{"id":24770328,"url":"https://github.com/farhaj499/rag_with_weaviate_db","last_synced_at":"2026-04-12T18:47:15.137Z","repository":{"id":270343300,"uuid":"910067311","full_name":"Farhaj499/RAG_with_Weaviate_DB","owner":"Farhaj499","description":"This project implements a Retrieval Augmented Generation (RAG) system that answers questions based on the PDF document. It utilizes Weaviate as a vector database for efficient retrieval of relevant information and Gemini to generate natural language responses.","archived":false,"fork":false,"pushed_at":"2025-01-12T17:40:53.000Z","size":64,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-01-29T03:38:00.356Z","etag":null,"topics":["agentic-ai","embeddings","huggingface-transformers","langchain","pdf-processing","python","rag","retrieval-augmented-generation","semantic-search","vector-database","weaviate"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","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/Farhaj499.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":"2024-12-30T12:12:47.000Z","updated_at":"2025-01-15T06:42:19.000Z","dependencies_parsed_at":"2024-12-30T13:22:49.679Z","dependency_job_id":"4f68f54e-b076-4a62-94fc-853646fa1da2","html_url":"https://github.com/Farhaj499/RAG_with_Weaviate_DB","commit_stats":null,"previous_names":["farhaj499/rag_with_weaviate_db"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Farhaj499%2FRAG_with_Weaviate_DB","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Farhaj499%2FRAG_with_Weaviate_DB/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Farhaj499%2FRAG_with_Weaviate_DB/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Farhaj499%2FRAG_with_Weaviate_DB/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Farhaj499","download_url":"https://codeload.github.com/Farhaj499/RAG_with_Weaviate_DB/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245161997,"owners_count":20570690,"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":["agentic-ai","embeddings","huggingface-transformers","langchain","pdf-processing","python","rag","retrieval-augmented-generation","semantic-search","vector-database","weaviate"],"created_at":"2025-01-29T03:37:26.065Z","updated_at":"2026-04-12T18:47:10.108Z","avatar_url":"https://github.com/Farhaj499.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agentic AI RAG System with Weaviate and Gemini\n\nThis project implements a Retrieval Augmented Generation (RAG) system that answers questions based on the \"Agentic AI\" PDF document ([https://www.artificiality.world/content/files/2024/05/Agentic-AI.pdf](https://www.artificiality.world/content/files/2024/05/Agentic-AI.pdf)). It utilizes Weaviate as a vector database for efficient retrieval of relevant information and Gemini (or another LLM) to generate natural language responses.\n\n## Overview\n\nThis RAG system follows these key steps:\n\n1.  **Data Ingestion:** The \"Agentic AI\" PDF is downloaded and its text content is extracted.\n2.  **Text Chunking:** The extracted text is divided into smaller chunks to improve retrieval relevance and manage context within the LLM.\n3.  **Embedding Generation:** Sentence embeddings are created for each text chunk using the \"sentence-transformers/all-mpnet-base-v2\" Hugging Face model.\n4.  **Vector Database Storage:** The text chunks and their corresponding embeddings are stored in a Weaviate vector database.\n5.  **Retrieval and Question Answering:** When a user asks a question, the system generates an embedding for the query, retrieves the most similar text chunks from Weaviate, and uses Gemini (or another LLM) to generate a natural language answer based on the retrieved context.\n\n## Technologies Used\n\n*   **Weaviate:** Vector database for storing and retrieving embeddings.\n*   **Hugging Face Transformers:** For generating sentence embeddings using \"sentence-transformers/all-mpnet-base-v2\".\n*   **Gemini (or alternative LLM):** Large Language Model for generating natural language responses.\n*   **Python:** Programming language for implementation.\n*   **LangChain (Optional but recommended):** For streamlining the RAG pipeline.\n*   **DirectoryLoader :** For all PDF files text extraction.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffarhaj499%2Frag_with_weaviate_db","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffarhaj499%2Frag_with_weaviate_db","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffarhaj499%2Frag_with_weaviate_db/lists"}