└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Knowledge Graphs + LLMs 2 | 3 | 4 | 5 | ## **Background** 6 | 7 | A collection of interesting links, articles, research papers and projects related to knowledge graphs, GenAI and LLMs (large language models) 8 | 9 | I’ve been fascinated with the concept of “connected knowledge” and knowledge representation for quite some time. When blogging was still a major trend, I wrote extensively about mind mapping and it’s still a significant part of my personal and business workflow today. 10 | 11 | In the mid-late 2000s, I developed a keen interest in personal knowledge management. Inspired by the work of Gordon Bell (https://en.wikipedia.org/wiki/Gordon_Bell), I created my own Personal Memex project using Semantic Mediawiki (RDF, SPARQL, etc.) to store and visualize knowledge and data (https://eric-blue.com/my-projects/personal-memex/). 12 | 13 | Fast forward to the last 18-24 months, and I’ve immersed myself in the GenAI space and large language models (LLMs). A couple of months ago, I posted about the National Security Hackathon in San Francisco (May - 2024), where we leveraged graph databases and large language models for knowledge extraction and modeling. Since then, partly due to the influence of social media algorithms and general momentum in this space, I’ve noticed a surge in activity. Although I’ve been aware of graph databases for some time and have experimented with them over the years, my interest has been reignited given their potential when coupled with GPT. 14 | 15 | With that in mind, I wanted to share a collection of interesting links, articles, research papers, and projects related to knowledge graphs, GenAI, and LLMs. This list is not exhaustive and reflects the activity I’ve noted since May. However, I plan to continually update it. If anyone has recommendations for interesting projects, research, or key players in this space, please let me know—I’d love to include them in this list. 16 | 17 | # **Books** 18 | 19 | ### **Knowledge Graph-Enhanced RAG** 20 | 21 | - https://www.manning.com/books/knowledge-graph-enhanced-rag 22 | 23 | ## **Frameworks** 24 | 25 | ### **Graph Databases** 26 | 27 | - Neo4j 28 | - https://neo4j.com/ 29 | - ArangoDB 30 | - https://arangodb.com/ 31 | - FalkorDB 32 | - https://github.com/FalkorDB 33 | - objective is to create an outstanding Knowledge Graph specifically for Large Language Models (LLM) that boasts exceptionally low latency, ensuring swift delivery of information through our Graph Database, known as KG-RAG. 34 | 35 | ### **Microsoft GraphRag** 36 | 37 | - Github 38 | - https://github.com/microsoft/graphrag 39 | - Microsoft 40 | - modular graph-based Retrieval-Augmented Generation (RAG) system 41 | - Links 42 | - GraphRAG: Unlocking LLM discovery on narrative private data 43 | - https://www.microsoft.com/en-us/research/blog/graphrag-unlocking-llm-discovery-on-narrative-private-data/ 44 | 45 | ### **LlamaIndex** 46 | 47 | - Property Graph Index 48 | - Introducing the Property Graph Index: A Powerful New Way to Build Knowledge Graphs with LLMs 49 | - https://www.llamaindex.ai/blog/introducing-the-property-graph-index-a-powerful-new-way-to-build-knowledge-graphs-with-llms 50 | - integrates with Neo4j 51 | - Articles 52 | - Customizing property graph index in LlamaIndex 53 | - https://www.llamaindex.ai/blog/customizing-property-graph-index-in-llamaindex 54 | - Github 55 | - https://github.com/tomasonjo/blogs/blob/master/llm/llama_index_neo4j_custom_retriever.ipynb 56 | 57 | ### **LangGraph** 58 | 59 | - https://langchain-ai.github.io/langgraph/ 60 | - Building language agents as graphs 61 | - library for building stateful, multi-actor applications with LLMs, used to create agent and multi-agent workflows 62 | - Articles 63 | - Build a Reliable RAG Agent using LangGraph 64 | - https://medium.com/the-ai-forum/build-a-reliable-rag-agent-using-langgraph-2694d55995cd 65 | - LangGraph Cloud 66 | - https://langchain-ai.github.io/langgraph/cloud/ 67 | - Article 68 | - https://cobusgreyling.medium.com/langchain-just-launched-langgraph-cloud-bf8f65e45a54 69 | - Video 70 | - https://www.youtube.com/watch?v=l4sMKF1dTDM 71 | 72 | ### **Neo4j GraphRAG** 73 | 74 | - Video 75 | - Demo LLM Knowledge Graph Construction with Gemini (short) 76 | - https://www.youtube.com/watch?v=PeYwFoYY3jI 77 | - Transforms unstructured documents, Youtube videos, Wikipedia pages to Knowledge Graph in 𝟑 𝐜𝐥𝐢𝐜𝐤𝐬. 78 | - Articles 79 | - Neo4j Brings GraphRAG Capabilities for GenAI to Google Cloud 80 | - https://neo4j.com/blog/graphrag-genai-googlecloud/ 81 | - GenAI package for Python 82 | - https://neo4j.com/docs/neo4j-genai-python/current/ 83 | 84 | ### **DataBricks** 85 | 86 | - Neo4j-Databricks Connector Delivers Deeper Insights, Faster GenAI Development 87 | - https://neo4j.com/blog/neo4j-databricks-connector/ 88 | 89 | ## **Research Articles / Papers** 90 | 91 | ### **Cluster of research abstracts on graphs and llms** 92 | 93 | - Nomic Graph Research 94 | - https://atlas.nomic.ai/data/ct/graph-research/map/52484ea8-e730-480a-990d-ab917df980eb 95 | 96 | ### **A Survey on Open Information Extraction from Rule-based Model to Large Language Model** 97 | 98 | - https://arxiv.org/pdf/2208.08690v6 99 | - A new survey paper traces the evolution of Open Information Extraction. - Open Information Extraction (OpenIE) 100 | 101 | ### **GraphReader** 102 | 103 | - The Next Level of Long-form Document Understanding and Why Iteration Matters 104 | - GraphReader with a 4k context window consistently outperformed GPT-4 with a 128k context window on texts ranging from 16k to 256k words 105 | - GraphReader: Building Graph-based Agent to Enhance Long-Context Abilities of Large Language Models 106 | - https://arxiv.org/html/2406.14550v1 107 | 108 | ### **A Survey of Large Language Models for Graphs** 109 | 110 | - https://arxiv.org/abs/2405.08011 111 | - Combining GNNs (Graph Neural Networks) with LLMs (Large Language Models) 112 | 113 | ### **GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning** 114 | 115 | - https://arxiv.org/abs/2405.20139 116 | 117 | ### **XLLM** 118 | 119 | - New Generation of Large Language Models 120 | - https://mltechniques.com/2024/06/03/new-trends-in-llm-overview-with-focus-on-xllm/ 121 | - Presentation 122 | - Vincent Granville, PhD - Chief AI Scientist 123 | - https://docs.google.com/presentation/d/15jlAz0pOmybTxAzywzXklBcL1DLvQy50/edit#slide=id.p1 124 | - xLLM has been using knowledge graphs since the very beginning: taxonomies, related concepts (related links found in any large repository such as Wikipedia or corporate, that you can extract to enrich your LLM) 125 | 126 | ### **ML Techniques** 127 | 128 | - Resources & Papers 129 | - https://mltechniques.com/resources/ 130 | 131 | ### **Unifying Large Language Models and Knowledge Graphs: A Roadmap** 132 | 133 | - https://arxiv.org/abs/2306.08302 134 | 135 | ### **From LLM Graph** 136 | 137 | - Knowledge Graph Generation From Text 138 | - https://arxiv.org/abs/2211.10511 139 | - Towards Foundation Models for Knowledge Graph Reasoning 140 | - https://arxiv.org/abs/2310.04562 141 | - BertNet: Harvesting Knowledge Graphs with Arbitrary Relations from Pretrained Language Models 142 | - https://arxiv.org/abs/2206.14268 143 | - Large Language Models on Graphs: A Comprehensive Survey 144 | - https://arxiv.org/abs/2312.02783 145 | - A Hitchhiker’s Guide to Knowledge Galaxies 146 | - https://caminao.blog/knowledge-management-booklet/a-hitchhikers-guide-to-knowledge-galaxies/ 147 | - A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey" 148 | - https://github.com/PeterGriffinJin/Awesome-Language-Model-on-Graphs 149 | 150 | ## **Notable People - Sources of Knowledge** 151 | 152 | ### **LinkedIn** 153 | 154 | - Chandler T. Wilson 155 | - https://www.linkedin.com/in/chandlertwilson/ 156 | - AI, LLMs, OSINT, and alternative data for corporate strategy, private equity, and public affairs 157 | - Pascal Biese 158 | - https://www.linkedin.com/in/pascalbiese/ 159 | - LLM Watch - Daily LLM highlights 160 | - Tomaz Bratanic 161 | - https://www.linkedin.com/in/tomaz-bratanic-a58891127/ 162 | - Graph ML and GenAI research at Neo4j 163 | - Cobus Greyling 164 | - https://www.linkedin.com/in/cobusgreyling/ 165 | - LLMs, NLP, NLU, Chatbots, Voicebots, CCAI, Ambient Orchestration, Ubiquitous User Interfaces 166 | - Ryan Siegler 167 | - https://www.linkedin.com/in/ryan-siegler-816207102/ 168 | - GenAI | Vector DBs | Data Science | Emerging Technology Advocate 169 | - Dan Selman 170 | - https://www.linkedin.com/in/dselman/ 171 | - Distinguished Engineer @ DocuSign | CTO, Chief Architect 172 | 173 | ### **LLM Watch** 174 | 175 | - https://www.llmwatch.com/ 176 | - Newsletter 177 | - https://www.linkedin.com/newsletters/llm-watch-7106973553371099136/ 178 | 179 | ### **[DAIR.AI](http://DAIR.AI)** 180 | 181 | - Top AI-ML papers of the week 182 | - Democratizing Artificial Intelligence Research, Education, and Technologies 183 | - https://www.linkedin.com/company/dair-ai/posts/ 184 | 185 | ## **Interesting Apps** 186 | 187 | ### **Connected Papers** 188 | 189 | - Explore connected papers in a visual graph 190 | - https://www.connectedpapers.com/ 191 | 192 | ### **Open Source** 193 | 194 | - ScrapeGraphAI 195 | - https://github.com/VinciGit00/Scrapegraph-ai 196 | - https://scrapegraphai.com/ 197 | - web scraping python library that uses LLM and direct graph logic to create scraping pipelines for websites and local documents (XML, HTML, JSON, etc.). 198 | - Lab-Concerto-Graph 199 | - Graph storage for Concerto Models 200 | - https://github.com/accordproject/lab-concerto-graph 201 | - Concerto 202 | - https://concerto.accordproject.org/ 203 | - Article 204 | - Text to Knowledge Graph 205 | - https://blog.selman.org/2024/06/22/text-to-knowledge-graph/ 206 | - Movie - Knowledge graph demo 207 | - https://github.com/dselman/movie-graph 208 | - Knowledge graph in 100 lines of code 209 | - https://www.docusign.com/blog/developers/knowledge-graph-100-lines-code? 210 | - Llama Parse 211 | - Knowledge Graph Agent with LlamaParse 212 | - https://github.com/run-llama/llama_parse/blob/main/examples/knowledge_graphs/kg_agent.ipynb 213 | - Chat Graph 214 | - A generic web interface to chat with any graph created with Concerto Graph 215 | - https://github.com/dselman/chat-graph 216 | - Video 217 | - https://www.youtube.com/watch?v=GtbEiIce-S0 218 | - Knowledge Graphs: RAG is NOT all you need 219 | - https://blog.selman.org/2024/06/04/knowledge-graphs-rag-is-not-all-you-need/ 220 | - R2R - production ready RAG engine w/ knowledge graphs 221 | - https://github.com/SciPhi-AI/R2R 222 | - https://github.com/SciPhi-AI/R2R 223 | - EKnowledge 224 | - https://github.com/chigwell/eknowledge 225 | - Generating Knowledge Graphs from Textual Inputs Using Diverse Language Models 226 | - https://medium.com/@chigwel/eknowledge-generating-knowledge-graphs-from-textual-inputs-using-diverse-language-models-dfd8bf0f7b38 227 | - LLM Graph 228 | - https://github.com/dylanhogg/llmgraph 229 | - Graph Notebook: easily query and visualize graphs 230 | - https://github.com/aws/graph-notebook 231 | - PyG re-implementation of Neural Bellman-Ford Networks 232 | - https://github.com/KiddoZhu/NBFNet-PyG 233 | 234 | ### **Memary** 235 | 236 | - https://www.memarylabs.com/ 237 | - Memory for Agent Self-Improvement 238 | - Agents promote human-like reasoning and represent a significant leap towards AGI and understanding ourselves as humans. Memory is a key component of how we as humans approach tasks and should be given equal importance when building AI agents. Memary pioneers the use of action graphs to track agent resources so that your agent can continuously self-improve in production environments and become more reliable over time. 239 | - Github 240 | - https://github.com/kingjulio8238/memary 241 | 242 | ### **YWorks** 243 | 244 | - Advanced library for graph visualization 245 | - Fraud detection demo 246 | - https://www.yworks.com/demos/showcase/frauddetection/ --------------------------------------------------------------------------------