RAG from Scratch
Contribute to labdmitriy/llm-rag development by creating an account on GitHub.
Example
What Is GraphRAG?
GraphRAG is a powerful retrieval mechanism that improves Generative AI applications by taking advantage of the rich context in graph data structures.
Concept
Introducing the Weaviate Query Agent | Weaviate
Learn about the Query Agent, our new agentic search service that redefines how you interact with Weaviate’s database!
Design Pattern
An Overview of Late Interaction Retrieval Models: ColBERT, ColPali, and ColQwen
Late interaction allow for semantically rich interactions that enable a precise retrieval process across different modalities of unstructured data, including text and images.
In this context, “interaction” refers to the process of assessing how well a document matches a given search query by comparing their representations.
A dense retrieval model is a model that uses some type of neural network architecture to retrieve relevant documents for a search query.
Traditional methods for retrieval commonly use “no-interaction” retrieval models. In this case, the search query and documents are processed separately
Advantages of no-interaction retrieval models are primarily that they are fast and computationally efficient
These characteristics make full interaction models great for second-stage retrieval, like reranking a curated set of candidate documents
extremely computationally expensive
contextually rich
scalable and contextually rich
storage requirements - they require an embedding for each token, which requires a lot more storage for a complete set of vectors
Disadvantages of no-interaction retrieval models lie in the lack of interaction between the search query and the documents.
multimodal late interaction retrieval models
vision language models (VLMs) instead of text-only models
ConceptVectifyAI/PageIndex: Document Index System for Reasoning-Based RAG
Document Index System for Reasoning-Based RAG
Tool
How to Build a Knowledge Graph in 7 Steps
Discover how to build a knowledge graph in 7 simple steps, from defining your use case to creating a model to ingesting your data.
Tutorial
Building Your Own RAG System: Enhancing Claude with Your Documentation
Connecting Claude Desktop to Your Documentation Through MCP and Qdrant
Tutorial
EbookDevelopers guide how to build knowledge graph
Ebook
Design and Develop a RAG Solution - Azure Architecture Center
How to plan a RAG project
Evaluating Chunking Strategies for Retrieval | Chroma Research
Deep Dive
Transformation Agent | Weaviate
This Weaviate Agent is in technical preview.
ToolDo you know the answer to these three questions? You should... 1. What are vector embeddings and embedding models? 2. What’s the benefit of having a vector database for vector search? 3. What’s on the next horizon for AI applications? I just finished a 3-part webinar series… pic.twitter.com/nFOAPHQw2q— Victoria Slocum (@victorialslocum) March 5, 2025
Concept
Multi-vector embeddings (ColBERT, ColPali, etc.) | Weaviate
Learn how to use multi-vector embeddings in Weaviate.
15 Best Graph Visualization Tools for Your Neo4j Graph Database
Discover the best graph visualization tools for visualizing your Neo4j graph database, including development, exploration, dashboarding, and embedded tools.
ToolJérémy Ravenel on LinkedIn: What are the key ontology standards you should have in mind? Ontology… | 100 comments
What are the key ontology standards you should have in mind?
Ontology standards are crucial for knowledge representation and reasoning in AI and data… | 100 comments on LinkedIn
From PDFs to Insights: Structured Outputs from PDFs with Gemini 2.0
Learn how to extract structured data from PDFs with Gemini 2.0 and Pydantic.
Tutorialrecipes/weaviate-features/generative-search/generative_search_anthropic/rag_with_anthropic_citations.ipynb at main · weaviate/recipes
This repository shares end-to-end notebooks on how to use various Weaviate features and integrations! - weaviate/recipes
Open source: it works!
Two months ago user durable-racoon posted about DocumentContextExtractor, their iteration on a technique for improving the accuracy of RAG that both and had made demo implementations of.
Contextual Retrieval improves the…
— LlamaIndex 🦙 (@llama_index)
ConceptThe recipes repo is such an underrated developer resource.
Here are 8 notebooks you should know about:
1. Vanilla vector search:
2. Image similarity search:
3. Hybrid search:
4. Local RAG…
— Leonie (@helloiamleonie)
GitHub - getomni-ai/zerox: PDF to Markdown with vision models
PDF to Markdown with vision models.
Packageathina-ai/rag-cookbooks: This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems.
This repository contains various advanced techniques for Retrieval-Augmented Generation (RAG) systems. - athina-ai/rag-cookbooks
Qwen2.5-VL/cookbooks at main · QwenLM/Qwen2.5-VL
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud. - QwenLM/Qwen2.5-VL
Exampleq(80)%2Fcueao4i8p6is73fqbiig.webp?width=92&height=&ar=&mode=&dpr=2)
SurrealDB | Enhancing Retrieval-Augmented Generation with SurrealDB
GraphRAG: Enhancing Retrieval-Augmented Generation with SurrealDB, Gemini and DeepSeek
Design Pattern
Integrate Qdrant and Neo4j to Enhance Your RAG Pipeline
Learn more about integrating Neo4j with Qdrant for external vector searches by spinning up both locally and loading with sample data.
GitHub - X-PLUG/mPLUG-DocOwl: mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding
mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding - X-PLUG/mPLUG-DocOwl
We now support VLMs in smolagents!
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
EyeLevel | RAG on-Prem
EyeLevel.ai's GroundX APIs are the fastest way to build enterprise-grade RAG on prem or cloud. Trusted by Air France, Dartmouth, UltraCommerce and hundreds more.
Interactive LLM-Powered Data Processing with DocWrangler
DocWrangler is an IDE that provides instant feedback, visual exploration tools, and AI assistance for building and iterating on LLM-powered data processing pipelines