[全量] 初始化项目代码、配置、文档及Agent协同harness

langchain-chat/tests/document_loader/test_html.py

@@ -0,0 +1,10 @@
+data_path = './人工智能发展月报.html'
+from langchain_community.document_loaders import TextLoader
+
+loader = TextLoader(data_path)
+data = loader.load()
+print(data)
+
+from unstructured.partition.html import partition_html
+rst = partition_html(text=data[0].page_content)
+print("\n\n".join([str(el) for el in rst]))

langchain-chat/tests/document_loader/test_imgloader.py

@@ -0,0 +1,21 @@
+import sys
+from pathlib import Path
+
+root_path = Path(__file__).parent.parent.parent
+sys.path.append(str(root_path))
+from pprint import pprint
+
+test_files = {
+    "ocr_test.jpg": str(root_path / "tests" / "samples" / "ocr_test.jpg"),
+}
+
+def test_rapidocrloader():
+    img_path = test_files["ocr_test.jpg"]
+    from document_loaders import RapidOCRLoader
+
+    loader = RapidOCRLoader(img_path)
+    docs = loader.load()
+    pprint(docs)
+    assert isinstance(docs, list) and len(docs) > 0 and isinstance(docs[0].page_content, str)
+
+

langchain-chat/tests/document_loader/test_pdfloader.py

@@ -0,0 +1,21 @@
+import sys
+from pathlib import Path
+
+root_path = Path(__file__).parent.parent.parent
+sys.path.append(str(root_path))
+from pprint import pprint
+
+test_files = {
+    "ocr_test.pdf": str(root_path / "tests" / "samples" / "ocr_test.pdf"),
+}
+
+def test_rapidocrpdfloader():
+    pdf_path = test_files["ocr_test.pdf"]
+    from document_loaders import RapidOCRPDFLoader
+
+    loader = RapidOCRPDFLoader(pdf_path)
+    docs = loader.load()
+    pprint(docs)
+    assert isinstance(docs, list) and len(docs) > 0 and isinstance(docs[0].page_content, str)
+
+