Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Everything you need to know to build your own RAG application
| Date | Stars |
|---|---|
| 2026-07-24 | 4144 |
| 2026-07-25 | 4144 |
| 2026-07-28 | 4144 |
| 2026-07-30 | 4144 |
| 2026-07-31 | 4149 |
| 2026-08-03 | 4149 |
| 2026-08-05 | 4149 |
| 2026-08-06 | 4149 |
Today
— stars today
This week
+5 stars this week
This month
— stars this month
Momentum
5.0
growth rate 0.12%/day
# Retrieval-Augmented Generation (RAG) Project #### 🔜 Check out [bragai.dev](https://bragai.dev) (launching soon) --------------------- This repository contains a comprehensive exploration of Retrieval-Augmented Generation (RAG) for various applications. Each notebook provides a detailed, hands-on guide to setting up and experimenting with RAG from an introductory level to advanced implementations, including multi-querying and custom RAG builds.  ## Project Structure If you want to jump straight into it, check out the file `full_basic_rag.ipynb` -> this file will give you a boilerplate starter code of a fully customizable RAG chatbot. Make sure to run your files in a virtual environment (checkout section `Get Started`) The following notebooks can be found under the directory `notebooks/`. ### [1]\_rag_setup_overview.ipynb This introductory notebook provides an overview of RAG architecture and its foundational setup. The notebook walks through: - **Environment Setup**: Configuring the environment, installing necessary libraries, and API setups. - **Initial Data Loading**: Basic document loaders and data preprocessing methods. - **Embedding Generation**: Generating embeddings using various models, including OpenAI's embeddings. - **Vector Store**: Setting up a vector store (ChromaDB/Pinecone) for efficient similarity search. - **Basic RAG Pipeline**: Creating a simple retrieval and generation pipeline to serve as a baseline. ### [2]\_rag_with_multi_query.ipynb Building on the basics, this notebook introduces multi-querying techniques in the RAG pipeline, exploring: - **Multi-Query Setup**: Configuring multiple queries to diversify retrieval. - **Advanced Embedding Techniques**: Utilizing multiple embedding models to refine retrieval. - **Pipeline with Multi-Querying**: Implementing multi-query handling to improve relevance in response generation. - **Comparison & Analysis**: Comparing results with single-query pipelines and analyzing performance improvements. ### [3]_rag_routing_and_query_construction.ipynb This notebook delves deeper into customizing a RAG pipeline. It covers: - **Logical Routing:** Implements function-based routing for classifying user queries to appropriate data sources based on programming languages. - **Semantic Routing:** Uses embeddings and cosine similarity to direct questions to either a math or physics prompt, optimizing response accuracy. - **Query Structuring for Metadata Filters:** Defines structured search schema for YouTube tutorial metadata, enabling advanced filtering (e.g., by view count, publication date). - **Structured Search Prompting:** Leverages LLM prompts to generate database queries for retrieving relevant content based on user input. - **Integration with Vector Stores:** Links structured queries to vector stores for efficient data retrieval. ### [4]_rag_indexing_and_advanced_retrieval.ipynb Continuing from the previous customization, this notebook explores: - **Preface on Document Chunking:** Points to external resources for document chunking techniques. - **Multi-representation Indexing:** Sets up a multi-vector indexing structure for handling documents with different embeddings and representations. - **In-Memory Storage for Summaries:** Uses InMemoryByteStore for storing document summaries alongside parent documents, enabling efficient retrieval. - **MultiVectorRetriever Setup:** Integrates multiple vector representations to retrieve relevant documents based on user queries. - **RAPTOR Implementation:** Explores RAPTOR, an advanced indexing and retrieval model, linking to in-depth resources. - **ColBERT Integration:** Demonstrates ColBERT-based token-level vector indexing and retrieval, which captures contextual meaning at a fine-grained level. - **Wikipedia Example with ColBERT:** Retrieves information about Hayao Miyazaki using the ColBERT retrieval model for demonstration. ### [5]_rag_retrieval_and_reranking.ip
Excerpt of 9,851 characters
Read on GitHub
61
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:67f3d0bbddad71ef, topic:rag, topic:retrieval-augmented-generation, readme:retrieval-augmented generation
matched fp:67f3d0bbddad71ef, topic:chatbot, readme:chatbot