{"id":21601399,"url":"https://github.com/dominodatalab/rag","last_synced_at":"2025-03-18T13:18:55.137Z","repository":{"id":207439919,"uuid":"714068603","full_name":"dominodatalab/RAG","owner":"dominodatalab","description":null,"archived":false,"fork":false,"pushed_at":"2023-11-30T20:00:22.000Z","size":2435,"stargazers_count":1,"open_issues_count":0,"forks_count":2,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-01-24T18:27:30.781Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/dominodatalab.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}},"created_at":"2023-11-03T21:07:44.000Z","updated_at":"2023-11-16T02:53:46.000Z","dependencies_parsed_at":"2023-11-30T21:22:26.484Z","dependency_job_id":"68784bb1-47ce-44fa-b10f-aab9ef3e3a19","html_url":"https://github.com/dominodatalab/RAG","commit_stats":null,"previous_names":["dominodatalab/rag"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dominodatalab%2FRAG","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dominodatalab%2FRAG/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dominodatalab%2FRAG/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dominodatalab%2FRAG/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dominodatalab","download_url":"https://codeload.github.com/dominodatalab/RAG/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244227577,"owners_count":20419262,"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":[],"created_at":"2024-11-24T19:09:24.272Z","updated_at":"2025-03-18T13:18:55.103Z","avatar_url":"https://github.com/dominodatalab.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG\n\n## Files\n*  RAG.ipynb : This notebook contains all the logic to load embeddings, setup the QA chain for RAG and allows users to ask queries once all the hyperparameters have been finalized.\n  \n*  MLflow_eval.ipynb : This notebook contains code to evaluate a RAG pipeline for faithfulness and relevance using Mlflow. The metrics are also stored and can be visualized in the Experiments tab in Domino\n  \n*  RAGAS_eval.ipynb : This notebook uses the RAGAS package to evaluate a RAG pipeline. This is another example of how to evaluate a RAG pipeline, RAGAS offers a couple of more metrics than MLFlow\n  \n*  example_prompts.txt : Has a few examples of questions that can be presented as prompts to the QA chain\n  \n*  app.sh : Script required to setup and use Streamlit in Domino\n  \n*  streamlit_app.py : This file contains code that sets up the UI and workflow for a Streamlit chatbot. The app needs an Anthropic and Qdrant key to set in the sidebar to run\n\nOn `se-demo` this was run on a `Medium` hardware tier\n\n## Environment Setup\n\n### Custom base image \n```Domino Standard Environment Py3.9 R4.2```\n\n\n### Dockerfile instructions\n\n```\nUSER root:root\n\nRUN pip uninstall --yes mlflow\n\nRUN pip install openai langchain  transformers tiktoken  sentence-transformers \\\n                qdrant-client ragas mlflow==2.8.0 getpass4 anthropic evaluate \\\n                textstat streamlit pypdf accelerate peft bitsandbytes\n\nRUN pip install -i https://test.pypi.org/simple/ streamlit-chat-domino\n```\nOn `se2-demo` this environment is available as `MedRAG`\n\n### \n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdominodatalab%2Frag","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdominodatalab%2Frag","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdominodatalab%2Frag/lists"}