> For the complete documentation index, see [llms.txt](https://docs.extracta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.extracta.ai/document-classification-api/api-endpoints-document-classification/1.-create-classification.md). # 1. Create classification `POST` `/documentClassification/createClassification` Initiates a new document classification process. This endpoint allows you to define a classification with a list of possible document types. Once created, you can use the returned `classificationId` to upload documents for type prediction. ## Server URL ``` https://api.extracta.ai/api/v1 ``` ## Headers | Name | Value | | ------------- | ------------------ | | Content-Type | `application/json` | | Authorization | `Bearer ` | ## Body
NameTypeRequiredDescription
namestringtrueA name for the classification.
descriptionstringfalseA description for the classification.
documentTypesobjecttrueAn array of objects, each specifying a document type.
## 💡 Need help defining `documentTypes`? Each item in the `documentTypes` array represents a document category used for classification (e.g., Invoice, Receipt). To learn how to properly define a document type — including required fields, keyword strategy, and optional data extraction linkage — refer to the [Document Types](/document-classification-api/classification-details/document-types.md) page. ## Body Example ```json { "classificationDetails": { "name": "Financial Document Classifier", "description": "Classifies uploaded documents into predefined financial document types.", "documentTypes": [ { "name": "Invoice", "description": "Standard commercial invoice from vendors or suppliers.", "uniqueWords": ["invoice number", "bill to", "total amount"], "extractionId": "invoiceExtractionId" }, { "name": "Purchase Order", "description": "Internal or external purchase order documents.", "uniqueWords": ["PO number", "item description", "quantity ordered"] }, { "name": "Receipt", "description": "Retail or online transaction receipts.", "uniqueWords": ["receipt", "paid", "transaction id"] } ] } } ``` ## Code Example {% tabs %} {% tab title="JavaScript" %} ```javascript const axios = require('axios'); async function createClassification(token, classificationDetails) { const url = "https://api.extracta.ai/api/v1/documentClassification/createClassification"; try { const response = await axios.post(url, { classificationDetails: classificationDetails }, { headers: { 'Content-Type': 'application/json', 'Authorization': `Bearer ${token}` } }); return response.data; } catch (error) { throw error.response ? error.response.data : new Error('An unknown error occurred'); } } async function main() { const token = 'apiKey'; const classificationDetails = { name: "Financial Documents Classifier", description: "Classifies invoices, receipts, and purchase orders.", documentTypes: [ { name: "Invoice", description: "Documents with billing and totals for payment.", uniqueWords: ["invoice number", "bill to", "total amount"], extractionId: "invoiceExtractionId" }, { name: "Receipt", description: "Confirmation of payment or transaction.", uniqueWords: ["receipt", "paid", "transaction id"] }, { name: "Purchase Order", description: "Authorizes a purchase transaction.", uniqueWords: ["PO number", "item", "quantity ordered"] } ] }; try { const response = await createClassification(token, classificationDetails); console.log("New Classification Created:", response); } catch (error) { console.error("Failed to create classification:", error); } } main(); ``` {% endtab %} {% tab title="Python" %} ```python import requests def create_classification(token, classification_details): url = "https://api.extracta.ai/api/v1/documentClassification/createClassification" headers = {"Content-Type": "application/json", "Authorization": f"Bearer {token}"} try: response = requests.post(url, json={"classificationDetails": classification_details}, headers=headers) response.raise_for_status() return response.json() except requests.RequestException as e: print(e) return None if __name__ == "__main__": token = "apiKey" classification_details = { "name": "Financial Documents Classifier", "description": "Classifies invoices, receipts, and purchase orders.", "documentTypes": [ { "name": "Invoice", "description": "Documents with billing and totals for payment.", "uniqueWords": ["invoice number", "bill to", "total amount"], "extractionId": "invoiceExtractionId" }, { "name": "Receipt", "description": "Confirmation of payment or transaction.", "uniqueWords": ["receipt", "paid", "transaction id"] }, { "name": "Purchase Order", "description": "Authorizes a purchase transaction.", "uniqueWords": ["PO number", "item", "quantity ordered"] } ] } response = create_classification(token, classification_details) print("New Classification Created:", response) ``` {% endtab %} {% tab title="PHP" %} ```php $classificationDetails]); // Set cURL options curl_setopt($ch, CURLOPT_POSTFIELDS, $payload); curl_setopt($ch, CURLOPT_HTTPHEADER, [ 'Content-Type: application/json', 'Authorization: Bearer ' . $token, ]); curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); curl_setopt($ch, CURLOPT_POST, 1); try { $response = curl_exec($ch); if (curl_errno($ch)) { throw new Exception('Curl error: ' . curl_error($ch)); } return $response; } catch (Exception $e) { return 'Error: ' . $e->getMessage(); } finally { curl_close($ch); } } // Example usage $token = 'apiKey'; $classificationDetails = [ "name" => "Financial Documents Classifier", "description" => "Classifies invoices, receipts, and purchase orders.", "documentTypes" => [ [ "name" => "Invoice", "description" => "Documents with billing and totals for payment.", "uniqueWords" => ["invoice number", "bill to", "total amount"], "extractionId" => "invoiceExtractionId" ], [ "name" => "Receipt", "description" => "Confirmation of payment or transaction.", "uniqueWords" => ["receipt", "paid", "transaction id"] ], [ "name" => "Purchase Order", "description" => "Authorizes a purchase transaction.", "uniqueWords" => ["PO number", "item", "quantity ordered"] ] ] ]; try { $response = createClassification($token, $classificationDetails); echo $response; } catch (Exception $e) { echo "Failed to create new classification: " . $e->getMessage(); } ?> ``` {% endtab %} {% endtabs %} ## Responses {% tabs %} {% tab title="200" %} ```json { "status": "created", "createdAt": 1712547789609, "classificationId": "classificationId" } ``` {% endtab %} {% tab title="400" %} ```json { "status": "error", "message": "Name is required" } ``` {% endtab %} {% tab title="500" %} ```json { "status": "error", "message": "Error creating classification" } ``` {% endtab %} {% endtabs %} --- # 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.extracta.ai/document-classification-api/api-endpoints-document-classification/1.-create-classification.md?ask=&goal= ``` `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.