Arabic-first grounded Q&A
TaLibAI answering an Arabic C++ question from indexed course material, with the interface showing the loaded retrieval pipeline and FAISS index state.
Arabic NLP / RAGComplete
TaLibAI
Answer Arabic and English study questions from course materials instead of relying on generic model memory.
Bilingual RAGManual FAISS pipelineLangChain refactorArabic normalizationRTL-aware retrievalOCR supportLocal Gemma path
Local project explainer
Ask about this system
A local, predefined assistant for the documented details in TaLibAI.
Problem
What this project had to solve
Students need answers grounded in their own lecture slides, textbooks, and handwritten notes, but bilingual Arabic-English retrieval is harder when OCR, RTL text, and mixed-language queries are involved.
Role / contribution
What I owned in the system
Project author responsible for both the manual RAG implementation and the later LangChain refactor, including retrieval design, Arabic normalization, OCR integration, and local-generation path selection.
Technical implementation
How the system is built
The repository includes a manual version built around direct FAISS retrieval, Arabic normalization, custom chunking, and explicit grounding mechanics.
A second version refactors the system with LangChain abstractions, hybrid retrieval, LCEL chains, and local Gemma generation through the documented local-first stack.
OCR support is included for scanned or handwritten notes, which keeps the system useful beyond born-digital PDFs.
Architecture flow
System flow from input to output
Step 01
Document ingestion
What happens
PDFs, slides, and handwritten notes enter through a loader or OCR path depending on source type.
Why it matters
The assistant only works on real study material if it can handle both clean digital inputs and scanned notes.
Related tools
Gemini Flash OCR
Engineering decisions
Tradeoffs that shaped the build
Build the system twice
Keeping both a manual pipeline and a framework refactor proves understanding of retrieval internals and higher-level abstractions.
Treat Arabic processing as a first-class concern
Normalization, RTL handling, and OCR support are system requirements, not cosmetic extras.
Support local generation paths
The repo's local-generation design keeps the project closer to a practical student assistant than an API-only demo.
Stack
Core tools and system layers
PythonFastAPIFAISSLangChainGemmaOllamaGemini Flash OCRStreamlit
What I would improve next
Next technical upgrades
- Add retrieval evaluation and citation-quality scoring to quantify answer grounding.
- Improve document lifecycle handling for updates, duplicates, and stale indices.
- Expose a cleaner service boundary for production-style API consumption.
Evidence
Grounded project proof
Honest out-of-scope response
TaLibAI responding conservatively when the indexed documents do not contain enough information to fully answer the question.