# DB-GPT V0.6.0, Defining new standards for AI-native data applications.
## Introduction
DB-GPT is an open source AI native data application development framework with AWEL and agents. In the V0.6.0 version, we further provide flexible and scalable AI native data application management and development capabilities around large models, which can help enterprises quickly build and deploy intelligent AI data applications, and achieve enterprise digital transformation and business growth through intelligent data analysis, insights and decisions
### The V0.6.0 version mainly adds and enhances the following core features
- AWEL protocol upgrade 2.0, supporting more complex orchestration
- Supports the creation and lifecycle management of data applications, and supports multiple application construction modes, such as: multi-agent automatic planning mode, task flow orchestration mode, single agent mode, and native application mode
- GraphRAG supports graph community summary and hybrid retrieval, and the graph index cost is reduced by 50% compared to Microsoft GraphRAG.
- Supports multiple Agent Memories, such as perceptual memory, short-term memory, long-term memory, hybrid memory, etc.
- Supports intent recognition and prompt management, and newly added support for Text2NLU and Text2GQL fine-tuning
- GPT-Vis front-end visualization upgrade to support richer visualization charts
**AWEL protocol upgrade 2.0 supports more complex orchestration and optimizes front-end visualization and interaction capabilities.**
AWEL (Agentic Workflow Expression Language) is an agent-based workflow expression language designed specifically for large model application development, providing powerful functions and flexibility. Through the AWEL API, developers can focus on large model application logic development without having to pay attention to cumbersome model, environment and other details. In AWEL2.0, we support more complex orchestration and visualization
**Supports the creation and life cycle management of data applications, and supports multiple modes to build applications, such as: multi-agent automatic planning mode, task flow orchestration mode, single agent mode, and native application mode**
**GraphRAG supports graph community summarization and hybrid retrieval.**
The graph construction and retrieval performance have obvious advantages compared to community solutions, and it supports cool visualization. GraphRAG is an enhanced retrieval generation system based on knowledge graphs. Through the construction and retrieval of knowledge graphs, it further enhances the accuracy of retrieval and the stability of recall, while reducing the illusion of large models and enhancing the effects of domain applications. DB-GPT combines with TuGraph to build efficient retrieval enhancement generation capabilities
Based on the universal RAG framework launched in DB-GPT version 0.5.6 that integrates vector index, graph index, and full-text index, DB-GPT version 0.6.0 has enhanced the capabilities of graph index (GraphRAG) to support graph community summary and hybrid retrieval. ability. In the new version, we introduced TuGraph’s built-in Leiden community discovery algorithm, combined with large models to extract community subgraph summaries, and finally used similarity recall of community summaries to cope with generalized questioning scenarios, namely QFS (Query Focused Summarization). question. In addition, in the knowledge extraction stage, we upgraded the original triple extraction to graph extraction with point edge information summary, and optimized cross-text block associated information extraction through text block history to further enhance the information density of the knowledge graph.
Based on the above design, we used the open source knowledge graph corpus (OSGraph) provided by the TuGraph community and the product introduction materials of DB-GPT and TuGraph (about 43k tokens in total), and conducted comparative tests with Microsoft's GraphRAG system. Finally, DB-GPT It only consumes 50% of the token overhead and generates a knowledge graph of the same scale. And on the premise that the quality of the question and answer test is equivalent, the global search performance has been significantly improved.
For the final generated knowledge graph, we used AntV's G6 engine to upgrade the front-end rendering logic, which can intuitively preview the knowledge graph data and community segmentation results.
**Text2GQL and Text2NLU fine-tuning: Newly supports fine-tuning from natural language to graph language, as well as fine-tuning for semantic classification.**
This iteration is inseparable from the participation of developers and users in the community, and it also further cooperates with the [TuGraph](https://github.com/TuGraph-family) and [AntV](https://github.com/antvis) communities. Thanks to all the contributors who made this release possible!
Our version release information is maintained on GitHub. For more details, please visit [ReleaseNotes](https://github.com/eosphoros-ai/DB-GPT/releases)
"description": "The number of tables to retrieve from the database.",
"defaultValue": "10"
},
{
"name": "schema_max_tokens",
"type": "integer",
"required": false,
"description": "The maximum number of tokens to pass to the model, default 100 * 1024.Just work for the schema retrieval failed, and load all tables schema.",
"description": "The directory of the duckdb extensions.Duckdb will download the extensions from the internet if not provided.This configuration is used to tell duckdb where to find the extensions and avoid downloading. Note that the extensions are platform-specific and version-specific.",
"defaultValue": "[]"
},
{
"name": "force_install",
"type": "boolean",
"required": false,
"description": "Whether to force install the duckdb extensions. If True, the extensions will be installed even if they are already installed.",
"description": "The number of tables to retrieve from the database.",
"defaultValue": "10"
},
{
"name": "schema_max_tokens",
"type": "integer",
"required": false,
"description": "The maximum number of tokens to pass to the model, default 100 * 1024.Just work for the schema retrieval failed, and load all tables schema.",
"defaultValue": "102400"
},
{
"name": "max_num_results",
"type": "integer",
"required": false,
"description": "The maximum number of results to return from the query.",
"description": "The number of tables to retrieve from the database.",
"defaultValue": "10"
},
{
"name": "schema_max_tokens",
"type": "integer",
"required": false,
"description": "The maximum number of tokens to pass to the model, default 100 * 1024.Just work for the schema retrieval failed, and load all tables schema.",
"defaultValue": "102400"
},
{
"name": "max_num_results",
"type": "integer",
"required": false,
"description": "The maximum number of results to return from the query.",
"description": "Database password, you can write your password directly, of course, you can also use environment variables, such as ${env:DBGPT_DB_PASSWORD}",
description: "Columnar database for high-performance analytics and real-time queries."
---
import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail";
<ConfigDetail config={{
"name": "ClickhouseParameters",
"description": "Columnar database for high-performance analytics and real-time queries.",
"documentationUrl": null,
"parameters": [
{
"name": "host",
"type": "string",
"required": true,
"description": "Database host, e.g., localhost"
},
{
"name": "port",
"type": "integer",
"required": true,
"description": "Database port, e.g., 8123"
},
{
"name": "user",
"type": "string",
"required": true,
"description": "Database user to connect"
},
{
"name": "database",
"type": "string",
"required": true,
"description": "Database name"
},
{
"name": "engine",
"type": "string",
"required": false,
"description": "Storage engine, e.g., MergeTree",
"defaultValue": "MergeTree"
},
{
"name": "password",
"type": "string",
"required": false,
"description": "Database password, you can write your password directly, of course, you can also use environment variables, such as ${env:DBGPT_DB_PASSWORD}",
description: "A new-generation open-source real-time data warehouse."
---
import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail";
<ConfigDetail config={{
"name": "DorisParameters",
"description": "A new-generation open-source real-time data warehouse.",
"documentationUrl": null,
"parameters": [
{
"name": "host",
"type": "string",
"required": true,
"description": "Database host, e.g., localhost"
},
{
"name": "port",
"type": "integer",
"required": true,
"description": "Database port, e.g., 3306"
},
{
"name": "user",
"type": "string",
"required": true,
"description": "Database user to connect"
},
{
"name": "database",
"type": "string",
"required": true,
"description": "Database name"
},
{
"name": "driver",
"type": "string",
"required": false,
"description": "Driver name for Doris, default is doris.",
"defaultValue": "doris"
},
{
"name": "password",
"type": "string",
"required": false,
"description": "Database password, you can write your password directly, of course, you can also use environment variables, such as ${env:DBGPT_DB_PASSWORD}",
description: "Powerful, scalable, secure relational database system by Microsoft."
---
import { ConfigDetail } from "@site/src/components/mdx/ConfigDetail";
<ConfigDetail config={{
"name": "MSSQLParameters",
"description": "Powerful, scalable, secure relational database system by Microsoft.",
"documentationUrl": null,
"parameters": [
{
"name": "host",
"type": "string",
"required": true,
"description": "Database host, e.g., localhost"
},
{
"name": "port",
"type": "integer",
"required": true,
"description": "Database port, e.g., 3306"
},
{
"name": "user",
"type": "string",
"required": true,
"description": "Database user to connect"
},
{
"name": "database",
"type": "string",
"required": true,
"description": "Database name"
},
{
"name": "driver",
"type": "string",
"required": false,
"description": "Driver name for MSSQL, default is mssql+pymssql.",
"defaultValue": "mssql+pymssql"
},
{
"name": "password",
"type": "string",
"required": false,
"description": "Database password, you can write your password directly, of course, you can also use environment variables, such as ${env:DBGPT_DB_PASSWORD}",
