🧑‍⚖️ Building a Saudi Labor Law AI Assistant — Bilingual, Semantic, and Context-Aware

The Saudi Labor Law is a complex and evolving legal framework. For HR teams, employers, and employees, understanding its details — from leave entitlements to termination rules — often means scrolling through dozens of pages, interpreting legal text, and trying to connect articles to real-world cases.

I wanted to change that.

So I built Saudi Labor Law AI Assistant — an intelligent, bilingual chatbot that answers legal questions instantly, explains relevant articles, and even analyzes employee-specific scenarios — all powered by vector search, LLMs, and semantic retrieval.

📌 Why This Project Matters

The challenges were clear:

⚠️ The official English translation of the law is outdated — the Arabic version is the authoritative reference.

📚 Searching manually across legal PDFs is slow and error-prone.

🧠 HR teams need contextual interpretations, not just raw text.

The solution? Combine document parsing, embeddings, vector databases, translation, and LLM reasoning into one end-to-end system that delivers article-backed, trustworthy answers in Arabic or English.

🧠 What the AI Assistant Can Do

Here’s what the system offers today:

💬 Ask legal questions in Arabic or English — answers come in the same language.

🧾 Analyze real employee cases — like leave eligibility, overtime pay, or termination compensation.

🔍 Retrieve the exact legal articles that support every answer.

🧑‍💼 Integrate employee data (age, salary, service years) into the reasoning process for personalized results.

🌐 Handle bilingual queries with automatic translation and context matching.

🔧 How It Works

The assistant is built on a robust NLP and retrieval pipeline:

📄 PDF Parsing – The official Arabic labor law is parsed with PyMuPDF, preserving RTL text and diacritics.

🔎 Structured Splitting – The document is split into parts, chapters, and articles with metadata.

🌐 Translation – Each article is translated to English using Helsinki-NLP/opus-mt-ar-en for bilingual support.

📊 Vectorization – Both Arabic and English texts are embedded using intfloat/multilingual-e5-base and stored in a Qdrant vector database.

🤖 Retrieval + Reasoning – A VectorIndexRetriever fetches the most relevant articles, which are then passed to GPT-4o-mini for grounded, human-readable answers.

📈 Hybrid Search Evaluation – After testing semantic and hybrid retrieval methods on 1,245 queries, hybrid search proved superior and is used by default.

🧑‍💼 Context-Aware Legal Reasoning

One of the most powerful features is employee-specific reasoning.

For example:

“Is this employee eligible for 30 days of annual leave if he has worked for 6 years?”

The chatbot uses employee metadata (service years, salary, leave days, etc.) to reason about the law in context, delivering precise, actionable answers — always citing the original legal article.

🖥️ Streamlit Interface

The frontend is built with Streamlit to make the experience intuitive and user-friendly:

🌍 Auto-detect Arabic or English queries.

📄 Optional employee data input.

🔍 Expandable references with similarity scores.

📚 Source tracing from Part → Chapter → Article.

🚀 Example in Action

Arabic Example:

👤: ما هي مدة الإجازة السنوية بعد خمس سنوات من الخدمة؟

🤖: يستحق العامل ثلاثين يوماً من الإجازة السنوية…

📖: استنادًا إلى المادة التاسعة بعد المائة

English Example:

👤: What are the sick leave entitlements for an employee?

🤖: The employee is entitled to paid sick leave for a specific duration…

📖: Based on Article 117 – Chapter Four

🧭 What’s Next

The project is just getting started. Planned enhancements include:

📑 PDF export of Q&A with references

🧮 HR calculators (end-of-service, overtime, vacation accrual)

🔊 Arabic voice interaction

📊 HR analytics dashboard

🧰 Tech Stack

💡 Saudi Labor Law AI Assistant is open-source and licensed under MIT. It’s built to make labor law understandable, accessible, and actionable — for HR teams, companies, and employees across Saudi Arabia.

🔗 Explore the Project

👉 GitHub Repository

I build This Project as Final Project Of learning LLm-ZoomCamp Course