{"id":22313292,"url":"https://github.com/chibuikeeugene/llm_app_question_and_answer","last_synced_at":"2025-03-26T02:38:03.673Z","repository":{"id":253977776,"uuid":"823538734","full_name":"chibuikeeugene/llm_app_question_and_answer","owner":"chibuikeeugene","description":"A large language model that takes any website as an input together with a user query prompt and returns a suitable human response. This program uses a llama3 model locally hosted to return human readable and understandable results.","archived":false,"fork":false,"pushed_at":"2024-09-12T10:25:56.000Z","size":1491,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-30T23:45:39.311Z","etag":null,"topics":["generative-ai","langchain-python","llm"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/chibuikeeugene.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":"2024-07-03T08:15:14.000Z","updated_at":"2024-09-12T10:25:59.000Z","dependencies_parsed_at":"2024-09-12T20:21:04.558Z","dependency_job_id":"6e1f5dd8-5628-4a42-b780-057322988a02","html_url":"https://github.com/chibuikeeugene/llm_app_question_and_answer","commit_stats":null,"previous_names":["chibuikeeugene/llm_app_question_and_answer"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chibuikeeugene%2Fllm_app_question_and_answer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chibuikeeugene%2Fllm_app_question_and_answer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chibuikeeugene%2Fllm_app_question_and_answer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/chibuikeeugene%2Fllm_app_question_and_answer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/chibuikeeugene","download_url":"https://codeload.github.com/chibuikeeugene/llm_app_question_and_answer/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245577918,"owners_count":20638409,"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":["generative-ai","langchain-python","llm"],"created_at":"2024-12-03T22:06:53.930Z","updated_at":"2025-03-26T02:38:03.642Z","avatar_url":"https://github.com/chibuikeeugene.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM Q\u0026A with any website  \n\nA large language model that takes any website as an input together with a user query prompt and returns a suitable human response. This program uses a **llama3 model locally hosted** to return human readable and understandable results.  \n\n## Dependencies and packages  \n\n1. python = \"^3.10\"\n2. streamlit = \"^1.36.0\"\n3. langchain = \"^0.2.6\"\n4. llama 3\n5. huggingface-hub = \"^0.23.4\"\n6. python-dotenv = \"^1.0.1\"\n7. langchain-community = \"^0.2.6\"\n8. langchain-ollama = \"^0.1.0\"\n9. beautifulsoup4 = \"^4.12.3\"\n10. faiss-cpu = \"^1.8.0.post1\"\n11. sphinx = \"^8.0.2\"\n12. loguru = \"^0.7.2\"\n13. fire = \"^0.6.0\"\n\n## To run the application\n\n1. install llama3 and run server locally - using the command -  ollama run llama3\n2. Install the package dependencies using poetry install command. Ensure you do this in a virual environment.\n3. navigate to the q_and_a sub-folder and run the command -  streamlit run main.py\n4. Good luck !\n\n## Snapshots\n\n### Q\u0026A architecture\n\n![Q\u0026A app schema](\u003cLangSmith Question \u0026 Answer.drawio.png\u003e)\n\n### Live view of our application in workmode with Streamlit as the frontend\n\n![Streamlit app 1](\u003cScreenshot 2024-08-23 at 11.49.52 pm.png\u003e)\n\n![Streamlit app 2](\u003cScreenshot 2024-08-23 at 11.49.59 pm.png\u003e)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchibuikeeugene%2Fllm_app_question_and_answer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fchibuikeeugene%2Fllm_app_question_and_answer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fchibuikeeugene%2Fllm_app_question_and_answer/lists"}