feat: add method - detect format / data_type (#380)

embedchain/models/data_type.py

@@ -0,0 +1,13 @@
+from enum import Enum
+
+
+class DataType(Enum):
+    YOUTUBE_VIDEO = "youtube_video"
+    PDF_FILE = "pdf_file"
+    WEB_PAGE = "web_page"
+    SITEMAP = "sitemap"
+    DOCX = "docx"
+    DOCS_SITE = "docs_site"
+    TEXT = "text"
+    QNA_PAIR = "qna_pair"
+    NOTION = "notion"