3 रिपॉजिटरी
Offloads intensive document ingestion and processing tasks to background workers to maintain system responsiveness.
Distinct from High-Performance Ingestion: Distinct from High-Performance Ingestion: focuses on the asynchronous execution pattern for background tasks rather than the throughput of the ingestion pipeline itself.
Explore 3 awesome GitHub repositories matching data & databases · Asynchronous Processing. Refine with filters or upvote what's useful.
Chonkie is a text chunking library designed for retrieval-augmented generation pipelines. It functions as a semantic text splitter and RAG ingestion pipeline, transforming raw text into embedded segments for storage in vector databases. The project distinguishes itself through specialized splitting strategies, including an AST-based code splitter for preserving logical boundaries in source code and a semantic text splitter that uses embedding models to determine boundaries based on meaning. It also provides a vector database ingestor to automate the generation of embeddings and their export t
Utilizes non-blocking asynchronous calls to handle high-throughput text ingestion and concurrent API requests.
This project is a web-based platform designed for retrieval-augmented generation, providing a conversational interface that connects language models to private document collections. It functions as a comprehensive system for managing enterprise knowledge bases, allowing users to query internal documents and receive context-aware, source-verified answers through a natural language chat interface. The platform distinguishes itself by integrating vector-based semantic search with modular knowledge base management, enabling the ingestion, segmentation, and indexing of documents into searchable em
Offloads document processing to asynchronous background workers to keep the interface responsive during intensive data operations.
This platform is a self-hosted knowledge management system designed for interacting with documents through natural language. It functions as a retrieval-augmented generation engine, allowing users to upload files and query them using large language models. The system provides a unified interface for document-based chat, ensuring that responses are grounded in the source material through specific citations. The platform distinguishes itself through a multi-tenant architecture that enforces strict data isolation between users and organizations. It features a flexible AI gateway that standardize
Offloads intensive document ingestion and processing tasks to background workers to maintain system responsiveness.