# GraphRAG Lifecycle in GraphAI

The GraphRAG component of GraphAI follows a continuous lifecycle to maintain an up-to-date and comprehensive knowledge graph:

1. **Data Ingestion**: Continuously indexing new blockchain data.
2. **Relationship Mapping**: Identifying and establishing connections between data points.
3. **Context Building**: Aggregating related information to provide a fuller picture of each entity or transaction.
4. **Query Optimization**: Utilizing the graph structure to enhance the speed and accuracy of complex queries.
5. **AI Model Integration**: Providing contextual information to AI models for improved understanding and decision-making.
6. **Feedback Loop**: Continuously refining the graph based on new data and AI model interactions.

This iterative process ensures that the knowledge graph remains a dynamic and valuable resource for AI-driven blockchain applications.

<figure><img src="/files/9WO04KSGBc9EvzTqDDC3" alt=""><figcaption></figcaption></figure>


---

# 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://graphai-1.gitbook.io/graphai/how-graphai-works/graphrag-lifecycle-in-graphai.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.