diff --git a/scripts/ingest.py b/scripts/ingest.py
index 2194a7cf..f41b86e7 100644
--- a/scripts/ingest.py
+++ b/scripts/ingest.py
@@ -37,7 +37,7 @@ def ingest(yes: bool = typer.Option(False, "-y", "--yes", prompt=False,
                                                    help="Maximum number of files to read."),
            formats: Optional[List[str]] = typer.Option([".rst", ".md"],
                                                    help="""List of required extensions (list with .)
-                                                        Currently supported: .rst, .md, .pdf, .docx, .csv, .epub"""),
+                                                        Currently supported: .rst, .md, .pdf, .docx, .csv, .epub, .html"""),
            exclude: Optional[bool] = typer.Option(True, help="Whether to exclude hidden files (dotfiles).")):
 
     """
diff --git a/scripts/parser/file/html_parser.py b/scripts/parser/file/html_parser.py
index c941dd78..12c01aef 100644
--- a/scripts/parser/file/html_parser.py
+++ b/scripts/parser/file/html_parser.py
@@ -16,8 +16,12 @@ class HTMLParser(BaseParser):
         """Init parser."""
         return {}
 
-    def parse_file(self, file: Path, errors: str = "ignore") -> str:
-        """Parse file."""
+    def parse_file(self, file: Path, errors: str = "ignore") -> Union[str, list[str]]:
+        """Parse file.
+
+            Returns:
+            Union[str, List[str]]: a string or a List of strings.
+        """
         try:
             import unstructured
         except ImportError:
@@ -26,48 +30,53 @@ class HTMLParser(BaseParser):
         from unstructured.staging.base import convert_to_isd
         from unstructured.cleaners.core import clean
 
+        # Using the unstructured library to convert the html to isd format
+        # isd sample : isd = [
+                            #   {"text": "My Title", "type": "Title"},
+                            #   {"text": "My Narrative", "type": "NarrativeText"}
+                            # ]
         with open(file, "r", encoding="utf-8") as fp:
             elements = partition_html(file=fp)
-            isd = convert_to_isd(elements)
+            isd = convert_to_isd(elements)  
 
-            # Removing non ascii charactwers from isd_el['text']
-            for isd_el in isd:
-                isd_el['text'] = isd_el['text'].encode("ascii", "ignore").decode()
+        # Removing non ascii charactwers from isd_el['text']
+        for isd_el in isd:
+            isd_el['text'] = isd_el['text'].encode("ascii", "ignore").decode()
 
-            # Removing all the \n characters from isd_el['text'] using regex and replace with single space
-            # Removing all the extra spaces  from isd_el['text'] using regex and replace with single space
-            for isd_el in isd:
-                isd_el['text'] = re.sub(r'\n', ' ', isd_el['text'], flags=re.MULTILINE|re.DOTALL)
-                isd_el['text'] = re.sub(r"\s{2,}"," ", isd_el['text'], flags=re.MULTILINE|re.DOTALL)
+        # Removing all the \n characters from isd_el['text'] using regex and replace with single space
+        # Removing all the extra spaces  from isd_el['text'] using regex and replace with single space
+        for isd_el in isd:
+            isd_el['text'] = re.sub(r'\n', ' ', isd_el['text'], flags=re.MULTILINE|re.DOTALL)
+            isd_el['text'] = re.sub(r"\s{2,}"," ", isd_el['text'], flags=re.MULTILINE|re.DOTALL)
 
-            # more cleaning: extra_whitespaces, dashes, bullets, trailing_punctuation
-            for isd_el in isd:
-                clean(isd_el['text'], extra_whitespace=True, dashes=True, bullets=True, trailing_punctuation=True )
+        # more cleaning: extra_whitespaces, dashes, bullets, trailing_punctuation
+        for isd_el in isd:
+            clean(isd_el['text'], extra_whitespace=True, dashes=True, bullets=True, trailing_punctuation=True )
 
-            # Creating a list of all the indexes of isd_el['type'] = 'Title'
-            title_indexes = [i for i,isd_el in enumerate(isd) if isd_el['type'] == 'Title']
+        # Creating a list of all the indexes of isd_el['type'] = 'Title'
+        title_indexes = [i for i,isd_el in enumerate(isd) if isd_el['type'] == 'Title']
 
-            # Creating 'Chunks' - List of lists of strings 
-            # each list starting with with isd_el['type'] = 'Title' and all the data till the next 'Title'
-            # Each Chunk can be thought of as an individual set of data, which can be sent to the model
+        # Creating 'Chunks' - List of lists of strings 
+        # each list starting with with isd_el['type'] = 'Title' and all the data till the next 'Title'
+        # Each Chunk can be thought of as an individual set of data, which can be sent to the model
+        # Where Each Title is grouped together with the data under it
 
-            Chunks = list(list())
+        Chunks = list(list())
+        final_chunks = list(list())
 
-            for i,isd_el in enumerate(isd):
-                if i in title_indexes:
-                    Chunks.append([])
-                Chunks[-1].append(isd_el['text'])
+        for i,isd_el in enumerate(isd):
+            if i in title_indexes:
+                Chunks.append([])
+            Chunks[-1].append(isd_el['text'])
 
-            print(Chunks)
-
-            # writing the chunks to a file
-            # with open('chunks.txt', 'w') as f:
-                # for chunk in Chunks:
-                    # f.write("%s \n" % chunk)
-
-
-        # # convert to isd ;Format : {'text': 'Navigation', 'type': 'Title'}         
-        # with open(file, "r", encoding="utf-8") as fp:
-        #     elements = partition_html(file=fp)
-        #     isd = convert_to_isd(elements)
-        #     print(isd)
\ No newline at end of file
+        # Removing all the chunks with sum of lenth of all the strings in the chunk < 25 #TODO: This value can be an user defined variable
+        for chunk in Chunks:
+            # sum of lenth of all the strings in the chunk
+            sum = 0
+            sum += len(str(chunk))
+            if sum < 25:
+                Chunks.remove(chunk)
+            else :         
+                # appending all the approved chunks to final_chunks as a single string       
+                final_chunks.append(" ".join([str(item) for item in chunk]))
+        return final_chunks