Commit cd4a2b

2025-11-13 10:17:26 Shilpa: updated the document
Projects/Audit-matic.md ..
@@ 40,12 40,6 @@
2. **Express.js Backend:**
* Receives the file and triggers the AI pipeline.
- 3. **Python AI Core:**
- * Uses PyMuPDF to extract text from documents.
- * Uses spaCy for NLP to detect Jira IDs and commit hashes.
- * Fetches relevant data via Jira and GitLab APIs.
- * Runs compliance checks (Traceability, Accountability, Completeness) via a rule-based expert system.
- * Returns a structured JSON report to the web app for display.
**What makes it innovative?**
@@ 55,7 49,7 @@
**AI/ML Models:** spaCy (NLP/NER), Custom Rule-Based Expert System
- **Frameworks & Libraries: **PyMuPDF, python-docx, jira, python-gitlab, multer
+ **Frameworks & Libraries: ** jira, multer
**Backend:** Express.js (Node.js)
@@ 81,7 75,7 @@
**Challenges**:
* Creating robust NLP patterns to handle document variations.
- * Ensuring smooth orchestration between React, Node.js, and Python.
+ * Ensuring smooth orchestration between React, Node.js.
* Handling API rate limits and error management for Jira and GitLab.
**Learnings:**
@@ 93,13 87,13 @@
**Short-term Goal: **Implement core compliance checks (Traceability, Accountability, Completeness) using regex-based entity recognition.
- **Medium-term Goal:** Train a custom NLP model with spaCy to recognize non-standard internal project identifiers for better accuracy.
+ **Medium-term Goal:** Train a custom NLP model to recognize non-standard internal project identifiers for better accuracy.
**Long-term Goal:** Use machine learning to automatically categorize different types of requirement documents (e.g., Test Plan, Risk Plan, Functional Spec) and apply different rule sets.
> ### **Repository & Live Demo**
- **GitHub Repository:** [Link to your code repo here]
+ **GitHub Repository:** https://gitlab.enovate-it.com/enovate/hackathon/audit-matic
**Live Demo:** [Link to live demo or video walkthrough here]
0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9