Merge pull request #69 from enoch3712/68-add-critical-tests-to-run-in…

…-actions

workflow and pytests added for critical run

.github/workflows/workflow.yml

@@ -23,8 +23,10 @@ jobs:
         pip install poetry
         poetry install
 
-    # - name: Run tests
-    #   run: poetry run pytest
+    - name: Run critical tests
+      env:
+        GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
+      run: poetry run pytest tests/critical/ -v
 
     - name: Build package
       run: poetry build

tests/critical/test_critical_classification.py

@@ -0,0 +1,45 @@
+import os
+import sys
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../..')))
+
+from dotenv import load_dotenv
+from extract_thinker import Process
+from extract_thinker.document_loader.document_loader_pypdf import DocumentLoaderPyPdf
+from extract_thinker.extractor import Extractor
+from extract_thinker.models.classification import Classification
+from tests.models.invoice import InvoiceContract
+from tests.models.driver_license import DriverLicense
+
+load_dotenv()
+CURRENT_DIR = os.path.dirname(os.path.abspath(__file__))
+INVOICE_PATH = os.path.join(CURRENT_DIR, '..', 'files', 'invoice.pdf')
+
+def test_critical_classification():
+    """Critical test for basic classification"""
+    # Setup
+    document_loader = DocumentLoaderPyPdf()
+    extractor = Extractor(document_loader)
+    extractor.load_llm("groq/llama-3.1-70b-versatile")
+
+    process = Process()
+    process.add_classify_extractor([[extractor]])
+
+    classifications = [
+        Classification(
+            name="Invoice",
+            description="This is an invoice document",
+            contract=InvoiceContract
+        ),
+        Classification(
+            name="Driver License",
+            description="This is a driver license document",
+            contract=DriverLicense
+        )
+    ]
+
+    # Act
+    result = process.classify(INVOICE_PATH, classifications)
+
+    # Assert
+    assert result is not None
+    assert result.name == "Invoice" 

tests/critical/test_critical_extraction.py

@@ -0,0 +1,27 @@
+import os
+import sys
+sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../..')))
+
+from dotenv import load_dotenv
+from extract_thinker import Extractor
+from extract_thinker.document_loader.document_loader_pypdf import DocumentLoaderPyPdf
+from tests.models.invoice import InvoiceContract
+
+load_dotenv()
+cwd = os.getcwd()
+
+def test_critical_extract_with_pypdf():
+    """Critical test for basic extraction functionality"""
+    test_file_path = os.path.join(cwd, "tests", "files", "invoice.pdf")
+
+    extractor = Extractor()
+    extractor.load_document_loader(DocumentLoaderPyPdf())
+    extractor.load_llm("groq/llama-3.1-70b-versatile")
+
+    result = extractor.extract(test_file_path, InvoiceContract)
+
+    assert result is not None
+    assert result.lines[0].description == "Consultation services"
+    assert result.lines[0].quantity == 3
+    assert result.lines[0].unit_price == 375
+    assert result.lines[0].amount == 1125