feat: Add SpaCy Processor for Enhanced NLP Support in Quivr #3468
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
- Introduced SpaCyProcessor to handle various file formats (PDF, DOCX, TXT, CSV) - Supports recursive text splitting for chunked processing - Applies spaCy NLP pipeline for tokenization and entity recognition on file content
…sing - Added support for PDF, DOCX, TXT, and CSV file extraction using fitz (PyMuPDF) and python-docx. - Integrated spaCy NLP pipeline for entity recognition and sentence tokenization. - Configured RecursiveCharacterTextSplitter for document chunking with metadata (chunk size, entities, sentences). - Added error handling and logging for robust file processing and validation. - Improved support for asynchronous text extraction, enabling efficient file reading.
dosubot
bot
added
the
size:L
Sahil-2101
changed the title
|
Very nice PR! We'll take a closer look :) @AmineDiro |
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Outdated suggestions cannot be applied.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.
Description
This pull request introduces the SpaCyProcessor class to handle various text file types (PDF, DOCX, TXT, and CSV) and perform NLP processing using spaCy. This addition includes:
Key Features:
Motivation:
This feature adds support for spaCy NLP processing to enable richer text analysis and processing across various file types. The processor now efficiently handles different file formats, extracts meaningful text, and applies NLP, making it easier to work with structured document data in downstream applications.
Checklist before requesting a review
Please delete options that are not relevant.
Screenshots (if appropriate):