# Based on RAG Model

## Combination of AI Analysis Model and Real-time Data (Based on RAG Model)

Existing AI, especially LLM (Large Language Model), has the following problems:

* Generation of false information (Hallucination)
* Use of outdated information
* Analysis based on data with unclear sources

<div align="left"><figure><img src="/files/UDEJOxVZtTBa3MFnSXOd" alt="" width="16"><figcaption></figcaption></figure></div>

To solve this, Agendabook introduces a RAG (Retrieval-Augmented Generation) structure. This method works as follows:

* Agendabook collects panel survey response data in real-time
* Records this data on the blockchain to create a "verifiable trusted dataset"
* AI uses this blockchain-based real-time data as the basis (source) for analysis
* As a result, fact-based reliable insights can be derived

This structure preemptively verifies and guarantees data reliability based on blockchain in AI's analysis environment, simultaneously improving reliability, precision, and currency. Additionally, since all data sources are disclosed, it can secure transparency in data analysis, maximizing the advantages of blockchain.

<p align="center">Data forgery/falsification verification method</p>

<figure><img src="/files/7tpXmj9hShUAnHPOLFoB" alt=""><figcaption></figcaption></figure>

<p align="center"></p>

<figure><img src="/files/3CpMuPGmEbHh8MJAWaTd" alt=""><figcaption></figcaption></figure>

<p align="center"></p>

<p align="center">Verification by On-Chain (Etherscan)</p>

<figure><img src="/files/v0vy7uesPoHZMBPzPMxo" alt=""><figcaption></figcaption></figure>

<figure><img src="/files/JmAzMosnmn1Imwl0SQdH" alt=""><figcaption></figcaption></figure>

<p align="center"></p>


---

# Agent Instructions: 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:

```
GET https://baasid.gitbook.io/baasid-docs/whitepaper/services/based-on-rag-model.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.