Support for Excel files (#1319)

tests/chunkers/test_chunkers.py

@@ -2,6 +2,7 @@ from embedchain.chunkers.common_chunker import CommonChunker
 from embedchain.chunkers.discourse import DiscourseChunker
 from embedchain.chunkers.docs_site import DocsSiteChunker
 from embedchain.chunkers.docx_file import DocxFileChunker
+from embedchain.chunkers.excel_file import ExcelFileChunker
 from embedchain.chunkers.gmail import GmailChunker
 from embedchain.chunkers.google_drive import GoogleDriveChunker
 from embedchain.chunkers.json import JSONChunker
@@ -43,6 +44,7 @@ chunker_common_config = {
     DiscourseChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
     CommonChunker: {"chunk_size": 2000, "chunk_overlap": 0, "length_function": len},
     GoogleDriveChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
+    ExcelFileChunker: {"chunk_size": 1000, "chunk_overlap": 0, "length_function": len},
 }
 
 

tests/loaders/test_excel_file.py

@@ -0,0 +1,33 @@
+import hashlib
+from unittest.mock import patch
+
+import pytest
+
+from embedchain.loaders.excel_file import ExcelFileLoader
+
+
+@pytest.fixture
+def excel_file_loader():
+    return ExcelFileLoader()
+
+
+def test_load_data(excel_file_loader):
+    mock_url = "mock_excel_file.xlsx"
+    expected_content = "Sample Excel Content"
+
+    # Mock the load_data method of the excel_file_loader instance
+    with patch.object(
+        excel_file_loader,
+        "load_data",
+        return_value={
+            "doc_id": hashlib.sha256((expected_content + mock_url).encode()).hexdigest(),
+            "data": [{"content": expected_content, "meta_data": {"url": mock_url}}],
+        },
+    ):
+        result = excel_file_loader.load_data(mock_url)
+
+    assert result["data"][0]["content"] == expected_content
+    assert result["data"][0]["meta_data"]["url"] == mock_url
+
+    expected_doc_id = hashlib.sha256((expected_content + mock_url).encode()).hexdigest()
+    assert result["doc_id"] == expected_doc_id