diff --git a/modules/genai-ecosystem/pages/customer-graph-agent.adoc b/modules/genai-ecosystem/pages/customer-graph-agent.adoc index 4654df56..240d0019 100644 --- a/modules/genai-ecosystem/pages/customer-graph-agent.adoc +++ b/modules/genai-ecosystem/pages/customer-graph-agent.adoc @@ -1,4 +1,4 @@ -= GraphRAG Agent for \Customer & Retail Analytics += GraphRAG Agent for Customer & Retail Analytics include::_graphacademy_llm.adoc[] :slug: customer-graph-agent :author: Zach Blumenfeld @@ -11,10 +11,10 @@ include::_graphacademy_llm.adoc[] This is an *end-to-end worked example for building a GraphRAG agent to accelerate customer and retail analytics*. It covers the entire process from: -1. *Quickly constructing a graph from mixed unstructured and structured data sources*. -2. *Resolving and linking entities* in the graph along the way. -3. *Creating diverse graph retrieval tools*, including query templates, vector search, dynamic text2Cypher, and graph community detection to answer a boarder range of questions. -4. *Building an agent* with Semantic Kernel for conducting analytics and responding to complex user questions. +1. *Quickly constructing a graph from mixed unstructured and structured data sources* +2. *Resolving and linking entities* in the graph along the way +3. *Creating diverse graph retrieval tools*, including query templates, vector search, dynamic text2Cypher, and graph community detection to answer a boarder range of questions +4. *Building an agent* with Semantic Kernel for conducting analytics and responding to complex user questions All of this using a central *source-of-truth graph schema* to govern the process and AI-interactions, ensuring higher data & retrieval quality. @@ -27,7 +27,7 @@ This workflow can be adapted for *analytics, reporting, and Q&A* across various Follow the instructions below to try it yourself! 🚀 -image::ai-customer-graph-query-sample.png[align=center] +image::ai-customer-graph-query-sample.png[align="center"] == Prerequisites @@ -84,7 +84,7 @@ This script perform entity extraction on the `credit-notes.pdf` file and write e Once complete, you can check the database to see the generated graph. Go to the https://console.neo4j.io/[Aura Console^] and navigate to the Query tab. -image::ai-customer-graph-unstruct-ingest-1-goto-query.png[align=left] +image::ai-customer-graph-unstruct-ingest-1-goto-query.png[align="left"] Select the "Connect instance" button