From e8a502b44c953c5959bc07dc72d59827cb865e66 Mon Sep 17 00:00:00 2001 From: zach-blumenfeld Date: Wed, 25 Sep 2024 14:13:01 -0400 Subject: [PATCH] Updating Customer Experience Intro for Clarity --- .../pages/ai-for-customer-experiences.adoc | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/modules/genai-ecosystem/pages/ai-for-customer-experiences.adoc b/modules/genai-ecosystem/pages/ai-for-customer-experiences.adoc index 24c1c473..76048699 100644 --- a/modules/genai-ecosystem/pages/ai-for-customer-experiences.adoc +++ b/modules/genai-ecosystem/pages/ai-for-customer-experiences.adoc @@ -11,14 +11,14 @@ include::_graphacademy_llm.adoc[] //image::https://dist.neo4j.com/wp-content/uploads/20240618104511/build-kg-genai-e1718732751482.png[width=800, align=center,link="https://llm-graph-builder.neo4jlabs.com/",window="_blank"] -Use GenAI + GraphRAG to improve customer experiences throughout multiple touch-points in the journey: +Use Graph-powered RAG (GraphRAG) to improve customer experiences throughout multiple touch-points in their journey: * *Discovery:* Generate personalized marketing and email content * *Search:* Offer tailored results based on semantic similarity * *Recommendations:* Provide targeted product suggestions * *Support:* Deliver compliant AI scripts for customer assistance -This short guide walks through setting up a full-stack GraphRAG application demonstrating all the above using Neo4j, LangChain (with LangServ), and OpenAI. The app focuses on a retail example using the https://github.com/neo4j-product-examples/graphrag-customer-experience#:~:text=H%26M%20Personalized%20Fashion%20Recommendations%20Dataset[H&M Personalized Fashion Recommendations Dataset^], a sample of real customer purchase data that includes rich information around products including names, types, descriptions, department sections, etc. All code can be found in the https://github.com/neo4j-product-examples/graphrag-customer-experience[GitHub repository^]. +This short guide walks through setting up a full-stack GraphRAG application demonstrating all the above using Neo4j, LangChain (with LangServe), and OpenAI. The app focuses on a retail example using the https://github.com/neo4j-product-examples/graphrag-customer-experience#:~:text=H%26M%20Personalized%20Fashion%20Recommendations%20Dataset[H&M Personalized Fashion Recommendations Dataset^], a sample of real customer purchase data that includes rich information around products including names, types, descriptions, department sections, etc. All code can be found in the https://github.com/neo4j-product-examples/graphrag-customer-experience[GitHub repository^]. image::ai-cust-exp-architecture.png[align=center] @@ -36,8 +36,8 @@ Clone the repository git clone https://github.com/neo4j-product-examples/graphrag-customer-experience.git ---- -create a `.env` file with the below. Fill in your OpenAI key. You can use our pre-loaded retail demo database to start. -The git repository has directions for creating the database from source data if you are interested. +create a `.env` file with the below. Fill in your OpenAI key. You can use our pre-loaded demo database to start, just copy the Neo4j uri, password, username, and database credentials below. +Alternatively, the https://github.com/neo4j-product-examples/graphrag-customer-experience[GitHub repository^] has directions for creating your own database from source data if you are interested. [source, bash] ----