{"id":22410834,"url":"https://github.com/runtime-error786/hybridsearch-rerank","last_synced_at":"2025-03-27T02:44:12.524Z","repository":{"id":253760985,"uuid":"844445825","full_name":"runtime-error786/HybridSearch-Rerank","owner":"runtime-error786","description":null,"archived":false,"fork":false,"pushed_at":"2024-08-19T20:43:42.000Z","size":1601,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-02-01T08:21:54.114Z","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/runtime-error786.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":"2024-08-19T09:20:53.000Z","updated_at":"2024-12-31T19:23:37.000Z","dependencies_parsed_at":"2025-02-01T08:21:03.223Z","dependency_job_id":"36bf1596-70e9-4a19-9699-2df5ca46cea4","html_url":"https://github.com/runtime-error786/HybridSearch-Rerank","commit_stats":null,"previous_names":["runtime-error786/hybridsearch-rerank"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runtime-error786%2FHybridSearch-Rerank","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runtime-error786%2FHybridSearch-Rerank/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runtime-error786%2FHybridSearch-Rerank/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/runtime-error786%2FHybridSearch-Rerank/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/runtime-error786","download_url":"https://codeload.github.com/runtime-error786/HybridSearch-Rerank/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245773144,"owners_count":20669719,"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":"2024-12-05T13:11:31.394Z","updated_at":"2025-03-27T02:44:12.496Z","avatar_url":"https://github.com/runtime-error786.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RAG-based Question Answering System with HybridSearch , Reranking and Compression\n\nThis project implements a Retrieval-Augmented Generation (RAG) system for question-answering, combining multiple retrieval techniques with reranking and contextual compression to optimize the relevance and accuracy of responses.\n\n## Overview\n\nIn this project, we build a sophisticated question-answering system using the following components:\n\n- **RAG (Retrieval-Augmented Generation)**: This technique combines document retrieval and generation to answer questions. It first retrieves relevant documents and then uses a language model to generate answers based on the retrieved content.\n  \n- **BM25Retriever**: A sparse retrieval method based on the BM25 algorithm. It is used to retrieve a broad set of relevant documents based on the query.\n\n- **Cohere Reranking**: A deep learning-based model provided by Cohere that reorders the initially retrieved documents, ensuring that the most relevant documents are prioritized.\n\n- **ContextualCompressionRetriever**: This retriever further refines the retrieval process by focusing on the most relevant sections of documents, effectively compressing the information that is passed to the language model.\n\n- **EnsembleRetriever**: Combines the outputs of multiple retrieval methods (e.g., BM25 and vector-based retrieval) to improve the breadth and relevance of the retrieved documents.\n\n- **RetrievalQA Chain**: A hybrid chain that integrates retrieval and language model capabilities to generate high-quality, contextually accurate answers.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fruntime-error786%2Fhybridsearch-rerank","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fruntime-error786%2Fhybridsearch-rerank","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fruntime-error786%2Fhybridsearch-rerank/lists"}