Computer Science Course Materials for Retrieval-Augmented Generation

Processed Computer Science and Engineering course materials from Ho Chi Minh City University of Technology, prepared for Retrieval-Augmented Generation systems. The dataset includes pre-built FAISS indices, processed documents, raw PDFs, and converted images, ready for educational RAG applications. It was created by author hatakekksheeshh and last updated in December 2025.

Use Cases

• Fine-tune a retrieval model using the pre-built FAISS indices to answer questions about Computer Science course content.
• Build a multimodal RAG system that queries processed course documents and associated converted images.
• Develop an educational assistant using the processed Computer Science and Engineering materials from HCMUT.

Strengths

• Includes pre-built FAISS indices, reducing setup time for RAG system development.
• Contains processed course documents, raw PDFs, and converted images, offering multiple data modalities.
• Last updated in December 2025, indicating recent maintenance.

Limitations

• Unknown row count, column structure, and total dataset size.
• Geographic scope is limited to course materials from a single Vietnamese university, Ho Chi Minh City University of Technology.
• Data quality and completeness of the processed documents and images are not specified.

Provenance

Source

Ho Chi Minh City University of Technology (HCMUT).

Collection Method

Processed Computer Science and Engineering course materials, including PDF conversion and index building.

Freshness

Last updated on 2025-12-16.

Geography

Vietnam (Ho Chi Minh City).