> For the complete documentation index, see [llms.txt](https://k-ai.gitbook.io/knowledge-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://k-ai.gitbook.io/knowledge-ai/sources-and-ingestion/sources-ingestion.md).

# Overview

Sources & ingestion is how documents enter the K-AI Platform. K-AI does not require centralising the document estate — it addresses sources where they live, ingests them incrementally, preserves their native ACLs, and indexes them into the Semantic Document Layer.

## What's in this section

* **Connectors** — supported source types, one sub-page per connector. SharePoint, Confluence, Notion, Google Drive, Azure Blob Storage, Snowflake Stage, ServiceNow, generic HTTP, and the web crawler are documented in the section navigation. Start with the [SharePoint connector](/knowledge-ai/sources-and-ingestion/connectors/sharepoint.md); the others follow the same shape.
* **Document state machine** — the lifecycle of a document from registration to indexed. See [Document state machine](/knowledge-ai/sources-and-ingestion/document-state-machine.md).
* **Indexation pipeline** — what runs between source and Semantic Document Layer. See [Indexation pipeline](/knowledge-ai/sources-and-ingestion/indexation-pipeline.md).
* **Instance API** — the machine-to-machine HTTP surface for indexation control. See [Instance API overview](/knowledge-ai/sources-and-ingestion/instance-api/instance-api.md).

## Architectural placement

This section covers Layers 1 (Sources) and 2 (Ingestion & Indexing) of the [5-layer architecture](/knowledge-ai/the-k-ai-platform/architecture.md). Layer 3 (Semantic Document Layer) is the [Neural Semantic Graph](/knowledge-ai/the-k-ai-platform/neural-semantic-graph.md). Layers 4 (Governance & Quality) and 5 (Exposure) are covered by [K-AI Audit](/knowledge-ai/k-ai-audit/audit.md) and [K-AI MCP](/knowledge-ai/k-ai-mcp/mcp.md) respectively.

## Auth

The Instance API uses `instance-id` + `api-key` headers — see [Authentication — Instance API keys](/knowledge-ai/authentication/api-keys.md).

## Next steps

1. Pick a connector (e.g. [SharePoint](/knowledge-ai/sources-and-ingestion/connectors/sharepoint.md)).
2. Start an indexation via the [Orchestrator endpoint](/knowledge-ai/sources-and-ingestion/instance-api/orchestrator.md).
3. Monitor progress in the [Documents endpoint](/knowledge-ai/sources-and-ingestion/instance-api/documents.md).


---

# 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://k-ai.gitbook.io/knowledge-ai/sources-and-ingestion/sources-ingestion.md?ask=<question>&goal=<endgoal>
```

`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.