feat: create pdf parser with unstructured #8
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| import re | ||
| import pathlib | ||
|
|
||
| pdf_path = r"C:\Users\ADMIN\Desktop\KTHAIS\twiga-warehouse\data\parsed\text.md" |
There was a problem hiding this comment.
The path should be relative inside the project, so that every developer has its own absolute path
| ("#####", "Header 4"), # Bold + italic | ||
| ] | ||
|
|
||
| def preprocess_md(md_doc): |
There was a problem hiding this comment.
Can you type the input and the output? Example:
def foo(im_a_number: int) -> int:
return im_a_number + 1There was a problem hiding this comment.
same for other functions
Comment on lines
+39
to
+40
| chunk_size = 250 | ||
| chunk_overlap = 30 |
There was a problem hiding this comment.
Maybe it would be interesting to declare these two variables as input of the functions so that we could play with them if needed. Example:
def recursive_split(md_header_splits, chunk_size: int = 250, chunk_overlap: int = 30):
"""Split document recursively."""
...
Comment on lines
+50
to
+72
| md_doc = preprocess_md(md_doc) | ||
|
|
||
| # Split data | ||
| md_header_splits = md_split(md_doc) | ||
| #character_splits = recursive_split(md_header_splits) | ||
|
|
||
| # Append metadata | ||
| splits_data = [] | ||
| for split in md_header_splits: | ||
| splits_data.append({ | ||
| "content": split.page_content, | ||
| "metadata": split.metadata | ||
| }) | ||
|
|
||
| # Save JSON output | ||
| output_dir = pathlib.Path(r"C:\Users\ADMIN\Desktop\KTHAIS\twiga-warehouse\data\parsed") | ||
| output_dir.mkdir(exist_ok=True) | ||
|
|
||
| output_json_path = output_dir / "text.json" | ||
| with open(output_json_path, "w", encoding="utf-8") as json_file: | ||
| json.dump(splits_data, json_file, ensure_ascii=False, indent=4) | ||
|
|
||
| print(f"Markdown splits saved to {output_json_path}") |
There was a problem hiding this comment.
Can you move this inside a main function? This also implies creating the if __name__ == "__main__": famous line at the bottom of the file. Same for the other files
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #4 : Experimented with unstructuredloader for pdf parsing. Has element_id, parent_id and document type metadata which is very useful. Coordinate metadata could be used to find images. Can (somewhat) handle math formulas which may be relevant if/when we expand to other subjects.