> For the complete documentation index, see [llms.txt](https://docs.openagrinet.global/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.openagrinet.global/technical/ai-layer/data-ingestion-pipeline.md).

# Data Ingestion Pipeline

The Data Ingestion Pipeline in OpenAgriNet (OAN) is responsible for preparing agricultural knowledge and programme information so that it can be reliably retrieved during AI-driven user interactions. It converts raw source content from institutions such as agricultural universities, government departments, and programme teams into structured, searchable formats that can be consumed by the retrieval layer.

Unlike runtime query processing, which operates in real time for every user interaction, the data ingestion pipeline operates offline as part of system setup and periodic content updates. Its primary objective is to ensure that all knowledge made available through the AI layer is accurate, authorised, traceable, and optimised for retrieval.

The ingestion pipeline is also designed to be deployment-agnostic and reusable across states and programmes. New content sources can be onboarded using the same ingestion utilities and schema, without requiring changes to the AI orchestration or retrieval architecture. This enables rapid expansion of OAN deployments while maintaining consistency in data quality and retrieval performance.

All content processed through the ingestion pipeline is indexed with source metadata, enabling traceability and auditability of responses generated by the AI layer. At runtime, the AI module does not directly access raw documents; instead, it retrieves pre-ingested and validated content through the retrieval layer, ensuring predictable performance and grounded responses.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.openagrinet.global/technical/ai-layer/data-ingestion-pipeline.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
