Blog Contributor

Learn how to overcome them using knowledge graphs and structured toolsEveryone loves text embedding models, and for good reason: They excel at encoding unstructured text, making it easier to discover semantically similar content. It’s no surprise that they form the backbone of most RAG... read more

Store the MSFT GraphRAG output into Neo4j and implement local and global retrievers with LangChain or LlamaIndex Microsoft’s GraphRAG implementation has gained significant attention lately. In my last blog post, I discussed how the graph is constructed and explored some of the innovative... read more

Constructing knowledge graphs from text has been a fascinating area of research for quite some time. With the advent of large language models (LLMs), this field has gained more mainstream attention. However, LLMs can be quite costly. An alternative approach is to fine-tune smaller models, which has... read more

Created using ChatGPTUse Llama 3.1 native function-calling capabilities to retrieve structured data from a knowledge graph to power your RAG applicationsWhile most people focus on retrieval-augmented generation (RAG) over unstructured text, such as company documents or documentation, I am... read more

Combine text extraction, network analysis, and LLM prompting and summarization for improved RAG accuracyI am always intrigued by new approaches to implementing Retrieval-Augmented Generation (RAG) over graphs, often called GraphRAG. However, it seems that everyone has a different... read more

Entity Deduplication and Custom Retrieval Methods to Increase GraphRAG Accuracy BackgroundThe Property Graph Index is an excellent addition to LlamaIndex and an upgrade from the previous knowledge graph integration. The data representation is now slightly different. In the previous... read more

Optimizing vector retrieval with advanced graph-based metadata techniques using LangChain and Neo4j.In retrieval-augmented generation (RAG) applications, text embeddings and vector similarity search help us find documents by understanding their meanings and how similar they are to each other.... read more

When you give large language models (LLMs) the power to search beyond their own fixed knowledge and pull in information from the wider world, you have more options for LLM-powered applications. This technique of retrieving data from external sources is called retrieval-augmented generation... read more

A practical guide to constructing and retrieving information from knowledge graphs in RAG applications with Neo4j and LangChain. Image created by DALL-E.Graph retrieval-augmented generation (GraphRAG) is gaining momentum and becoming a powerful addition to traditional vector search retrieval... read more

Retrieval-augmented generation (RAG) applications excel at answering simple questions by integrating data from external sources into LLMs. But they struggle to answer multi-part questions that involve connecting the dots between associated pieces of information. That’s because RAG applications... read more

Forbes recently named RAG applications the hottest thing in AI. That comes as no surprise since Retrieval-Augmented Generation requires minimal code and helps build user trust in your LLM. The challenge when building a great RAG app or chatbot is handling structured text alongside unstructured... read more

These days, you can deploy retrieval-augmented generation (RAG) applications in just a few minutes. Most RAG applications like Chat with Your PDF use basic vector similarity search to retrieve relevant information from the database and feed it to the LLM to generate a final response. Vector... read more

Learn to implement a Mixtral agent that interacts with a graph database Neo4j through a semantic layer   By now, we all have probably recognized that we can significantly enhance the capabilities of LLMs by providing them with additional tools. For example, even ChatGPT can use Bing... read more

Learn how to customize LangChain’s wrapper of Neo4j vector index. A robot customizing stuff as imagined by Midjourney. Neo4j was and is an excellent fit for handling structured information, but it struggled a bit with semantic search due to its brute-force approach. However, the struggle is in... read more

Understanding data points through the context of their relationshipsThis is the fourth blog post of Neo4j’s NaLLM project. We started this project to explore, develop, and showcase practical uses of these LLMs in conjunction with Neo4j. As part of this project, we will construct and publicly... read more

How to optimize prompts for Cypher statement generation to retrieve relevant information from Neo4j in your LLM applicationsLast time, we looked at how to get started with Cypher Search in the LangChain library and why you would want to use knowledge graphs in your LLM applications. In this... read more

Will we still need to learn query languages in the future?Photo by Lyman Hansel Gerona on UnsplashLarge language models have great potential to translate a natural language into a query language. For example, some people use GPT models to translate text to SQL, while others use GPT models... read more

Learn how to implement a chatbot that bases its answers on the information retrieved from a graph databaseNot so long ago, OpenAI added Chat API, which is optimized for generating conversations. The main difference between Chat and the older Completion APIs is that the Chat API allows specifying... read more

Use GPT-4 as a domain expert to help you extract knowledge from a video transcript.A couple of days ago, I got access to GPT-4. The first thing that came to my mind was to test how well it performs as an information extraction model, where the task is to extract relevant entities and... read more

Natural Language Processing (NLP) has seen rapid advancements in recent years. One important aspect of this progress has been the use of embeddings, which are numerical representations of words or phrases that capture their meaning and relationships to other words in a language. Embeddings can be... read more

ChatGPT has changed how I, and probably most of you, look at AI and chatbots. We can use chatbots to help us find information, construct creative works, and more.However, one problem with ChatGPT and similar chatbots is that they can hallucinate and return... read more

Knowing your users is vital to any business. When your users can interact with each other on a social media platform, content sharing platform, or even work-related platforms, you can construct a network between your users based on their interactions and extract graph-based features to segment your... read more

A wave of graph-based approaches to data science and machine learning is rising. We live in an era where the exponential growth of graph technology is predicted . The ability to analyze data points through the context of their relationships enables more profound and accurate data exploration and... read more

Learn the basic syntax of the newly released Python client for Neo4j Graph Data ScienceData scientists like me love Python. It features a wide variety of machine learning and data science libraries that can help you get started on a data science project in minutes. It is not uncommon to use a... read more

Editor's note: This presentation is given by Tomaz Bratanic at NODES 2021. As organizations build knowledge graphs to find answers to their most pressing problems, one of the challenges they face is that much of the information they would like to incorporate in their knowledge graphs exists in... read more