Added documentation (#219)

embedchain/chunkers/base_chunker.py

@@ -3,6 +3,7 @@ import hashlib
 
 class BaseChunker:
     def __init__(self, text_splitter):
+        ''' Initialize the chunker. '''
         self.text_splitter = text_splitter
 
     def create_chunks(self, loader, src):

embedchain/chunkers/docx_file.py

@@ -14,6 +14,7 @@ TEXT_SPLITTER_CHUNK_PARAMS = {
 
 
 class DocxFileChunker(BaseChunker):
+    ''' Chunker for .docx file. '''
     def __init__(self, config: Optional[ChunkerConfig] = None):
         if config is None:
             config = TEXT_SPLITTER_CHUNK_PARAMS

embedchain/chunkers/pdf_file.py

@@ -13,6 +13,7 @@ TEXT_SPLITTER_CHUNK_PARAMS = {
 
 
 class PdfFileChunker(BaseChunker):
+    ''' Chunker for PDF file. '''
     def __init__(self, config: Optional[ChunkerConfig] = None):
         if config is None:
             config = TEXT_SPLITTER_CHUNK_PARAMS

embedchain/chunkers/qna_pair.py

@@ -13,6 +13,7 @@ TEXT_SPLITTER_CHUNK_PARAMS = {
 
 
 class QnaPairChunker(BaseChunker):
+    ''' Chunker for QnA pair. '''
     def __init__(self, config: Optional[ChunkerConfig] = None):
         if config is None:
             config = TEXT_SPLITTER_CHUNK_PARAMS

embedchain/chunkers/text.py

@@ -13,6 +13,7 @@ TEXT_SPLITTER_CHUNK_PARAMS = {
 
 
 class TextChunker(BaseChunker):
+    ''' Chunker for text. '''
     def __init__(self, config: Optional[ChunkerConfig] = None):
         if config is None:
             config = TEXT_SPLITTER_CHUNK_PARAMS

embedchain/chunkers/web_page.py

@@ -13,6 +13,7 @@ TEXT_SPLITTER_CHUNK_PARAMS = {
 
 
 class WebPageChunker(BaseChunker):
+    ''' Chunker for web page. '''
     def __init__(self, config: Optional[ChunkerConfig] = None):
         if config is None:
             config = TEXT_SPLITTER_CHUNK_PARAMS

embedchain/chunkers/youtube_video.py

@@ -13,6 +13,7 @@ TEXT_SPLITTER_CHUNK_PARAMS = {
 
 
 class YoutubeVideoChunker(BaseChunker):
+    ''' Chunker for Youtube video. '''
     def __init__(self, config: Optional[ChunkerConfig] = None):
         if config is None:
             config = TEXT_SPLITTER_CHUNK_PARAMS