{"id":18899527,"url":"https://github.com/seeed-projects/rag_based_on_jetson","last_synced_at":"2025-07-20T14:32:43.060Z","repository":{"id":234359250,"uuid":"788736464","full_name":"Seeed-Projects/RAG_based_on_Jetson","owner":"Seeed-Projects","description":"This project has implemented the RAG function on Jetson and supports TXT and PDF document formats. It uses MLC for 4-bit quantization of the Llama2-7b model, utilizes ChromaDB as the vector database, and connects these features with Llama_Index. I hope you like this project.","archived":false,"fork":false,"pushed_at":"2024-05-16T08:36:02.000Z","size":13361,"stargazers_count":9,"open_issues_count":1,"forks_count":1,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-04-05T10:41:27.084Z","etag":null,"topics":["chromadb","jetson","llama-index","llama2-7b","mlc"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Seeed-Projects.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2024-04-19T01:33:17.000Z","updated_at":"2025-03-19T17:47:47.000Z","dependencies_parsed_at":"2024-11-08T08:47:25.583Z","dependency_job_id":"b5de7369-1dc2-4d29-9c27-fbd9f7515eea","html_url":"https://github.com/Seeed-Projects/RAG_based_on_Jetson","commit_stats":null,"previous_names":["seeed-projects/rag_based_on_jetson"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Seeed-Projects/RAG_based_on_Jetson","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Seeed-Projects%2FRAG_based_on_Jetson","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Seeed-Projects%2FRAG_based_on_Jetson/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Seeed-Projects%2FRAG_based_on_Jetson/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Seeed-Projects%2FRAG_based_on_Jetson/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Seeed-Projects","download_url":"https://codeload.github.com/Seeed-Projects/RAG_based_on_Jetson/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Seeed-Projects%2FRAG_based_on_Jetson/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266140096,"owners_count":23882607,"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":["chromadb","jetson","llama-index","llama2-7b","mlc"],"created_at":"2024-11-08T08:46:46.335Z","updated_at":"2025-07-20T14:32:43.009Z","avatar_url":"https://github.com/Seeed-Projects.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG_based_on_Jetson\nThis project has implemented the RAG function on Jetson and supports TXT and PDF document formats. It uses MLC for 4-bit quantization of the Llama2-7b model, utilizes ChromaDB as the vector database, and connects these features with Llama_Index. I hope you like this project.\n\n# Hardware Prepare\nHere I use reComputer J4012 powered by NVIDIA [Jetson Orin NX 16GB](https://www.seeedstudio.com/reComputer-J4012-p-5586.html), this project will use RAM at a peak of 11.7GB.\n\n# Run this project\n## Step 1: prepare environment\n\n```\n# install jetson-container and its requirements\n\ngit clone --depth=1 https://github.com/dusty-nv/jetson-containers\ncd jetson-containers \npip install -r requirements.txt \ncd data\n```\n\n```\n# Install RAG project and llama2-7b model after 4bit quantification\n\ngit clone https://github.com/Seeed-Projects/RAG_based_on_Jetson.git \nsudo apt-get install git-lfs\ncd RAG_based_on_Jetson\ngit clone https://huggingface.co/JiahaoLi/llama2-7b-MLC-q4f16-jetson-containers \ncd ..\n```\n\n## Step 2: run and enter the docker \n\n```cd .. \u0026\u0026 ./run.sh $(./autotag mlc) ```\n\n![](./source/enter_docker.png)\n```\n# Those command will run in this docker \ncd data/RAG_based_on_Jetson \u0026\u0026 pip install -r requirements.txt\npip install chromadb==0.3.29\n```\n\n\u003eNote: If you get this error please ignore it.\n\n![](./source/error.png)\n\n## step 3: run the project\n\n```\n# Command run in docker \npython3 RAG.py\n```\n![](./source/RAG.png)\n\n# Result \nBelow is the live demo, and the blue text is the context search from ChromaDB will be the context of the question\n\n[![Alt text](https://img.youtube.com/vi/v1SDRko5cNM/0.jpg)](https://youtu.be/v1SDRko5cNM)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseeed-projects%2Frag_based_on_jetson","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fseeed-projects%2Frag_based_on_jetson","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseeed-projects%2Frag_based_on_jetson/lists"}