The Extract from Document smart service lets you integrate your AI skill into your process. This smart service takes a document as its input, uses pre-trained artificial intelligence models to analyze the data within the document, and then returns a map of the data it extracted based on the structure you defined in the skill.
The user who executes the process model doesn't need to have access to the AI skill being called by the Extract from Document smart service. However, without those permissions, some smart service configuration options are masked.
To properly view the results, you need to have permission to the document being analyzed.
The Setup tab allows you to select an AI skill.
| Name | Data Type | Description | Required | Multiple |
|---|---|---|---|---|
| Document | Document | File to extract data from. | Y | N |
| Is Structured Doc | Boolean | Set to true when fields to be extracted are in the same location for all documents. When you pass in structured documents and perform reconciliation, Appian Document Extraction learns to recognize this information based on its position, improving results for future extractions. | N | N |
The smart service returns a map of the data extracted from the document.
| Output | Data Type | Multiple | Description |
|---|---|---|---|
| Doc Extraction Id | String | N | The identifier of the AI skill execution, which can be used as input for the Reconcile Doc Extraction smart service. |
| Extracted Data | Any Type (Map) | N | Returns the extracted data in the form of the data structure defined in the AI Skill. |
Note: The Reconcile Doc Extraction smart service uses new inputs in 23.2. To adapt an older document extraction process to use the Extract from Document smart service, you'll need to remove the old Reconcile Doc Extraction smart service and replace it with the updated node to use the new inputs.
Activity chaining is not supported.
Appian is capable of processing PDF documents up to 15 pages or 7 MB. If a larger document is passed to the smart service, it will fail.
As you build your process, you'll map the smart service output to process variables. Appian supports casting data from Maps to CDTs or record types so you can use the extraction results to write to your database.
Note: Review the design guidance to ensure that the fields in your AI skill are named based on how you want to cast the data.
To ensure that the AI skill extracts and uses your data as you intend, carefully map the Extract from Document smart service output to the proper variables so your data is used or stored properly:
At run-time, the smart service calls the AI skill configured in the Setup tab.
Extraction is asynchronous and may take some time to complete.
The node will fail if the size of the document is too large. Send a document with 15 or fewer pages and 7 MB or less to the smart service.
If you see the following error, it is because the Extract from Document smart service is referring to an AI Skill design object that no longer exists. Reconfigure the smart service to use an existing AI Skill.
There is a problem with the task "Extract from Document" in the process "process_model_name". The underlying AI Skill object has been deleted or is otherwise invalid. Please confirm the node's configuration and try again.
