

Korvus
Overview :
Korvus is a search SDK built on Postgres, unifying the entire RAG (Retrieval Augmented Generation) process into a single database query. It offers high-performance, customizable search capabilities while minimizing infrastructure concerns. Korvus leverages PostgresML's pgml and pgvector extensions, compressing the RAG workflow within Postgres itself. It supports multi-language SDKs, including Python, JavaScript, Rust, and C, allowing developers to seamlessly integrate into existing technology stacks.
Target Users :
Korvus is designed for developers and data scientists who need efficient RAG (Retrieval Augmented Generation) operations at the database level, aiming to simplify search architecture and improve performance. Its multi-language support and open-source nature make it an ideal choice for technical teams, especially those already using Postgres as their data storage solution.
Use Cases
Use Korvus for fast retrieval and generation of large-scale text data.
Integrate into existing applications to achieve complex text processing and search functionalities through a single query.
Utilize Korvus for efficient data retrieval and model training in data analysis and machine learning projects.
Features
Postgres-Native RAG: Execute complex RAG operations directly within the database, eliminating the need for external services and API calls.
Single Query Efficiency: The entire RAG workflow, from embedding generation to text generation, is executed within a single SQL query.
Scalability and Performance: Built on Postgres, inheriting its excellent scalability and performance characteristics.
Simplified Architecture: Replace complex service-oriented architectures with a single, powerful query.
High Performance: Eliminate API calls and data movement for faster processing and higher reliability.
Open Source: Open-source software and models, providing a local Docker runtime experience.
Multi-Language Support: Supports multiple programming languages, including Python, JavaScript, and Rust.
Unified Pipeline: Combines embedding generation, vector search, reranking, and text generation within a single query.
How to Use
1. Set up a Postgres database and install the pgml and pgvector extensions.
2. Set the KORVUS_DATABASE_URL environment variable pointing to your database connection string.
3. Initialize Collection and Pipeline, configuring the required text processing and search models.
4. Insert documents into the Collection, providing data for search and generation operations.
5. Execute RAG queries, leveraging vector search and text generation to obtain desired results.
6. Adjust and optimize queries as needed, utilizing Postgres' query optimization capabilities.
Featured AI Tools
Chinese Picks

360AI Browser
The 360AI Browser is an integrated AI technology browser offering functions such as AI search, AI reading assistant, and AI video assistant. It aims to enhance users' online browsing and information acquisition efficiency through intelligent technology.
AI search engine
431.1K

Kimi Exploration Edition
Kimi Exploration Edition is an advanced deep reasoning AI search feature of Kimi. It interprets and breaks down problems, then searches and infers answers, allowing for thorough reading of 500 pages in a single search. This new feature enables Kimi to think like a human, providing more accurate and practical search results. It can also use mathematical models and programming to tackle complex issues, and engage in self-reflection when needed to optimize answers. In short, the Kimi Exploration Edition makes AI search smarter and closer to human cognitive processes.
AI search engine
409.9K