> AI agents: this is one page from PostHog's docs. Full index of Markdown docs for LLMs: https://posthog.com/llms.txt

# Linking LlamaCloud as a source

Canonical URL: https://posthog.com/docs/data-pipelines/sources/llama-cloud

> **Cloud region:** This page uses US Cloud hosts. For an EU Cloud project, use `https://eu.posthog.com` instead of `https://us.posthog.com` or `https://app.posthog.com` (app host for links).

## On this page

- [Prerequisites](#prerequisites)
- [Adding a data source](#adding-a-data-source)
- [Sync modes](#sync-modes)
- [Configuration](#configuration)
- [Supported tables](#supported-tables)
- [Troubleshooting](#troubleshooting)

![](https://res.cloudinary.com/dmukukwp6/image/upload/texture_tan_9608fcca70)

![](https://res.cloudinary.com/dmukukwp6/image/upload/texture_tan_dark_a92b0e022d)

Let AI connect your sources for you

Skip the manual setup — run this in your project and the wizard auto-detects your databases and APIs and connects them to PostHog.

`npx @posthog/wizard warehouse`

![PostHog Wizard hedgehog](https://res.cloudinary.com/dmukukwp6/image/upload/wizard_3f8bb7a240.png)

![](https://res.cloudinary.com/dmukukwp6/image/upload/wizard_3f8bb7a240.png)Let AI connect your sources for you

The LlamaCloud connector syncs your document-processing data from [LlamaCloud](https://cloud.llamaindex.ai) (LlamaIndex's hosted platform) – parse, extract, classify, split, and spreadsheet jobs, batches, pipelines, projects, files, and usage metrics with credit consumption – into PostHog, so you can analyze your document pipelines and AI costs alongside your product data.

## Prerequisites

You need a LlamaCloud account and an API key. Create one in [LlamaCloud](https://cloud.llamaindex.ai) under **Settings > API Keys**. API keys are scoped to a project and to the region they were created in (North America or Europe).

## Adding a data source

1.  In PostHog, go to the [Sources tab](https://app.posthog.com/data-management/sources) of the data pipeline section.
2.  Click **\+ New source** and click **Link** next to this source.
3.  Enter your credentials (see [Configuration](#configuration) below) and click **Next**.
4.  Select the tables you want to sync, choose a sync method and frequency, then click **Import**.

Once the syncs are complete, you can start querying this data in PostHog.

When linking LlamaCloud, you'll need:

-   **API key** – the key you created in LlamaCloud (starts with `llx-`).
-   **Region** – the region your API key was created in. A key only works against its own region's API, so a key from the wrong region fails validation.

## Sync modes

Each table can be synced in one of several modes, depending on what the source supports:

-   **Webhook** (when available) – the source pushes changes to PostHog in real time. Fastest freshness, lowest ongoing cost, and the only mode that reliably captures updates and deletes.
-   **Incremental** – only new or updated rows are synced on each run, using a cursor field (such as an `updated_at` timestamp). Cheaper than a full refresh, but deletes aren't captured.
-   **Append only** – new rows are appended using a cursor field; existing rows are never updated. Ideal for immutable, append-only tables like event logs.
-   **Full refresh** – the whole table is reloaded on every sync. Use it when a table has no reliable cursor or when you need deletions reflected.

See [sync methods](https://posthog.com/docs/data-pipelines/sources.md#sync-methods) for a full explanation of how each mode works and how to choose between them.

The job tables (`parse_jobs`, `extract_jobs`, `classify_jobs`, `batches`, `split_jobs`, `sheets_jobs`) support incremental sync on `created_at`. Each incremental sync also re-reads a trailing 24-hour window, so status changes to recently created jobs are picked up. Status changes to jobs created earlier than that are only reflected on a full refresh.

The `usage_metrics` table supports incremental sync on `day`, and re-reads the boundary day each sync so its still-accumulating totals stay up to date.

The `projects`, `pipelines`, and `files` tables don't expose a timestamp filter in the LlamaCloud API, so they sync with a full refresh.

## Configuration

| Option | Type | Required |
| --- | --- | --- |
| `API key` | password | Yes |
| `Region` | select | Yes |

## Supported tables

| Table | Description | Sync method | Incremental field | Primary key |
| --- | --- | --- | --- | --- |
| `parse_jobs` | Incremental syncs filter on created\_at, re-reading a trailing 24h window so recent status transitions are picked up; status changes to jobs created earlier than that are only reflected on a full refresh | Incremental, Full refresh | created\_at | — |
| `extract_jobs` | Incremental syncs filter on created\_at, re-reading a trailing 24h window so recent status transitions are picked up; status changes to jobs created earlier than that are only reflected on a full refresh | Incremental, Full refresh | created\_at | — |
| `classify_jobs` | Incremental syncs filter on created\_at, re-reading a trailing 24h window so recent status transitions are picked up; status changes to jobs created earlier than that are only reflected on a full refresh | Incremental, Full refresh | created\_at | — |
| `batches` | Incremental syncs filter on created\_at, re-reading a trailing 24h window so recent status transitions are picked up; status changes to jobs created earlier than that are only reflected on a full refresh | Incremental, Full refresh | created\_at | — |
| `split_jobs` | Incremental syncs filter on created\_at, re-reading a trailing 24h window so recent status transitions are picked up; status changes to jobs created earlier than that are only reflected on a full refresh | Incremental, Full refresh | created\_at | — |
| `sheets_jobs` | Incremental syncs filter on created\_at, re-reading a trailing 24h window so recent status transitions are picked up; status changes to jobs created earlier than that are only reflected on a full refresh | Incremental, Full refresh | created\_at | — |
| `projects` | LlamaCloud projects visible to the API key. | Full refresh | — | — |
| `pipelines` | Managed index pipelines that ingest, chunk, embed, and index documents for retrieval. | Full refresh | — | — |
| `files` | Files uploaded to LlamaCloud for parsing, extraction, or indexing. | Full refresh | — | — |
| `extraction_agents` | LlamaExtract extraction agents, one row per agent with the schema and settings it extracts with. | Full refresh | — | — |
| `extraction_runs` | LlamaExtract extraction runs, one row per run of an extraction agent with its status. The extracted data is not imported. | Full refresh | — | — |
| `indexes` | LlamaCloud indexes, one row per index with its source and output directories and sync state. | Full refresh | — | — |
| `usage_metrics` | Per-day usage and credit consumption aggregates | Incremental, Full refresh | day | — |

## Troubleshooting

If validation fails with an invalid API key error, check the **Region** setting first: LlamaCloud keys are region-specific, so a key created in the EU region is rejected by the North America API and vice versa.

If your sync is failing or data looks wrong, see the [Data warehouse troubleshooting guide](https://posthog.com/docs/data-warehouse/troubleshooting.md). If that doesn't help, [contact support](https://us.posthog.com/#panel=support%3Asupport%3Adata_warehouse%3A%3Atrue) – we're happy to help.