# API

## Parse PDF

### Create Synchronization Job

"Synchronization" mean that you can receive results immediately after a request is completed

{% hint style="info" %}
Replace `{{API_TOKEN}}` with your actual token.
{% endhint %}

**Example Request:**

{% tabs %}
{% tab title="Curl" %}

```bash
curl -X POST 'https://api.netmind.ai/inference-api/agent/v1/parse-pdf' \
--header 'Authorization: Bearer {{API_TOKEN}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "url": "https://netmind-public-files.s3.us-west-2.amazonaws.com/test.pdf",
    "format": "json"
}'
```

{% endtab %}

{% tab title="Python" %}

```python
import requests
import json

url = "https://test.api.netmind.ai/inference-api/agent/v1/parse-pdf"

payload = json.dumps({
   "url": "https://netmind-public-files.s3.us-west-2.amazonaws.com/test.pdf",
   "format": "json"
})
headers = {
   'Authorization': 'Bearer {{API_TOKEN}}',
   'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)

```

{% endtab %}
{% endtabs %}

**Example Response:**

```json
[
    {
        "id": "0eKSDqCl",
        "version": "1.0.1",
        "page": 1,
        "seq_no": 1,
        "sentence": "FABSA: An aspect-based sentiment analysis dataset of user reviews",
        "type": "title",
        "text_location": {
            "location": [
                [
                    37,
                    629,
                    427,
                    613
                ]
            ],
            "location_raw": [
                [
                    37,
                    164,
                    427,
                    180
                ]
            ]
        },
        "info": {}
    },
    ...
]
```

### Create Asynchronous Job

"Asynchronous"  mean that you need to obtain results through another request (Get Job)

{% hint style="info" %}
Replace `{{API_TOKEN}}` with your actual token.
{% endhint %}

**Example Request:**

{% tabs %}
{% tab title="Curl" %}

```bash
curl -X POST 'https://api.netmind.ai/inference-api/agent/v1/parse-pdf/async' \
--header 'Authorization: Bearer {{API_TOKEN}}' \
--header 'Content-Type: application/json' \
--data-raw '{
    "url": "https://netmind-public-files.s3.us-west-2.amazonaws.com/test.pdf",
    "format": "json"
}'
```

{% endtab %}

{% tab title="Python" %}

```python

import requests
import json

url = "https://api.netmind.ai/inference-api/agent/v1/parse-pdf/async"

payload = json.dumps({
   "url": "https://netmind-public-files.s3.us-west-2.amazonaws.com/test.pdf",
   "format": "json"
})
headers = {
   'Authorization': 'Bearer {{API_TOKEN}}',
   'Content-Type': 'application/json'
}

response = requests.request("POST", url, headers=headers, data=payload)

print(response.text)
```

{% endtab %}
{% endtabs %}

**Example Response:**

```json
{
    "task_id":"1a9e46e...2a9fb",
    "status":"PENDING"
}
```

### Get Job

{% hint style="info" %}
Replace `{{API_TOKEN}}` with your actual token.

Replace `{{TASK_ID}}` with "task\_id" you got from previous step.
{% endhint %}

**Example Request:**

{% tabs %}
{% tab title="Curl" %}

```bash
curl -X GET 'https://api.netmind.ai/inference-api/agent/v1/parse-pdf/async/{{TASK_ID}}' \
--header 'Authorization: Bearer {{API_TOKEN}}'
```

{% endtab %}

{% tab title="Python" %}

```python
import requests

url = "https://api.netmind.ai/inference-api/agent/v1/parse-pdf/async/{{TASK_ID}}"

payload={}
headers = {
   'Authorization': 'Bearer {{API_TOKEN}}'
}

response = requests.request("GET", url, headers=headers, data=payload)

print(response.text)
```

{% endtab %}
{% endtabs %}

**Example Response:**

```json
[
    {
        "id": "0eKSDqCl",
        "version": "1.0.1",
        "page": 1,
        "seq_no": 1,
        "sentence": "FABSA: An aspect-based sentiment analysis dataset of user reviews",
        "type": "title",
        "text_location": {
            "location": [
                [
                    37,
                    629,
                    427,
                    613
                ]
            ],
            "location_raw": [
                [
                    37,
                    164,
                    427,
                    180
                ]
            ]
        },
        "info": {}
    },
    ...
]
```


---

# 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://netmind-power.gitbook.io/netmind-power-documentation/~/changes/88/ai-services/api.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.