Project Summary

• Develop and refine an AI Document Interpreter capable of reading, summarizing, and extracting key information from technical documents (datasheets, application notes, etc.).
• Implement a Component Adviser that provides component insights, propositions from the component database, and quick technical guidance for component selection.
• Build a Dashboard Database Generator to create statistics and dashboards for visualizing component attributes and trends.

Objectives & Purpose

• Elevate the component database user experience by integrating an intelligent engineering AI assistant that merges document understanding, recommendation, and visualization.
• Transform traditional component data into actionable intelligence to support faster and more informed design decisions.

Main Tasks / Work To Be Done

• Design and implement the AI Document Interpreter pipeline: ingestion, parsing, semantic extraction, and summarization for datasheets and application notes.
• Create the Component Adviser module to query the database, rank candidate components, and produce concise technical guidance for selection.
• Develop the Dashboard Database Generator to compute statistics, generate visual dashboards, and expose APIs or UI components for visualization.

Technical Stack & Keywords

• Expected technologies: Python, Generative AI (large language models / document understanding), data processing and ETL for component metadata.
• Domain focus: electronic engineering tools, electronic components, component databases, metadata extraction and analytics.

Expected Deliverables & Outcomes

• A working AI Document Interpreter capable of accurate extraction and summarization for typical technical documents used in component selection.
• A Component Adviser prototype integrated with the component database that returns ranked suggestions and short technical rationale.
• Dashboards and generated statistics showcasing component attributes, usage metrics, and comparison views to support engineer decisions.

Additional Notes

• The project is part of the PFE Book STTunis 2026 offerings and targets improving engineering workflows around electronic component selection and analysis.
• Emphasis on combining AI-driven document understanding with real-time recommendations and automated dashboard generation to make data actionable.