{"id":21214895,"url":"https://github.com/komangandika/rag-langchain-mistral","last_synced_at":"2026-05-11T07:42:34.843Z","repository":{"id":247322628,"uuid":"824005470","full_name":"KomangAndika/RAG-LangChain-Mistral","owner":"KomangAndika","description":"Using RAG(Retrieval-Augmented Generation) to retrieve informationn from 10 LLM research paper, the LLM I am using Mistral 7b with LangChain Framework","archived":false,"fork":false,"pushed_at":"2024-08-20T09:18:34.000Z","size":58,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-21T16:26:25.069Z","etag":null,"topics":["faiss","langchain","llm","mistral","mistralai","rag"],"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/KomangAndika.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":"2024-07-04T07:17:44.000Z","updated_at":"2024-09-19T07:56:43.000Z","dependencies_parsed_at":"2024-07-08T04:43:36.019Z","dependency_job_id":"0a1d1c88-df1f-45ec-a615-1f0b93e39298","html_url":"https://github.com/KomangAndika/RAG-LangChain-Mistral","commit_stats":null,"previous_names":["komangandika/rag-langchain-mistral"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KomangAndika%2FRAG-LangChain-Mistral","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KomangAndika%2FRAG-LangChain-Mistral/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KomangAndika%2FRAG-LangChain-Mistral/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KomangAndika%2FRAG-LangChain-Mistral/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KomangAndika","download_url":"https://codeload.github.com/KomangAndika/RAG-LangChain-Mistral/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243664031,"owners_count":20327406,"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":["faiss","langchain","llm","mistral","mistralai","rag"],"created_at":"2024-11-20T21:32:04.849Z","updated_at":"2026-05-11T07:42:29.824Z","avatar_url":"https://github.com/KomangAndika.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG-LangChain-Mistral\nUsing RAG(Retrieval-Augmented Generation) to retrieve informationn from 10 LLM research paper, the LLM I am using Mistral 7b with LangChain Framework. The Mistral model I am using is quntized with NF4 Quantization useful to reduce the model size and usage of VRAM but still kinda keeping the accuracy\n## RAG(Retrieval-Augmented Generation) with LangChain\nRag typically has two main components:\n1. Indexing, basically pipeline to ingest data (Usually done Offline).\n2. Retrieival + Generation, this is the actual part of the RAG, receive user query and retrieve relevant data from index and passing the model. \u003cbr\u003e\n### Indexing\n- Loading Document, using document loaders, can be from Google Drive, Notion, Slack, but in this case I am using kaggle database(or basically local kaggle notebook).\n- Split, using text splitter to break documents into smaller chunks, useful for indexing and feeding the model.\n- Store, place to store and index the splits (VectorDB and Embedding model are here), the VectorDB I am using is FAISS and sentence-transformer for embedding.\n\n### Retrieval + Generation\n- Retrieve, given the user input, retrieve relevant splits from the VectorDB(FAISS).\n- Generate, using chatmodel/LLM(in this case Mistral 7b) to produce respose based on user prompt and retrieved data\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkomangandika%2Frag-langchain-mistral","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkomangandika%2Frag-langchain-mistral","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkomangandika%2Frag-langchain-mistral/lists"}