Integrates AWS Bedrock's multimodal capabilities (Claude 3) into the Docling framework for generating image descriptions within document processing pipelines.

A serverless solution to streamline ESG compliance using AI-driven automation. Built with the AWS CDK (Python), Amazon Textract, Amazon Bedrock, and other AWS services to process and analyse compliance reports.

pRISM is a repository that combines Retrieval-Augmented Generation (RAG) with a multi-LLM voting approach to create accurate and reliable AI-generated outputs. It integrates multiple language models, including Mistral, Claude 3.5, and OpenAI, to enhance performance through advanced consensus techniques

【LLM infra】【文档处理】文档统一为pdf的服务端。支持高并发和不同复杂度业务场景下的解决方案，通常用于大模型开发中需要对文件格式进行转化的地方

AI-powered invoice processing system using Google Document AI - Automated AP workflows with CI/CD pipeline for enterprise finance operations

AI-powered system for summarizing PDF content with Armenian, Russian, and English language support. Automatically extracts and summarizes text, applies OCR to images, and identifies visual elements in documents. Built for efficient multilingual PDF processing.

An intelligent document processing system built with FastAPI + Streamlit, providing end-to-end document parsing, data cleaning, vectorization storage, and visual analytics for multi-format documents.

Distributed GCS-GCS multilingual PDF processing service built for horizontal scaling and concurrency, can be deployed using docker compose for voluminous processing

An AI-powered research assistant that analyzes academic papers and conducts literature reviews. Upload PDFs or search ArXiv papers by keywords to get intelligent summaries, key findings, and comparative analysis across research documents.

A sophisticated Python pipeline for automatically extracting dimensions and cabinet codes from architectural floorplan PDFs. This tool converts various dimension formats into standardized measurements and provides structured output with visualization capabilities.

MerchantPulse-Integrated Offline AI for modern finance. Convert statements, trades, and loan files into clean, validated data in seconds. Runs fully on your hardware—no cloud, no leaks. Built for credit analytics, risk, and compliance with speed and security at its core.

A fast, flexible API for extracting text from PDFs and images using smart file detection and OCR—perfect for automating your document workflows.

Customized LangChain Azure Document Intelligence loader for table extraction and summarization