Tencent/WeKnora
WeKnora is an LLM-powered modular framework for deep document understanding, semantic retrieval, and context-aware question answering using the Retrieval-Augmented Generation paradigm.
Awesome AI Agents › Document Analytics Platforms
georgia-tech-db/evadb
EvaDB is an innovative database system designed specifically for AI-powered applications, enabling software developers to build AI apps with minimal code. It offers a powerful SQL API that simplifies the development of AI applications by allowing users to query both structured and unstructured data sources seamlessly. EvaDB supports a wide range of data sources including traditional relational databases like PostgreSQL, SQLite, MySQL, MariaDB, Clickhouse, and Snowflake, as well as unstructured data sources such as local filesystems and AWS S3 buckets. Additionally, it integrates with application data sources like GitHub. One of EvaDB's standout features is its ability to query connected data using pre-trained AI models from popular platforms such as Hugging Face, OpenAI, and YOLO. This includes a variety of AI tasks like audio classification, speech recognition, text classification, summarization, text generation, image classification, segmentation, object detection, and depth estimation. The system also supports advanced AI models including GPT-4 and YOLOv8 variants. EvaDB facilitates the creation and fine-tuning of AI models for regression, classification, and time series forecasting using frameworks like Ludwig, Sklearn, Xgboost, Statsforecast, and Neuralforecast. It incorporates AI-centric query optimizations such as caching, batching, parallel processing, and query predicate re-ordering to enhance performance and reduce costs associated with AI model execution. The project is open-source and actively maintained, with comprehensive documentation and community support available through Slack, Twitter, and Medium. EvaDB aims to democratize AI by enabling developers without deep AI expertise to leverage advanced AI capabilities within a familiar SQL environment, making it a versatile tool for a broad range of AI applications including generative AI, image recognition, and automated AI workflows.
https://github.com/georgia-tech-db/evadb
Also in Document Analytics Platforms
StarTrail-org/PixelRAG
Visual retrieval-augmented generation pipeline that renders web pages, PDFs and images to screenshot tiles and retrieves over them with a LoRA-tuned Qwen3-VL embedding model.
loggie-io/loggie
Loggie is a lightweight, cloud-native data transfer agent and aggregator designed for scalable, high-performance log collection, processing, and monitoring in Kubernetes environments.
johnsonhk88/AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction
A full-stack pipeline that parses bank statement PDFs with layout detection, OCR and LLMs, then runs CrewAI, LangChain Deep Agents and Hermes agent harnesses over the extracted data for categorisation, analysis and RAG querying.
netboxlabs/pktvisor
pktvisor is a dynamic network observability agent that analyzes high volume network traffic and generates opentelemetry metrics for real-time and centralized monitoring.
genomoncology/FuzzTypes
FuzzTypes is a Pydantic extension that provides autocorrecting annotation types for enhanced data validation and normalization, enabling automatic correction and structured data composition in Python applications.