new genai rag guide

[Expeto]

Description

Added a new guide about RAG with genAI which also explains how RAG actually work

Reviews

• Technical review
• Editorial review
• Product review

[netlify]

✅ Deploy Preview for docsdocker ready!

Name	Link
🔨 Latest commit	f3b1e44
🔍 Latest deploy log	https://app.netlify.com/sites/docsdocker/deploys/6782b4a42d23a0000873fbe8
😎 Deploy Preview	https://deploy-preview-21703--docsdocker.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify site configuration.

[dvdksn]

Thank you for your contribution! I appreciate your effort; RAG is an important
topic, and expanding our documentation on it can add significant value for our
readers. However, I think this guide could benefit from more focus and
refinement to align with the needs of our audience and complement our existing
materials. Here are my thoughts:

• The guide's purpose is unclear. It's important to define what this guide
  offers that the existing RAG guide does not. It seems like you want to focus
  on RAG with graph databases and Neo4j in particular. If the goal of the guide
  is to explore and demonstrate the benefits of this technology in particular,
  consider a way of doing that by example. E.g., by comparing this approach to
  using a vector database.
• Th structure and flow of the article feels fragmented and doesn't follow a
  logical progression. For instance, introducing graph databases before RAG
  seems out of place, especially for readers unfamiliar with the primary topic.
  Start with RAG and its benefits, then explain how graph databases fit into
  the picture.
• The "Case Study" section is disconnected from the rest of the content. I
  would suggest removing it. Or if you want to keep it, integrate it into a
  narrative that supports the guide.
• Several sections lack detail and direction. The technical instructions for
  setting up the stack are too sparse to be genuinely useful. I'm missing
  detailed, hands-on workflows and concrete examples that readers can follow
  and apply.

[Expeto]

@dvdksn I did the changes, can you take another look. Thanks.

[craig-osterhout]

Thanks @Expeto.
Added some style suggestions. Overall, it's looking good. The last section is a hard to make sense of, so I suggest elaborating more, or replace it with a summary of what was covered.

[craig-osterhout]

Already defined in the intro, so not necessary to define again.

Suggested change

	## Understanding RAG (Retrieval-Augmented Generation)
	## Understanding RAG

[craig-osterhout]

Already defined in the intro, so not necessary to define again.

Suggested change

	RAG (Retrieval-Augmented Generation) is a hybrid framework that enhances the capabilities of large language models by integrating information retrieval. It combines three core components:
	RAG is a hybrid framework that enhances the capabilities of large language models by integrating information retrieval. It combines three core components:

[craig-osterhout]

Suggested change

In a Retrieval-Augmented Generation (RAG) system, vector embeddings are used to represent the semantic meaning of text in a way that a machine can understand and process. For instance, the words "dog" and "puppy" will have similar embeddings because they share similar meanings. By integrating these embeddings into the RAG framework, the system can combine the generative power of large language models with the ability to pull in highly relevant, contextually-aware data from external sources.

In a RAG system, vector embeddings are used to represent the semantic meaning of text in a way that a machine can understand and process. For instance, the words "dog" and "puppy" will have similar embeddings because they share similar meanings. By integrating these embeddings into the RAG framework, the system can combine the generative power of large language models with the ability to pull in highly relevant, contextually-aware data from external sources.

[craig-osterhout]

Suggested change

	## Introduction to Graph Databases
	## Introduction to Graph databases

[craig-osterhout]

Suggested change

	## Practical Implementation: Testing RAG Effectiveness
	## Practical implementation: testing RAG effectiveness

[craig-osterhout]

Suggested change

	### Monitoring Progress
	### Monitoring progress

[craig-osterhout]

Style nit

Suggested change

	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 [http://localhost:8502/](http://localhost:8502/). Instead of using the "neo4j" tag, change it to the "apache-nifi" tag, then select the **Import** button.

[craig-osterhout]

Suggested change

	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.
	Results will appear 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.

[craig-osterhout]

Style nit

Suggested change

	To execute this query, write in the box on the top and click the blue run button.
	To execute this query, write in the box on the top and select the blue run button.

[craig-osterhout]

Suggest elaborating in this section or removing the section.