feat: changed doc_file to docx and update readme (#157)

embedchain/chunkers/docx_file.py

@@ -0,0 +1,16 @@
+from embedchain.chunkers.base_chunker import BaseChunker
+
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+
+
+TEXT_SPLITTER_CHUNK_PARAMS = {
+    "chunk_size": 1000,
+    "chunk_overlap": 0,
+    "length_function": len,
+}
+
+
+class DocxFileChunker(BaseChunker):
+    def __init__(self):
+        text_splitter = RecursiveCharacterTextSplitter(**TEXT_SPLITTER_CHUNK_PARAMS)
+        super().__init__(text_splitter)