This project focuses on developing an AI-based Pre-Sales assistant that helps analyze Request for Proposal (RFP) documents and retrieve relevant information from internal knowledge sources. The system ingests documents in multiple formats, including PDF, DOCX, and PPTX, and extracts their textual content. The extracted text is processed and divided into smaller segments (chunks) with contextual metadata.

Each chunk is converted into a semantic embedding that represents its meaning in vector form. These embeddings enable efficient similarity search and retrieval of relevant information when users ask questions related to RFP requirements. The goal of the project is to improve the efficiency of pre-sales teams by automating document analysis and enabling faster access to relevant knowledge.