{"id":26991581,"url":"https://github.com/alejandrosoares/webchat","last_synced_at":"2026-05-07T08:37:06.191Z","repository":{"id":285956317,"uuid":"959859443","full_name":"alejandrosoares/WebChat","owner":"alejandrosoares","description":"A chatbot that answers questions about website content. Built using Python and LangChain.","archived":false,"fork":false,"pushed_at":"2025-04-03T16:21:17.000Z","size":92,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-09T16:20:44.024Z","etag":null,"topics":["langchain","llm","python","streamlit"],"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/alejandrosoares.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":"2025-04-03T13:20:26.000Z","updated_at":"2025-04-04T09:04:19.000Z","dependencies_parsed_at":"2025-04-03T15:27:40.915Z","dependency_job_id":"2a412cd4-30ed-42dc-a656-69c47be0c1ac","html_url":"https://github.com/alejandrosoares/WebChat","commit_stats":null,"previous_names":["alejandrosoares/webchat"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alejandrosoares%2FWebChat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alejandrosoares%2FWebChat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alejandrosoares%2FWebChat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alejandrosoares%2FWebChat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alejandrosoares","download_url":"https://codeload.github.com/alejandrosoares/WebChat/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248065287,"owners_count":21041872,"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":["langchain","llm","python","streamlit"],"created_at":"2025-04-03T22:16:13.817Z","updated_at":"2026-05-07T08:37:06.133Z","avatar_url":"https://github.com/alejandrosoares.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# WebChat\n\nWebChat is a chat bot that extracts and cleans the content of a website, allowing you to interact with it through a conversational interface. \n\n\n## Features\n\n- **Ensemble retriever**: combines keyword and semantic search to retrieve the source documents.\n- **Maximum Marginal Relevance**: re-ranks source documents maximizing the diversity and reducing redundancy.\n- **Reorder**: places the most relevant documents earlier in the context to avoid the lost-in-the-middle problem.\n\n\n## Installation\n\n1. Set the following environment variables in an .env file in project directory:\n```\nOPENAI_API_KEY\nWEBSITE_NAME\nWEBSITE_URL\nWEBSITE_DESCRIPTION\n```\n\n2. Create a virtual environment and install dependencies:\n```\npip install -r requirements.txt\n```\n\n3. Ingest the website content:\n```\npython src/ingest\n```\n\n4. Run the streamlit web app:\n```\nstreamlit run src/app.py\n```\n\n\n## Screenshot and demo video\n\n![Chat Screenshot](./assets/web_chat_screenshot.png)\n\n[![Demo Video](https://drive.google.com/file/d/19oFXdhismVUNWLNoVhvjSX23qW1PxtgM/view?usp=sharing)](https://drive.google.com/file/d/19oFXdhismVUNWLNoVhvjSX23qW1PxtgM/view?usp=sharing)\n\n\n## References\n\n1. **LangChain Documentation**:\n   [https://docs.langchain.com/](https://docs.langchain.com/)\n\n2. **Streamlit Documentation**:\n   [https://docs.streamlit.io/](https://docs.streamlit.io/)\n\n3. **Platzi LangChain Course for Document Management and Retrieval**:\n[https://platzi.com/cursos/langchain-documents/](https://platzi.com/cursos/langchain-documents/)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falejandrosoares%2Fwebchat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falejandrosoares%2Fwebchat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falejandrosoares%2Fwebchat/lists"}