Remove unneeded duplicate words

application/parser/file/html_parser.py

@@ -57,7 +57,7 @@ def parse_file(self, file: Path, errors: str = "ignore") -> Union[str, list[str]
         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 list starting 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
 

docs/pages/Guides/How-to-train-on-other-documentation.md

@@ -41,7 +41,7 @@ You can learn more about options while running ingest.py by running:
 `python ingest.py --help`
 |              Options             |                                                                                                                                |
 |:--------------------------------:|:------------------------------------------------------------------------------------------------------------------------------:|
-|            **ingest**            | Runs 'ingest' function converting documentation to to Faiss plus Index format                                                  |
+|            **ingest**            | Runs 'ingest' function converting documentation to Faiss plus Index format                                                  |
 | --dir TEXT                       | List of paths to directory for index creation. E.g. --dir inputs --dir inputs2 [default: inputs]                               |
 | --file TEXT                      | File paths to use (Optional; overrides directory) E.g. --files inputs/1.md --files inputs/2.md                                 |
 | --recursive / --no-recursive     | Whether to recursively search in subdirectories [default: recursive]                                                           |

scripts/parser/file/html_parser.py

@@ -57,7 +57,7 @@ def parse_file(self, file: Path, errors: str = "ignore") -> Union[str, list[str]
         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 list starting 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