Modules

📄️ SMMF

Service-oriented Multi-model Management Framework(SMMF)

📄️ MS-RAG

Multi-Source Enhanced Retrieval-Augmented Generation Framework(MS-RAG)

📄️ Fine-Tuning

Text2SQL and Text2API(DSL) fine-tune to enhance model performance.

📄️ Evaluation

Model effect and framework performance evaluation.

The connections module supports connecting to various structured, semi-structured, and unstructured data storage engines. Bring multi-dimensional data into the framework and realize the interaction between natural language and multi-dimensional data

📄️ Visualization

DB-GPT provides rich visualization capabilities, which are developed independently as reusable modules in the GPT-Vis project

📄️ Ant Group Data Retrieval Benchmark Dataset Guide

For Text2SQL tasks, we provide a dataset benchmarking capability. It evaluates different large language models (LLMs) and agents on Text2SQL, covering syntax correctness, semantic accuracy, and execution validity. It outputs metrics such as executability rate and accuracy rate, and provides an evaluation report.