.com/ollama/ollama?tab=readme-ov-file#model-library)  \n```basrhc\ndocker exec ollama ollama run gemma:2b\n```\n\n**b. Set up local SMTP (Gmail)**  \n\nLink to the [YouTube video](https://www.youtube.com/watch?v=g_j6ILT-X0k\u0026t=592s\u0026ab_channel=ThePyCoach)  \n\n## How to run?\n\nCreate a virtual environment based on `requirements.txt`.  \nModify the `main.py` and run the script.  \nMake sure to define the env variables in `.env`, see the `.env.example` for the required variables.\n\n```py\n    # Find pages with:\n    # all thses words:\n    search.set_all_words(\"\")\n    # his exact word or phrase:\n    search.set_exact_phrase(\"Johny Bravo\")\n    # any of these words:\n    search.set_any_words(\"\")\n    # none of these words:\n    search.set_none_words(\"\")\n    # numbers ranging from:\n    search.set_number_range(\"\", \"\")\n    # Then narrow the results by:\n    # language\n    search.set_language(\"en\")\n    # region\n    search.set_region(\"\")\n    # last update\n    # d - day, w - week, m - month, y - year, all - anytime\n    search.set_last_update(\"w\")\n    # site or domain\n    search.set_site_or_domain(\"\")\n    # terms appearing\n    search.set_terms_appearing(\"\")\n    # file type\n    search.set_file_type(\"\")\n    # usage rights\n    search.set_usage_rights(\"\")\n```\n\nThe fields are the same as in Google Advanced Search:  \n\n\u003cimg src=\"images/google.png\" alt=\"alt text\" width=\"800\"\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielstankw%2Fwordwatchsummary","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdanielstankw%2Fwordwatchsummary","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdanielstankw%2Fwordwatchsummary/lists"}