> For the complete documentation index, see [llms.txt](https://docs.waveline.ai/extract/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.waveline.ai/extract/examples/invoice-extraction.md).

# Invoice Extraction

Let's say we get a lot of invoices as a PDF. But for each invoice, we only want to extract the **first** and **last name** of the person that gets billed and the **total** amount to pay. 

<figure><img src="/files/sgXvURL4dvU48XdtdGl3" alt=""><figcaption></figcaption></figure>

{% file src="/files/9PAi7nLcsgQvbaqYhHa9" %}

Now let's construct a [Shape](/extract/types/shape.md) to extract those fields.&#x20;

```typescript
[
  {
    "name": "first_name",
    "type": "string",
    "description": "The first name of the one who receives the bill.",
    "isArray": false
  },
  {
    "name": "last_name",
    "type": "string",
    "description": "The last name of the one who receives the bill.",
    "isArray": false
  },
  {
    "name": "total",
    "type": "number",
    "description": "Total amount to pay",
    "isArray": false
  }
]
```

Once the shape is defined, we can call the [`/extract-document`](/extract/endpoints/extract-document.md) endpoint with it and the invoice PDF in the payload to create this job:

```bash
curl -X POST "https://waveline.ai/api/v1/extract-document" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -d '{
          "fileName": "invoice.pdf",
          "contentType": "application/pdf",
          "base64Content": "JVBERi0xLjMKMSAwIG9iago8PC9UeXBlL0NhdGF...",
          "shape": YOUR_SHAPE
        }'
```

We then process your call. Typically the job completion time lies between 10s and 3 minutes. From our request, we receive the following response:

```json
{
    "id": "a5ecc735-c48e-43ea-a739-d42bfb19edb3" 
    "status": "CREATED"; 
    "type": "extract"; 
    "result": null
    "urls": {
        "get": "https://waveline.ai/api/v1/jobs/a5ecc735-c48e-43ea-a739-d42bfb19edb3"; 
    }
}
```

With `urls["get"]` we can now query that job. This calls our [job](/extract/endpoints/jobs-id.md) endpoint with the correct `job_id` conveniently already pre-filled.\
If we call this URL 20s later when the job has finished, we get back the following:

```json
{
    "id": "a5ecc735-c48e-43ea-a739-d42bfb19edb3" 
    "status": "FINISHED"; 
    "type": "extract"; 
    "result": {
        "first_name": "Ben",
        "last_name": "Timond",
        "total": 330.75,
     },
    "urls": {
        "get": "https://waveline.ai/api/v1/jobs/a5ecc735-c48e-43ea-a739-d42bfb19edb3"; 
    }
}
```

In this response, we see the job status has changed to `FINISHED` and the `result` field now contains our requested information.


---

# 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://docs.waveline.ai/extract/examples/invoice-extraction.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.