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
loggie-io/loggie
Loggie is a lightweight, high-performance, cloud-native data transfer agent and aggregator designed to facilitate scalable log data collection, processing, and transmission in Kubernetes environments. It supports multiple pipelines and pluggable components such as data transfer, filtering, parsing, and alerting, making it highly adaptable for various production needs. Loggie leverages native Kubernetes Custom Resource Definitions (CRDs) for easy operation and management, allowing users to define data collection and processing pipelines through simple YAML configurations. This approach enables seamless integration and automation within Kubernetes clusters. The project supports multiple deployment architectures including Agent (via DaemonSet), Sidecar (auto-injection without manual template modification), and Aggregator (independent intermediate machine for data aggregation and processing). This flexibility allows Loggie to fit diverse infrastructure setups while maintaining a simple and intuitive internal design. Loggie emphasizes high performance, demonstrated by benchmarks showing superior CPU efficiency and transmission rates compared to Filebeat when sending logs to Kafka. It features adaptive sink concurrency, which dynamically adjusts data sending parallelism based on downstream server performance and upstream data flow, optimizing resource utilization and preventing bottlenecks. Beyond data transfer, Loggie offers lightweight streaming data analysis and monitoring capabilities. It supports real-time parsing and transformation of logs using various formats and conditional processing logic. Additionally, it provides detection, recognition, and alerting features to identify anomalies or issues in log data, with support for custom webhook integrations. Loggie also enables log data aggregation and metric calculation, allowing users to derive meaningful insights such as error rates, request counts, and data volume from logs. Observability is enhanced through configurable metrics and Grafana dashboards for monitoring Loggie's performance and troubleshooting data transmission issues. Overall, Loggie is a comprehensive cloud-native solution for efficient, scalable, and intelligent log data management in Kubernetes environments, combining ease of use, high performance, and advanced analytics.
https://github.com/loggie-io/loggie
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.
georgia-tech-db/evadb
EvaDB is an open-source database system that empowers developers to build AI-powered applications by integrating advanced AI models and optimizations within a SQL-based querying framework for both structured and unstructured data.
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.