{"id":30587378,"url":"https://github.com/koldim2001/rag_llm","last_synced_at":"2026-03-05T01:33:40.510Z","repository":{"id":309575300,"uuid":"918153062","full_name":"Koldim2001/RAG_LLM","owner":"Koldim2001","description":"Чат-бот с LLL + RAG","archived":false,"fork":false,"pushed_at":"2025-08-12T17:51:34.000Z","size":334,"stargazers_count":7,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-29T14:08:19.746Z","etag":null,"topics":["chatbot","docker-compose","llm","llm-inference","milvus","multimodal","qwen2-5","reranking","retrieval-augmented-generation","streamlit","text-embedding"],"latest_commit_sha":null,"homepage":"https://github.com/Koldim2001/RAG_LLM/tree/GPT_VQA_Example","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/Koldim2001.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":"2025-01-17T10:57:44.000Z","updated_at":"2025-08-27T11:54:03.000Z","dependencies_parsed_at":"2025-08-12T17:33:17.679Z","dependency_job_id":"0e963c18-ebe7-4c99-b576-faec351652f4","html_url":"https://github.com/Koldim2001/RAG_LLM","commit_stats":null,"previous_names":["koldim2001/rag_llm"],"tags_count":1,"template":false,"template_full_name":null,"purl":"pkg:github/Koldim2001/RAG_LLM","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FRAG_LLM","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FRAG_LLM/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FRAG_LLM/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FRAG_LLM/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Koldim2001","download_url":"https://codeload.github.com/Koldim2001/RAG_LLM/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Koldim2001%2FRAG_LLM/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30104503,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-05T01:06:53.091Z","status":"ssl_error","status_checked_at":"2026-03-05T01:02:35.679Z","response_time":59,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["chatbot","docker-compose","llm","llm-inference","milvus","multimodal","qwen2-5","reranking","retrieval-augmented-generation","streamlit","text-embedding"],"created_at":"2025-08-29T12:09:35.601Z","updated_at":"2026-03-05T01:33:35.493Z","avatar_url":"https://github.com/Koldim2001.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG (Retrieval Augmented Generation) with LLM\n\nСделано приложение, способное осуществлять QA при учитывании контента из любых предоставляемых сайтов. Надо передать список ссылок и далее можно задавать вопросы по данному материалу.\n\n---\n\n### Запуск сервисов:\n```\ndocker compose up -d --build\n```\n![Внешний вид сайта](https://github.com/user-attachments/assets/8d8da6d9-8c11-4dd3-b611-be1675e4ea74)\nСайт по работе с LLM (чат-бот с рагом) станет доступен после запуска компоуза по этому адресу - http://localhost:8501/\n\nКод для работы с раг из python - *rag_example.ipynb*\n\nТуториал по проекту - [видео](https://rutube.ru/video/private/236899f9912c7ebaabd3f4142c672684/?p=00pHeMu2UAZse16c78_wDA)\n\n---\nМодели, что использованы в проекте (поднимаются локально):\n```\nLLM: Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4\nEmbedder : intfloat/multilingual-e5-large-instruct\nReranker : BAAI/bge-reranker-v2-m3\n```\n\nКак предустановить модель Qwen чтобы вольюм ее увидел и без инета запускал:\n```\ncd models/nlp/llm\ngit clone https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4\n```\nPS: если заменить `command: --model /models/Qwen2.5-7B-Instruct-GPTQ-Int4` на `--model Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4` то модель сама скачается в кэш и не надо будет ее через git скачивать с хагингфеса (но тогда при каждом перезапуске будет качать ее)\n\n---\n\nВ ветке [**GPT_VQA_Example**](https://github.com/Koldim2001/RAG_LLM/tree/GPT_VQA_Example) можно найти примеры инференса готовых моделей в python по api. В том числе там пример с Visual LLM (VQA).\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkoldim2001%2Frag_llm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkoldim2001%2Frag_llm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkoldim2001%2Frag_llm/lists"}