[Feature]: Unstructured File Loader Support - USF (#815)

embedchain/loaders/unstructured_file.py

@@ -0,0 +1,40 @@
+import hashlib
+
+try:
+    from langchain.document_loaders import UnstructuredFileLoader
+except ImportError:
+    raise ImportError(
+        'PDF File requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
+    ) from None
+from embedchain.helper.json_serializable import register_deserializable
+from embedchain.loaders.base_loader import BaseLoader
+from embedchain.utils import clean_string
+
+
+@register_deserializable
+class UnstructuredLoader(BaseLoader):
+    def load_data(self, url):
+        """Load data from a Unstructured file."""
+        loader = UnstructuredFileLoader(url)
+        data = []
+        all_content = []
+        pages = loader.load_and_split()
+        if not len(pages):
+            raise ValueError("No data found")
+        for page in pages:
+            content = page.page_content
+            content = clean_string(content)
+            meta_data = page.metadata
+            meta_data["url"] = url
+            data.append(
+                {
+                    "content": content,
+                    "meta_data": meta_data,
+                }
+            )
+            all_content.append(content)
+        doc_id = hashlib.sha256((" ".join(all_content) + url).encode()).hexdigest()
+        return {
+            "doc_id": doc_id,
+            "data": data,
+        }