details added to steps and reorganized

Author: Baransel SAGINDA

content/guides/genai-leveraging-rag/image-1.png

@@ -11,39 +11,16 @@ params:
 ---
 
 
-This guide walks you through setting up a powerful AI stack that integrates Retrieval-Augmented Generation (RAG) systems with graph databases. In this guide, you’ll learn how to:
 
-- Set up a GenAI system that enhances language models with real-time data from graph databases
-- Use Docker to containerize and deploy the complete GenAI stack, including graph databases and AI models
-- Leverage Neo4j for efficient information retrieval and context-aware AI responses
-- Inspecting data in the database, ensuring smooth operation for AI-driven applications
+## Introduction
 
+Retrieval-Augmented Generation (RAG) is a powerful framework that enhances large language models (LLMs) by integrating information retrieval from external knowledge sources. This guide focuses on a specialized RAG implementation using graph databases like Neo4j, which excel in managing highly connected, relational data. Unlike traditional RAG setups with vector databases, combining RAG with graph databases offers better context-awareness and relationship-driven insights, making it ideal for domains like recommendation systems, compliance tracking, and social networks.
 
+In this guide, you will:
 
-## Introduction to Graph Databases 
-
-All NoSQL databases can be grouped under 4 main groups:
-
-* Document-based databases
-* Key-value stores
-* Column-oriented databases
-* Graph-based databases
-
-Being one of the four main groups, graph databases are specialized database systems designed to store and query data where relationships between entities are as important as the entities themselves. Unlike traditional databases, graph databases use nodes (vertices) to store entities and edges to store relationships between these entities, making them ideal for handling highly connected data.
-
-### Graph Databases vs SQL Databases 
-
-1. Data Model:
-   - SQL: Uses tables with rows and columns, relationships expressed through foreign keys
-   - Graph: Uses nodes and edges, relationships are much more flexible
-
-2. Schema Flexibility:
-   - SQL: Rigid schema, changes require extra steps
-   - Graph: Flexible schema, can add new relationships without migrations
-
-3. Use Cases:
-   - SQL: Structured data with fixed relationships
-   - Graph: Social networks, recommendation engines, knowledge graphs
+- Understand the benefits of integrating graph databases into a RAG system.
+- Set up a GenAI stack using Docker, including Neo4j and an AI model.
+- Explore a case study demonstrating the system’s effectiveness with real-world queries.
 
 
 ## Understanding RAG (Retrieval-Augmented Generation) 
@@ -62,80 +39,102 @@ The system operates as follows:
 3. The retrieved data is used to augment the input prompt for the LLM.  
 4. The LLM generates responses that blend the model's inherent knowledge with the retrieved context.  
 
-### When RAG is Effective 
-
-1. Knowledge Limitations:
-   - LLMs have fixed knowledge cutoffs
-   - Cannot access real-time or specialized information
-   - May hallucinate or provide outdated information
-
-2. Business Requirements:
-   - Need for accurate, up-to-date information
-   - Compliance and auditability
-   - Domain-specific knowledge integration
+To hold this vector information in a efficient manner, we need a special type of database.
 
-3. Cost Efficiency:
-   - Reduced need for model fine-tuning
-   - Smaller models can perform well with good context
-   - Lower computational requirements
 
+## Introduction to Graph Databases 
 
+Graph databases, such as Neo4j, are specifically designed for managing highly connected data. Unlike traditional relational databases, graph databases prioritize both the entities and the relationships between them, making them ideal for tasks where connections are as important as the data itself.
 
+In the broader landscape of NoSQL databases, there are four main categories:
 
-## A Case Study in RAG Implementation 
+* Document-based databases
+* Key-value stores
+* Column-oriented databases
+* Graph-based databases
 
-### What is Apache NiFi? 
+As one of these core categories, graph databases stand out for their unique approach to data storage and querying. They use nodes (or vertices) to represent entities and edges to represent the relationships between these entities. This structure allows for efficient handling of highly connected data and complex queries, which are difficult to manage in traditional database systems.
 
-Apache NiFi is a powerful data integration tool, but in our context, it serves us as a concept rather than a tool. Since it's a relatively new concept, large language models (LLMs) may have limited or no inherent knowledge about it.
+### Graph Databases vs SQL Databases 
 
+1. Data Model:
+   - SQL: Uses tables with rows and columns, relationships expressed through foreign keys
+   - Graph: Uses nodes and edges, relationships are much more flexible
 
+2. Schema Flexibility:
+   - SQL: Rigid schema, changes require extra steps
+   - Graph: Flexible schema, can add new relationships without migrations
 
-    Question: What is Apache Nifi? 
-    RAG: Disabled
+3. Use Cases:
+   - SQL: Structured data with fixed relationships
+   - Graph: Social networks, recommendation engines, knowledge graphs
 
-    Hello! I'm here to help you with your question about Apache NiFi. Unfortunately, I don't know the answer to that question. I'm just an AI and my knowledge cutoff is December 2022, so I may not be familiar with the latest technologies or software. Can you please provide more context or details about Apache NiFi? Maybe there's something I can help you with related to it.
 
-    Question: What is Apache Nifi? 
-    RAG: Enabled
 
-    Answer:
 
-    Apache NiFi is an open-source, distributed data processing system that allows you to collect, transform, and transport data across various sources and sinks. It provides a graphical user interface for designing and managing data flows, as well as a set of APIs for integrating with other systems.
+## Practical Implementation: A Case Study in RAG Effectiveness
 
-    According to this Stack Overflow question, the free Neo4J JDBC driver doesn't understand SQL, only Cypher, so you would need to use a non-free BI Connector to connect to Neo4j from Apache Drill.
+To illustrate the power of RAG systems in practice, let's examine a real-world implementation using Apache NiFi as our subject matter. This case study demonstrates how RAG can enhance an AI's ability to provide accurate, contextual information about specialized technical topics.
 
-    Additionally, this Stack Overflow question suggests that Apache POI does work in a Neo4j User Defined Function. However, there may be an unknown glitch in the standalone UDF mentioned in the initial question.
 
-    To export data from Neo4j to Excel using APOC Extended procedures, you can use apoc.export.xls.query which takes a Cypher query and exports the results to an Excel file.
 
-    References:
+## A Case Study in RAG Implementation 
 
-    How to connect and query Neo4j Database on Apache Drill?
-    Is a Neo4j UDF compatible with Apache POI?
+### Teaching AI About New Technologies
 
+Apache NiFi serves as an excellent example of the limitations of traditional LLMs and how RAG can overcome them. As a relatively recent technology, many LLMs have limited or outdated knowledge about it, making it a perfect candidate for demonstrating RAG's capabilities.
 
+Without RAG, the LLM may provide broad responses or acknowledge its limited knowledge when asked about information that is beyond its cutoff date.
 
 
 ## Setting Up GenAI Stack with GPU Acceleration on Linux 
 
-To set up and run the GenAI stack on a Linux host with GPU acceleration, execute the following command:
+To set up and run the GenAI stack on a Linux host, execute the following command:
+
+### GPU powered
 
 ```bash
+git clone https://github.com/docker/genai-stack
 docker compose --profile linux-gpu up -d
+mv env.example .env
+nano .env
+```
+Make sure following lines are commented out. Set your own credentials for security
+
+    NEO4J_URI=neo4j://database:7687
+    NEO4J_USERNAME=neo4j
+    NEO4J_PASSWORD=password
+    OLLAMA_BASE_URL=http://llm-gpu:11434
+
+
+
+### CPU powered
+
+```bash
+git clone https://github.com/docker/genai-stack
+docker compose --profile linux up -d
+mv env.example .env
+nano .env
 ```
+Make sure following lines are commented out. Set your own credentials for security
+
+    NEO4J_URI=neo4j://database:7687
+    NEO4J_USERNAME=neo4j
+    NEO4J_PASSWORD=password
+    OLLAMA_BASE_URL=http://llm:11434
+
 
 ### Setting Up on Other Platforms 
 
 For instructions on how to set up the stack on other platforms, refer to [this page](https://github.com/docker/genai-stack). 
 
 ---
+### Initial Startup
 
-### Notes 
-
-- **Initial Startup**: The first startup may take some time because the system needs to download a large language model (LLM).
-- **Monitoring Progress**: We can monitor the download and initialization progress by viewing the logs.
+The first startup may take some time because the system needs to download a large language model (LLM).
 
-Run the following command to view the logs:
+### Monitoring Progress
+We can monitor the download and initialization progress by viewing the logs. Run the following command to view the logs:
 
 ```bash
 docker compose logs
@@ -153,19 +152,30 @@ Wait for specific lines in the logs indicating that the download is complete and
     You can now access the interface at [http://localhost:8501/](http://localhost:8501/) to ask questions. For example, you can try the sample question:
 
 
-    What is Apache Nifi? 
+When we see those lines in the logs, web apps are ready to be used.
+
+Since our goal is to teach AI about things it does not yet know, we begin by asking it a simple question about Nifi at 
+[http://localhost:8501/](http://localhost:8501/).
+![alt text](image.png)
+
 
+    Question: What is Apache Nifi? 
+    RAG: Disabled
+
+    Hello! I'm here to help you with your question about Apache NiFi. Unfortunately, I don't know the answer to that question. I'm just an AI and my knowledge cutoff is December 2022, so I may not be familiar with the latest technologies or software. Can you please provide more context or details about Apache NiFi? Maybe there's something I can help you with related to it.
 
-    The response should be similar to the following:
 
+As we can see, AI does not know anything about this subject because it did not exist during the time of its training, also known as the information cutoff point.
 
-    ... I'm just an AI and my knowledge cutoff is December 2022...
+Now it's time to teach the AI some new tricks. First, connect to [http://localhost:8502/](http://localhost:8502/). Instead of using the "neo4j" tag, change it to the "apache-nifi" tag, then click the **Import** button. 
 
 
-Now it's time to teach the AI some new tricks. First, connect to [loader-1](http://localhost:8502/). Instead of using the "neo4j" tag, change it to the "apache-nifi" tag, then click the **Import** button. After the import is successful, access Neo4j to verify the data.
+![alt text](image-1.png)
 
 
 
+After the import is successful, we can access Neo4j to verify the data. 
+
 After logging in to [http://localhost:7474/](http://localhost:7474/) using the credentials from the `.env` file, you can run queries on Neo4j. Using the Neo4j Cypher query language, you can check for the data stored in the database.
 
 To count the data, run the following query:
@@ -177,6 +187,11 @@ RETURN DISTINCT labels(n) AS NodeTypes, count(*) AS Count
 ORDER BY Count DESC;
 ```
 
+To execute this query, write in the box on the top and click the blue run button.
+
+![alt text](image-2.png)
+
+Results will appera below. What we are seeing here is the information system downloaded from Stack Overflow and saved in the graph database. RAG will utilize this information to enhance its responses.
 
 You can also run the following query to visualize the data:
 
@@ -190,8 +205,32 @@ To check the relationships in the database, run the following query:
 CALL db.relationshipTypes()
 ```
 
+
+
 Now, we are ready to enable our LLM to use this information. Go back to [http://localhost:8501/](http://localhost:8501/), enable the **RAG** checkbox, and ask the same question again. The LLM will now provide a more detailed answer.
 
+![alt text](image-3.png)
+
+The system delivers comprehensive, accurate information by pulling from current technical documentation.
+
+    Question: What is Apache Nifi? 
+    RAG: Enabled
+
+    Answer:
+
+    Apache NiFi is an open-source, distributed data processing system that allows you to collect, transform, and transport data across various sources and sinks. It provides a graphical user interface for designing and managing data flows, as well as a set of APIs for integrating with other systems.
+
+    According to this Stack Overflow question, the free Neo4J JDBC driver doesn't understand SQL, only Cypher, so you would need to use a non-free BI Connector to connect to Neo4j from Apache Drill.
+
+    Additionally, this Stack Overflow question suggests that Apache POI does work in a Neo4j User Defined Function. However, there may be an unknown glitch in the standalone UDF mentioned in the initial question.
+
+    To export data from Neo4j to Excel using APOC Extended procedures, you can use apoc.export.xls.query which takes a Cypher query and exports the results to an Excel file.
+
+    References:
+
+    How to connect and query Neo4j Database on Apache Drill?
+    Is a Neo4j UDF compatible with Apache POI?
+
 Keep in mind that new questions will be added to Stack Overflow, and due to the inherent randomness in most AI models, the answers may vary and won't be identical to those in this example.
 
 Feel free to start over with another [Stack Overflow tag](https://stackoverflow.com/tags). To drop all data in Neo4j, you can use the following command in the Neo4j Web UI:
@@ -204,3 +243,21 @@ DETACH DELETE n;
 
 For optimal results, choose a tag that the LLM is not familiar with.
 
+
+### When RAG is Effective 
+
+1. Knowledge Limitations:
+   - LLMs have fixed knowledge cutoffs
+   - Cannot access real-time or specialized information
+   - May hallucinate or provide outdated information
+
+2. Business Requirements:
+   - Need for accurate, up-to-date information
+   - Compliance and auditability
+   - Domain-specific knowledge integration
+
+3. Cost Efficiency:
+   - Reduced need for model fine-tuning
+   - Smaller models can perform well with good context
+   - Lower computational requirements
+