Platform For AI:RAG

Document

Description

• RAG-based LLM chatbot

This topic describes how to use Elastic Algorithm Service (EAS) to deploy the RAG services. The RAG architecture is designed for retrieval and generation.

• Retrieval: EAS integrates a range of vector databases, including open source Faiss and Alibaba Cloud services such as Milvus, Elasticsearch, Hologres, OpenSearch, and AnalyticDB for PostgreSQL.

• Generation: EAS supports various open source models such as Qwen, Meta Llama, Mistral, and Baichuan, and also integrates ChatGPT.

After you deploy an RAG service, you can call the RAG service by using the web UI or API operations. The web UI provides various inference parameters and allows you to upload knowledge base files to develop personalized and precise large language models (LLMs).

• Use EAS and Elasticsearch to deploy a RAG-based LLM chatbot

• Use EAS and OpenSearch to deploy a RAG-based LLM chatbot

• Use EAS and ApsaraDB RDS for PostgreSQL to deploy a RAG-based LLM chatbot

These topics describe how to associate vector databases with RAG services when you use EAS to deploy the RAG services. This topic also describes the basic features of RAG chatbots and the features of corresponding vector databases.