> For the complete documentation index, see [llms.txt](https://tracdeepdive.gitbook.io/deepdive/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://tracdeepdive.gitbook.io/deepdive/overview/artificial-intelligence/chatgpt-vs-chatdkg.md).
# ChatGPT vs ChatDKG
The comparison between [**ChatGPT4** ](https://chat.openai.com/)by OpenAI and [**ChatDKG** ](https://world.origintrail.io/#chat)by OriginTrail sheds light on the performance of generative AI models in addressing specific queries. This head-to-head uses ChatGPT as an example but the same principles apply to other LLMs such has Google Gemini, Claude, Grok and so on.
When prompted with the question:
{% hint style="info" %}
"What was the composition of Nike's global corporate leadership in terms of gender in 2021?"
{% endhint %}
### ChatGPT response was characterized as vague, lengthy, and lacking in directness.
### Conversely, ChatDKG provided a concise and factually precise answer sourced from the OriginTrail Decentralized Knowledge Graph, ensuring verifiability and accuracy:
The framework facilitating this accuracy, termed Decentralized [**Retrieval-Augmented Generation**](https://research.ibm.com/blog/retrieval-augmented-generation-RAG) (RAG), allows AI models to access external knowledge bases for grounded responses. Meta introduced a similar concept in a 2020 [**paper** ](https://arxiv.org/abs/2005.11401v4)titled "Retrieval-Augmented Generation," aiming to expand LLMs' knowledge beyond training data.
{% hint style="success" %}
To enhance transparency, inclusivity and authenticity with ensured information provenance in RAG, OriginTrail DKG serves as a foundation for decentralized Internet, fostering more capable and precise, hallucinaton-proof AI solutions.
{% endhint %}
Returning to the query about Nike's corporate leadership composition, OriginTrail DKG traces the information lineage and facilitates further exploration by using the [**DKG Explorer**](https://dkg.origintrail.io/).
The answer provided by Decentralized RAG accurately reflects Nike's gender composition in 2021, sourced from the FY21 Nike, Inc. Impact Report accessible via the Wikirate open data platform providing open access to sustainability reports corporations publish annually.
OriginTrail DKG's utility extends beyond enterprise knowledge exchange, fostering trust and transparency across industries. As it evolves, OriginTrail aims to connect global knowledge repositories, driving precise and inclusive AI through Decentralized RAG.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://tracdeepdive.gitbook.io/deepdive/overview/artificial-intelligence/chatgpt-vs-chatdkg.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.