[全量] 初始化项目代码、配置、文档及Agent协同harness

langchain-chat/document_loaders/myimgloader.py

@@ -0,0 +1,26 @@
+from typing import List
+from langchain.document_loaders.unstructured import UnstructuredFileLoader
+from document_loaders.ocr import get_ocr
+
+
+class RapidOCRLoader(UnstructuredFileLoader):
+    def _get_elements(self) -> List:
+        def img2text(filepath):
+            resp = ""
+            ocr = get_ocr()
+            result, _ = ocr(filepath)
+            if result:
+                ocr_result = [line[1] for line in result]
+                resp += "\n".join(ocr_result)
+            return resp
+
+        text = img2text(self.file_path)
+        return text
+        # from unstructured.partition.text import partition_text
+        # return partition_text(text=text, **self.unstructured_kwargs)
+
+
+if __name__ == "__main__":
+    loader = RapidOCRLoader(file_path="../tests/samples/ocr_test.jpg")
+    docs = loader.load()
+    print(docs)