### First-time DB-GPT Setup Workflow

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/cli-quickstart.md

Install the DB-GPT application and start the server. Follow the interactive wizard to choose a provider and enter API keys.

```bash
pip install dbgpt-app
dbgpt start
# Follow the wizard → choose provider → enter API key → server starts
```

--------------------------------

### Use Install Helper Script

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/quick-start.md

Execute the install helper script for interactive installation or to list available commands. This script simplifies the setup process.

```bash
uv run install_help.py install-cmd --interactive
```

```bash
uv run install_help.py list
```

--------------------------------

### Start DB-GPT from PyPI installation

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/README.md

Starts the DB-GPT server after installation via PyPI. The first run will initiate an interactive setup wizard for LLM provider and API key configuration.

```bash
dbgpt start
```

--------------------------------

### Install DB-GPT from Source

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/changelog/Released_V0.8.0.md

Install all packages with specified extras and then start the DB-GPT webserver with a specific configuration file.

```bash
uv sync --all-packages \
  --extra "base" \
  --extra "proxy_openai" \
  --extra "rag" \
  --extra "storage_chromadb" \
  --extra "dbgpts"

uv run dbgpt start webserver --config configs/dbgpt-proxy-openai.toml
```

--------------------------------

### Start DB-GPT server

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/README.md

Starts the DB-GPT web server after installation. Replace '<profile>' with the profile name you used during installation (e.g., 'openai', 'kimi', 'minimax').

```bash
cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --profile <profile>
```

--------------------------------

### Start DB-GPT Web Server with Options

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/cli-quickstart.md

Examples of starting the DB-GPT web server with various options, including specifying a profile, using non-interactive mode with an API key, using a specific config file, and running as a daemon.

```bash
# Interactive (first run) — wizard will guide you
dbgpt start

# Use an existing profile
dbgpt start web --profile openai

# Non-interactive with explicit API key
dbgpt start web --profile kimi --api-key sk-xxx --yes

# Use a specific config file
dbgpt start web --config /path/to/my-config.toml

# Run as a daemon
dbgpt start web --daemon
```

--------------------------------

### Install DB-GPT via Shell Script

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/changelog/Released_V0.8.0.md

Initialize the DB-GPT environment using a shell script, with an example for OpenAI API key configuration. Then, start the DB-GPT webserver.

```bash
# Using OpenAI as an example, quickly initialize the environment
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh \
  | OPENAI_API_KEY=sk-xxx bash -s -- --profile openai

# Start DB-GPT
cd ~/.dbgpt/DB-GPT && uv run dbgpt start webserver --config ~/.dbgpt/configs/<profile>.toml
```

--------------------------------

### Run Interactive Install Helper

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/deploy/source-code.md

Use the interactive Python script to generate the correct `uv sync` command for your setup.

```bash
uv run install_help.py install-cmd --interactive
```

--------------------------------

### Setup Web Front-end

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/sourcecode.md

Installs npm dependencies and sets up environment variables for the web front-end. Remember to configure the API base URL.

```bash
cd web && npm install
cp .env.template .env
// Set API_BASE_URL to your DB-GPT server address, usually http://localhost:5670
npm run dev
```

--------------------------------

### Install DB-GPT with Extras

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/cli-quickstart.md

Install DB-GPT with specific extras for LLM providers, vector stores, RAG, and data sources. This example installs OpenAI, ChromaDB, RAG, and MySQL support.

```bash
# OpenAI + ChromaDB + RAG + MySQL
pip install "dbgpt-app[proxy_openai,storage_chromadb,rag,datasource_mysql]"
```

--------------------------------

### Start Model Controller (Server 1)

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/model_service/cluster_ha.md

Command to start the first model controller instance using a MySQL database for the registry. Ensure the database connection parameters are accurate for your setup.

```bash
dbgpt start controller \
--port 8000 \
--registry_type database \
--registry_db_type mysql \
--registry_db_name dbgpt \
--registry_db_host 127.0.0.1 \
--registry_db_port 3306 \
--registry_db_user root \
--registry_db_password aa123456
```

--------------------------------

### Install DB-GPT using the one-line script (macOS & Linux)

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/README.md

This command downloads and executes the installation script for DB-GPT. It's a quick way to get started on compatible systems.

```bash
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh | bash
```

--------------------------------

### Get Help with DB-GPT Installation

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/quickstart.md

Use this command to access the help information for the DB-GPT installation script, which can assist with various installation-related tasks.

```bash
uv run install_help.py --help
```

--------------------------------

### Development Environment Setup - Bash

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/data_analysis_planning_agent.md

Commands for setting up the development environment, including installing dependencies, running tests, and formatting code using black.

```bash
# 安装依赖
pip install -r requirements.txt

# 运行测试
pytest tests/

# 代码格式化
black src/
```

--------------------------------

### DB-GPT Configuration Example (TOML)

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/blog/2025-03-24-dbgpt-v0.7.0-release.md

Illustrates the new TOML configuration format for DB-GPT, covering system, service, RAG storage, and model settings. Use this for quick setup.

```toml
[system]
# Load language from environment variable(It is set by the hook)
language = "${env:DBGPT_LANG:-zh}"
api_keys = []
encrypt_key = "your_secret_key"

# Server Configurations
[service.web]
host = "0.0.0.0"
port = 5670

[service.web.database]
type = "sqlite"
path = "pilot/meta_data/dbgpt.db"
[service.model.worker]
host = "127.0.0.1"

[rag.storage]
[rag.storage.vector]
type = "chroma"
persist_path = "pilot/data"

# Model Configurations
[models]
[[models.llms]]
name = "deepseek-reasoner"
# name = "deepseek-chat"
provider = "proxy/deepseek"
api_key = "your_deepseek_api_key"

```

--------------------------------

### Install DB-GPT via PyPI

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/changelog/Released_V0.8.0.md

Install the dbgpt-app package using pip and then start DB-GPT.

```bash
# Step 1: Install dbgpt-app
pip install dbgpt-app

# Step 2: Start DB-GPT
dbgpt start
```

--------------------------------

### Setup DB-GPT Profile

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/cli-quickstart.md

Run the setup command to create a new profile if no configuration file is found.

```bash
dbgpt setup
```

--------------------------------

### DB-GPT Command Overview

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/cli-quickstart.md

Displays the available commands and options for the DB-GPT CLI, including start, stop, setup, profile, knowledge, model, and db management.

```bash
dbgpt [OPTIONS] COMMAND [ARGS]...

Options:
  --log-level TEXT   Log level (default: warn)
  --version          Show version and exit
  --help             Show help message

Commands:
  start     Start the DB-GPT server
  stop      Stop a running server
  setup     Configure LLM provider (interactive wizard or CI mode)
  profile   Manage configuration profiles
  knowledge Knowledge base operations
  model     Manage model serving
  db        Database management and migration
  ...
```

--------------------------------

### List Available Installation Modes

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/build_image.md

Lists all available installation modes and their configurations for the DB-GPT Docker build script.

```bash
bash docker/base/build_image.sh --list-modes
```

--------------------------------

### Install DB-GPT via PyPI (recommended with uv)

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/README.md

Installs the DB-GPT application package using uv, a fast Python package installer. This method requires Python 3.10+.

```bash
# Recommended: use uv
uv pip install dbgpt-app
```

--------------------------------

### Show Help for `dbgpt start apiserver`

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/application/advanced_tutorial/cli.md

View the detailed options for starting the API server. This includes configuration for host, port, controller address, and logging.

```bash
~ dbgpt start apiserver --help
```

--------------------------------

### Review and run installation script

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/README.md

This sequence allows you to download the installation script, review its contents using 'less', and then execute it with a specified profile.

```bash
curl -fsSL https://raw.githubusercontent.com/eosphoros-ai/DB-GPT/main/scripts/install/install.sh -o install.sh
less install.sh
bash install.sh --profile openai
```

--------------------------------

### View dbgpt Start Command Help

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/model_service/cluster.md

This command displays help information specifically for the `dbgpt start` command, outlining the different server components that can be launched.

```shell
dbgpt start --help
```

--------------------------------

### Show Help for `dbgpt start`

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/application/advanced_tutorial/cli.md

This command displays the general help information for starting DB-GPT services. It lists available sub-commands for different server types.

```bash
~ dbgpt start --help
```

--------------------------------

### Install DB-GPT via PIP

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/overview.mdx

Install the DB-GPT package using pip for a quick setup on any platform. Consider using a mirror for faster downloads in China.

```shell
pip install dbgpt-app
```

```shell
pip install dbgpt-app -i https://pypi.tuna.tsinghua.edu.cn/simple
```

--------------------------------

### Setup Local Development Environment for AWEL DAG

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/awel/get_started.ipynb

Configures and starts a local development environment for running AWEL DAGs without needing to start the full DB-GPT server. This is useful for debugging.

```python
if __name__ == "__main__":
    if dag.leaf_nodes[0].dev_mode:
        # Development mode, you can run the dag locally for debugging.
        from dbgpt.core.awel import setup_dev_environment

        setup_dev_environment([dag], port=5555)
    else:
        # Production mode, DB-GPT will automatically load and execute the current file after startup.
        pass
```

--------------------------------

### Install Dependencies for Proxy Multimodal Model

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/advanced_usage/multimodal.md

Installs packages required for a proxy multimodal model setup, including base, proxy integration, RAG, storage, DB-GPT, vision models, and S3 file handling.

```bash
uv sync --all-packages \
--extra "base" \
--extra "proxy_openai" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "dbgpts" \
--extra "model_vl" \
--extra "file_s3"
```

--------------------------------

### Start DB-GPT Web Server with Qwen Configuration

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/providers/qwen.md

Start the DB-GPT web server using the specified configuration file that includes Qwen model settings.

```bash
uv run dbgpt start webserver --config configs/dbgpt-proxy-tongyi.toml
```

--------------------------------

### Start DB-GPT Webserver with Qwen3 Configuration

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/blog/2025-04-29-db-gpt-qwen3-support.md

Command to start the DB-GPT webserver using the specified local Qwen3 configuration file. Access the interface at http://localhost:5670.

```bash
uv run dbgpt start webserver --config configs/dbgpt-local-qwen3.toml
```

--------------------------------

### Auto Search Agent Example

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/cookbook/agents/data_manus_application.md

This example shows how to use the WebSearchAgent to answer questions by leveraging web search capabilities. It reads Excel data, converts it to markdown, and then initiates a chat with the agent to get an answer.

```python
async def main():
    excel_file = your_directory_path
    filename_with_ext = os.path.basename(excel_file)
    # 读取Excel数据到变量
    headers, table_data = read_excel_headers_and_data(excel_file)
    mdstr = data2md(headers, table_data)

    llm_client = TongyiLLMClient(
        api_base=api_base,
        api_key=api_key,
        model=model
    )
    context: AgentContext = AgentContext(
        conv_id="test123", language="zh", temperature=0.5, max_new_tokens=2048
    )
    agent_memory = AgentMemory()
    agent_memory.gpts_memory.init(conv_id="test123")

    user_proxy = await UserProxyAgent().bind(agent_memory).bind(context).build()

    sql_boy = (
        await WebSearchAgent()
        .bind(context)
        .bind(LLMConfig(llm_client=llm_client))
        .bind(db_resource)
        .bind(agent_memory)
        .build()
    )

    await user_proxy.initiate_chat(
        recipient=sql_boy,
        reviewer=user_proxy,
        message=f"今年的中秋节是多久？"

```

--------------------------------

### Start Model Instances

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/application/advanced_tutorial/cli.md

The `dbgpt model start` command is used to deploy and start model instances. It supports various configuration options including model name, path, host, port, worker type, device, model type, prompt template, context size, GPU usage, memory limits, and quantization settings.

```bash
~ dbgpt model start  --help
Already connect 'dbgpt'
Usage: dbgpt model start [OPTIONS]

  Start model instances

Options:
  --model_name TEXT           The model name to deploy  [required]
  --model_path TEXT           The model path to deploy
  --host TEXT                 The remote host to deploy model  [default:
                              30.183.153.197]
  --port INTEGER              The remote port to deploy model  [default: 5000]
  --worker_type TEXT          Worker type  [default: llm]
  --device TEXT               Device to run model. If None, the device is
                              automatically determined
  --model_type TEXT           Model type: huggingface, llama.cpp, proxy and
                              vllm  [default: huggingface]
  --prompt_template TEXT      Prompt template. If None, the prompt template is
                              automatically determined from model path,
                              supported template: zero_shot,vicuna_v1.1,llama-
                              2,codellama,alpaca,baichuan-chat,internlm-chat
  --max_context_size INTEGER  Maximum context size  [default: 4096]
  --num_gpus INTEGER          The number of gpus you expect to use, if it is
                              empty, use all of them as much as possible
  --max_gpu_memory TEXT       The maximum memory limit of each GPU, only valid
                              in multi-GPU configuration
  --cpu_offloading            CPU offloading
  --load_8bit                 8-bit quantization
  --load_4bit                 4-bit quantization
  --quant_type TEXT           Quantization datatypes, `fp4` (four bit float)
                              and `nf4` (normal four bit float), only valid
                              when load_4bit=True  [default: nf4]
  --use_double_quant          Nested quantization, only valid when
                              load_4bit=True  [default: True]
  --compute_dtype TEXT        Model compute type
  --trust_remote_code         Trust remote code  [default: True]
  --verbose                   Show verbose output.
  --help                      Show this message and exit.
```

--------------------------------

### Alternative DB-GPT Webserver Startup

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/integrations/clickhouse_install.md

An alternative command to start the DB-GPT webserver, directly executing the Python script with the specified configuration file.

```bash
uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config configs/dbgpt-proxy-openai.toml
```

--------------------------------

### Run MCP SSE Server Gateway

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/blog/2025-03-24-dbgpt-v0.7.0-release.md

Starts the MCP SSE Server gateway for web scraping. Ensure Node.js is installed.

```bash
npx -y supergateway --stdio "uvx mcp-server-fetch"
```

--------------------------------

### Generated Prompts from Profile

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/agents/modules/profile/profile.md

Example of system and user prompts generated from a `ProfileConfig` object. These prompts are then passed to the LLM to guide its responses.

```text
System Prompt: 
You are a Summarizer, named Aristotle, your goal is Summarize answer summaries based on user questions from provided resource information or from historical conversation memories.. 
Please think step by step to achieve the goal. You can use the resources given below. 
At the same time, please strictly abide by the constraints and specifications in IMPORTANT REMINDER. 

*** IMPORTANT REMINDER ***
Please answer in English. 



##################################################
User Prompt: 

Question: What can you do?
```

--------------------------------

### Start dbgpt Webserver

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/application/advanced_tutorial/cli.md

Use this command to start the dbgpt webserver. It supports various options to configure the host, port, background execution, model controller, and logging.

```bash
~ dbgpt start webserver --help
```

--------------------------------

### Run Webserver with WenXin Config

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/advanced_usage/More_proxyllms.md

Start the dbgpt webserver using the configuration file for the Baidu WenXin proxy.

```bash
uv run dbgpt start webserver --config configs/dbgpt-proxy-wenxin.toml
```

--------------------------------

### Install Qwen (Tongyi) Dependencies with uv

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/advanced_usage/More_proxyllms.md

Install dependencies for the Aliyun Qwen (Tongyi) proxy using `uv sync`. This includes base, proxy_tongyi, rag, storage_chromadb, and dbgpts.

```bash
# Use uv to install dependencies needed for Aliyun Qwen (Tongyi) proxy
uv sync --all-packages \
--extra "base" \
--extra "proxy_tongyi" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "dbgpts"
```

--------------------------------

### Verify DAG with cURL (Server Running)

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/awel/get_started.ipynb

Example cURL command to test the deployed AWEL DAG by sending a GET request to the specified endpoint. Assumes the DB-GPT server is running.

```bash
% curl -X GET http://127.0.0.1:5000/api/v1/awel/trigger/examples/hello\?name\=zhangsan
"Hello, zhangsan, your age is 18"
```

--------------------------------

### Run DB-GPT Front-end Separately

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/web-ui/index.md

Instructions for running the Next.js front-end application independently for development purposes. This involves navigating to the web directory, installing dependencies, copying the environment template, setting the API base URL, and starting the development server.

```bash
cd web && npm install
cp .env.template .env
# Set API_BASE_URL=http://localhost:5670
npm run dev
```

--------------------------------

### Full Code Example for Chat Database

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/awel/cookbook/write_your_chat_database.md

This snippet shows the complete Python code for setting up a chat database application. It includes imports for AWEL components, data handling, LLM interaction, and vector store configuration. Ensure all necessary libraries are installed.

```python
import asyncio
import json
import shutil

import pandas as pd

from dbgpt.core import (
    ChatPromptTemplate,
    HumanPromptTemplate,
    SQLOutputParser,
    SystemPromptTemplate,
)
from dbgpt.core.awel import (
    DAG,
    BranchOperator,
    InputOperator,
    InputSource,
    JoinOperator,
    MapOperator,
    is_empty_data,
)
from dbgpt.core.operators import PromptBuilderOperator, RequestBuilderOperator
from dbgpt.datasource.operators import DatasourceOperator
from dbgpt_ext.datasource.rdbms.conn_sqlite import SQLiteTempConnector
from dbgpt.model.operators import LLMOperator
from dbgpt.model.proxy import OpenAILLMClient
from dbgpt_ext.rag import ChunkParameters
from dbgpt.rag.embedding import DefaultEmbeddingFactory
from dbgpt_ext.rag.operators.db_schema import DBSchemaAssemblerOperator, DBSchemaRetrieverOperator
from dbgpt_ext.storage.vector_store.chroma_store import ChromaVectorConfig, ChromaStore

# Delete old vector store directory(/tmp/awel_with_data_vector_store)
shutil.rmtree("/tmp/awel_with_data_vector_store", ignore_errors=True)

embeddings = DefaultEmbeddingFactory.openai()

# Here we use the openai LLM model, if you want to use other models, you can replace

```

--------------------------------

### Start DB-GPT Server with OpenAI Configuration

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/providers/openai.md

Start the DB-GPT web server using the specified OpenAI configuration file.

```bash
uv run dbgpt start webserver --config configs/dbgpt-proxy-openai.toml
```

--------------------------------

### Install uv Package Manager with pipx

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/CONTRIBUTING.md

Install or upgrade pip and pipx, then install the uv package manager using pipx. This is the recommended installation method.

```bash
python -m pip install --upgrade pip
python -m pip install --upgrade pipx
python -m pipx ensurepath
pipx install uv
```

--------------------------------

### Example: Search and Extract Information

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/skills/agent-browser/SKILL.md

A practical example demonstrating a search workflow: opening a search engine, filling the search query, submitting, waiting for results, and then extracting text and attributes from specific result elements.

```bash
agent-browser open https://www.google.com
agent-browser snapshot -i --json
# AI identifies search box @e1
agent-browser fill @e1 "AI agents"
agent-browser press Enter
agent-browser wait --load networkidle
agent-browser snapshot -i --json
# AI identifies result refs
agent-browser get text @e3 --json
agent-browser get attr @e4 "href" --json
```

--------------------------------

### Install Ollama on macOS

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/providers/ollama.md

Install Ollama on macOS using Homebrew. Ensure Ollama is installed and running before proceeding.

```bash
# Download from https://ollama.ai or use Homebrew:
brew install ollama
```

--------------------------------

### Install uv using pipx

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/prerequisites.md

Install or upgrade uv globally using pipx, a tool for installing Python applications.

```bash
python -m pip install --upgrade pip
python -m pip install --upgrade pipx
python -m pipx ensurepath
pipx install uv --global
```

--------------------------------

### Start DB-GPT Web Server

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/blog/2024-07-24-db-gpt-llama-3.1-support.md

Run this command to start the DB-GPT web server after configuring your .env file. You can then access the interface via your browser.

```bash
dbgpt start webserver
```

--------------------------------

### Run DB-GPT Webserver

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/sourcecode.md

Starts the DB-GPT webserver using a specified TOML configuration file. Ensure the config file path is correct.

```bash
uv run dbgpt start webserver --config configs/dbgpt-local-glm.toml
```

--------------------------------

### Install Dependencies with uv

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/sourcecode.md

Installs core dependencies and selected extensions for DB-GPT using uv sync. Ensure you have uv installed.

```bash
uv sync --all-packages \
--extra "base" \
--extra "cuda121" \
--extra "hf" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "quant_bnb" \
--extra "dbgpts"
```

--------------------------------

### Install AWEL Workflow

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/changelog/Released_V0.5.0.md

Use this command to install a specific AWEL workflow from the repository. Ensure DB-GPT is installed and deployed first.

```bash
dbgpt app install awel-flow-web-info-search
```

--------------------------------

### Install Financial Report App and Workflows

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/application/apps/chat_financial_report.md

Install the financial report app and its associated workflows using dbgpt. This includes the knowledge process pipeline and the financial robot chat app.

```bash
# install poetry
pip install poetry

# install financial report knowledge process pipeline workflow and financial-robot-app workflow
dbgpt app install financial-robot-app financial-report-knowledge-factory
```

--------------------------------

### Install Ollama Dependencies with uv

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/advanced_usage/ollama.md

Install necessary dependencies for the Ollama proxy using the uv package manager. Ensure you have uv installed.

```bash
# Use uv to install dependencies needed for Ollama proxy
uv sync --all-packages \
--extra "base" \
--extra "proxy_ollama" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "dbgpts"
```

--------------------------------

### dbgpt Webserver Options

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/application/advanced_tutorial/cli.md

Detailed options for starting the dbgpt webserver, including host, port, daemon mode, controller address, model name, sharing, remote embedding, logging, and tracing.

```bash
Usage: dbgpt start webserver [OPTIONS]

  Start webserver(dbgpt_server.py)

Options:
  --host TEXT                Webserver deploy host  [default: 0.0.0.0]
  --port INTEGER             Webserver deploy port  [default: 5000]
  --daemon                   Run Webserver in background
  --controller_addr TEXT     The Model controller address to connect. If None,
                             read model controller address from environment
                             key `MODEL_SERVER`.
  --model_name TEXT          The default model name to use. If None, read
                             model name from environment key `LLM_MODEL`.
  --share                    Whether to create a publicly shareable link for
                             the interface. Creates an SSH tunnel to make your
                             UI accessible from anywhere.
  --remote_embedding         Whether to enable remote embedding models. If it
                             is True, you need to start a embedding model
                             through `dbgpt start worker --worker_type
                             text2vec --model_name xxx --model_path xxx`
  --log_level TEXT           Logging level
  --light                    enable light mode
  --log_file TEXT            The filename to store log  [default:
                             dbgpt_webserver.log]
  --tracer_file TEXT         The filename to store tracer span records
                             [default: dbgpt_webserver_tracer.jsonl]
  --tracer_storage_cls TEXT  The storage class to storage tracer span records
  --disable_alembic_upgrade  Whether to disable alembic to initialize and
                             upgrade database metadata
  --help                     Show this message and exit.
```

--------------------------------

### Install CUDA Extra with uv

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/troubleshooting/installation.md

Install specific CUDA extras using `uv sync` to match your installed CUDA toolkit version.

```bash
# For CUDA 12.1
uv sync --all-packages --extra "cuda121" ...
```

```bash
# For CUDA 12.4
uv sync --all-packages --extra "cuda124" ...
```

--------------------------------

### Run Skill Agent Example

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/examples/agents/README_SKILL_AGENT.md

Execute the Python script to run the skill-enabled agent example. Ensure necessary environment variables for the local LLM client are set, or use a mock client for testing.

```bash
python examples/agents/skill_agent_example.py
```

--------------------------------

### Install Ollama on Linux

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/providers/ollama.md

Install Ollama on Linux by downloading and executing the official installation script. This command fetches and runs the script to set up Ollama.

```bash
curl -fsSL https://ollama.ai/install.sh | sh
```

--------------------------------

### Install AWEL Workflow

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/cookbook/app/data_analysis_app_develop.md

Use this command to install a specific AWEL workflow, such as 'awel-flow-web-info-search', into your local environment. After installation, refresh the interface to see the new workflow.

```bash
dbgpt app install awel-flow-web-info-search

> 
  Installing collected packages: awel-flow-web-info-search
  Successfully installed awel-flow-web-info-search-0.1.0
  Installed dbgpts at ~/.dbgpts/packages/ae442685cde998fe51eb565a23180544/awel-flow-web-info-search.
  dbgpts 'awel-flow-web-info-search' installed successfully.

```

--------------------------------

### Display Build Script Help

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/installation/build_image.md

Displays all available options and arguments for the DB-GPT Docker build script.

```bash
bash docker/base/build_image.sh --help
```

--------------------------------

### Install Agent Browser CLI

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/skills/agent-browser/SKILL.md

Installs the agent-browser CLI globally and downloads the Chromium browser. Use --with-deps on Linux to also install system dependencies.

```bash
npm install -g agent-browser
agent-browser install                     # Download Chromium
agent-browser install --with-deps         # Linux: + system deps
```

--------------------------------

### List Available Extras

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/docs/docs/getting-started/deploy/source-code.md

List all available extras that can be used with the `uv sync` command to customize dependency installation.

```bash
uv run install_help.py list
```

--------------------------------

### Install gettext on Fedora

Source: https://github.com/eosphoros-ai/db-gpt/blob/main/i18n/README.md

Installs the gettext package on Fedora systems.

```bash
sudo dnf install gettext
```