DataDoc

DataDoc is an AI-powered Business Intelligence and Document Intelligence platform built with Streamlit. It combines structured dataset analysis, AI-generated business insights, PDF document processing, semantic search, and Retrieval-Augmented Generation (RAG) into a single interactive workspace. The application supports both CSV-based business analysis and PDF-based document question answering.

For CSV datasets, DataDoc allows users to upload files, inspect dataset structure, analyze numerical and categorical features, identify missing values and duplicates, generate statistical summaries, and explore data through visualizations. It also automatically generates an executive summary, important trends, business risks, and actionable recommendations from uploaded datasets.

For PDF documents, DataDoc extracts content, splits documents into meaningful chunks, generates embeddings, and stores them in a vector database. Users can ask questions about uploaded documents and receive context-grounded answers with relevant page-level sources. The platform uses a multi-LLM fallback architecture: Google Gemini as the primary cloud LLM, Groq as the cloud fallback provider, and Ollama as a local fallback for development and local execution. It is deployed on Streamlit Community Cloud.