Agent Tool Configuration
This page is specifically designed for administrators (DevOps, IT, MLOps, or platform engineers) who deploy, manage, or secure h2oGPTe in production or enterprise environments.
This page provides integration details, configuration parameters, and requirements for all built-in agent tools available in Enterprise h2oGPTe.
Here you'll find:
- Tool-by-tool configuration variables and deployment requirements
- Default and optional settings, including cloud services and external API keys
- Hardware and dependency notes (e.g., GPU requirements, tokens/credentials needed)
- Best practices for enabling or restricting tools based on your organization's compliance, security, or data-access policies
Before onboarding end users or exposing agent capabilities, review this guide to ensure your environment is correctly configured and all necessary prerequisitesβsuch as external integrations, cloud credentials, or on-prem servicesβare in place.
Tool requirementsβ
Enterprise h2oGPTe includes multiple agent tools, each with specific requirements. Basic agent functionality is enabled by default, but many tools require additional configuration.
- Check the requirements for each tool you intend to use
- Configure the necessary environment variables in your deployment
- Ensure any required external services or credentials are set up properly
- Verify that hardware requirements (such as GPU for image generation) are met
- Replace all
<your-*-key>
placeholders with actual keys/tokens
This basic agent configuration enables several tools by default:
ALLOW_API: "1"
H2OGPT_OPENAI_LOG_PATH: /workspace/save/h2ogpt_openai/
TRANSFORMERS_CACHE: /workspace/.cache
Toolsβ
Data analysis capabilitiesβ
-
H2O Driverless AI Data Science: Build automated machine learning models and analyze data to generate actionable insights. This tool connects to H2O Driverless AI to run experiments, create predictions, and perform data analysis.
Configure the tool:β
- For DAI Cloud:
- For DAI on-premises:
ENABLE_DAI: "1"
DAI_INSTANCE_TYPE: cloud
DAI_CLIENT_ID: hac-platform-public
DAI_ENGINE: <your-dai-engine>
DAI_ENVIRONMENT: <your-dai-environment-url>
DAI_TOKEN: <your-dai-token>
DAI_TOKEN_ENDPOINT_URL: <your-token-endpoint-url>ENABLE_DAI: "1"
DAI_INSTANCE_TYPE: onprem
DAI_ADDRESS: <your-dai-address>
DAI_USERNAME: <your-username>
DAI_PASSWORD: <your-password>Configuration referenceβ
Parameter Type Deployment Type (Cloud/MC and On-Premises) Description ENABLE_DAI
String Both Set to "1"
to enable Driverless AI integrationDAI_INSTANCE_TYPE
String Both Specify "cloud"
or"onprem"
DAI_CLIENT_ID
String Cloud/MC Client ID for cloud instances. Default: hac-platform-public
DAI_ENGINE
String Cloud/MC Engine identifier for cloud deployments DAI_ENVIRONMENT
String Cloud/MC Cloud environment URL DAI_TOKEN
String Cloud/MC Authentication token for cloud access DAI_TOKEN_ENDPOINT_URL
String Cloud/MC Token endpoint URL for cloud authentication DAI_ADDRESS
String On-Premises Server address for on-premises installations DAI_USERNAME
String On-Premises Username for on-premises authentication DAI_PASSWORD
String On-Premises Password for on-premises authentication DAI_MAX_RUNTIME_MINUTES
(optional)Integer Both Maximum runtime limit for experiments in minutes (optional) How end users interact with the toolβ
Once configured, end users can interact with the H2O Driverless AI Data Science tool through natural language prompts. They don't need to write code directly. For example:
- "
Use Driverless AI to create a classification experiment with the Titanic dataset, targeting the 'Survived' column with accuracy setting 2
" - "
Run a regression experiment on my sales data with high interpretability
" - "
Create a DAI experiment with time setting 3 and accuracy setting 5
"
The agent will automatically invoke the underlying tool function:
# This code is executed automatically by the agent - not by end users
from api_server.agent_tools.driverless_ai_data_science import driverless_ai_data_science
driverless_ai_data_science(
data="titanic.csv",
dataset_name="titanic_test",
target_column="Survived",
task="classification",
experiment_name="titanic_test_experiment",
accuracy=2,
time=2,
interpretability=7
)Secure your credentialsβ
To securely access Driverless AI credentials:
- Navigate to Agents > Authentication in the Enterprise h2oGPTe UI.
- Create secure keys for DAI access.
- Assign the keys to the H2O Driverless AI Data Science tool.
Access the credentials in your code:
# Access credentials securely via environment variables
enable_dai = os.getenv("ENABLE_DAI")
dai_max_runtime = os.getenv("DAI_MAX_RUNTIME_MINUTES")Before you begin- Ensure your system has sufficient computational resources for experiments
- For cloud instances: Verify authentication tokens and network connectivity
- For on-premises: Confirm the Driverless AI (DAI) server is accessible from h2oGPTe
- Use
DAI_MAX_RUNTIME_MINUTES
to prevent long-running experiments
-
Python Coding: Execute Python code snippets for custom data computations, machine learning tasks, or to automate data preprocessing.
Requirements:β
- Enabled with basic agent configuration:
ALLOW_API: "1"
- Enabled with basic agent configuration:
-
Advanced Reasoning: Perform context-aware reasoning to enhance decision-making processes.
Requirements:β
-
Requires models that support reasoning capabilities.
-
Configure in Helm chart:
agent:
enabled: true
overrideConfig:
visible_reasoning_models:
- meta-llama/Llama-3.1-8B-Instruct
-
Information retrieval and researchβ
-
Scholar Papers Search: Locate scholarly papers, research articles, and academic content.
Requirements:β
- Requires the Internet Access tool to be enabled.
-
Google search: Access Google's search capabilities to gather timely and accurate information.
Requirements:β
- Requires the Internet Access tool to be enabled.
- Optional:
- Configure the Google API key:
GOOGLE_API_KEY: <your-google-api-key>
- Configure the Google API key:
-
Bing search: Access Bing's search capabilities to gather timely and accurate information.
Requirements:β
- Requires the Internet Access tool to be enabled.
- Optional:
- Configure the Bing API key:
BING_API_KEY: <your-bing-api-key>
- Configure the Bing API key:
-
Internet Access: Utilize general internet access for a wide range of tasks, from data retrieval to live updates.
Requirements:β
- Basic agent configuration:
ALLOW_API: "1"
- Basic agent configuration:
-
Wolfram|Alpha Math Science Search: Solve scientific and mathematical problems using the computational knowledge engine for complex computations.
Requirements:β
- Requires the Internet Access tool to be enabled.
- Optional:
- Configure the Wolfram|Alpha API key:
WOLFRAM_ALPHA_APPID: <your-wolfram-alpha-appid>
- Configure the Wolfram|Alpha API key:
-
Wikipedia Articles Search: Retrieve information from Wikipedia for learning or to support data analysis and research.
Requirements:β
- Requires the Internet Access tool to be enabled.
-
Wayback Machine Search: Access archived versions of websites for research, historical context, or to reference past web content.
Requirements:β
- Requires the Internet Access tool to be enabled.
-
Web Image Search: Find relevant images from the web to support visual analysis, presentations, or content creation.
Requirements:β
- Requires the Internet Access tool to be enabled.
-
Ask Question About Documents: Extract or query information from uploaded documents for detailed insights.
Requirements:β
- Basic agent configuration:
ALLOW_API: "1"
- Basic agent configuration:
Content generation and transformationβ
-
Image Generation: Create custom images based on textual descriptions. Integrate image generation capabilities from different providers, including local models, OpenAI, Azure OpenAI, and Black Forest Labs.
Requirements:β
- Requires GPU in agent pod.
- Shell Scripting tool must be enabled as a prerequisite.
- Configuration in Helm chart:
h2ogpt:
config:
externalLLM:
enabled: true
secret:
ALLOW_API: "1"
# Black Forest Labs Configuration
BFL_API_KEY: <your-black-forest-labs-api-key>
# OpenAI Configuration
IMAGEGEN_OPENAI_BASE_URL: https://api.openai.com/v1
IMAGEGEN_OPENAI_API_KEY: <your-openai-api-key>
# Azure OpenAI Configuration
AZURE_OPENAI_BASE_URL: openai.azure.com
AZURE_OPENAI_API_KEY: <your-azure-openai-api-key>
agent:
enabled: true
additionalConfig:
function_api_key: <your-function-api-key>
enforce_h2ogpt_api_key: false
enforce_h2ogpt_ui_key: false
enable_image: true
visible_image_models:
- "flux.1-schnell" # Local model for image generation
# Optional: Additional image generation models
# Uncomment and replace with actual model names when using external providers
# - "openai-model" # OpenAI model
# - "azure-model" # Azure model
-
Audio-Video Transcription: Convert spoken content from audio or video files into text.
Requirements:β
-
Basic agent configuration:
ALLOW_API: "1"
-
Optional:
- Configure the OpenAI base URL and API key for STT:
STT_OPENAI_BASE_URL: <your-stt-openai-base-url>
STT_OPENAI_API_KEY: <your-stt-openai-api-key>
# Additional Configuration:
asr_model: "distil-whisper/distil-large-v3" # Model for converting audio/video transcription
enable_stt: true # Enable speech-to-text for audio/video transcriptionnoteEnsure you have selected Agents Only when uploading.
- Configure the OpenAI base URL and API key for STT:
-
-
Convert Document to Text: Transform scanned or digital documents into editable text formats.
Requirements:β
- Basic agent configuration
ALLOW_API: "1"
- Basic agent configuration
-
Screenshot Webpage: Capture screenshots of webpages.
Requirements:β
- Requires the Internet Access tool to be enabled.
-
Mermaid Chart-Diagram Renderer: Generate flowcharts and diagrams.
Requirements:β
- Enabled with the default configuration.
Automation and scriptingβ
-
Shell Scripting: Automate system-level tasks to streamline operations.
Requirements:β
- Basic agent configuration:
ALLOW_API: "1"
- Basic agent configuration:
Specialized AI featuresβ
-
RAG Text: Enhance text-based tasks with retrieval-augmented generation.
Requirements:β
- Uses default models in ModelLock.
- Basic agent configuration:
ALLOW_API: "1"
-
RAG Vision: Apply retrieval-augmented generation for vision-based tasks.
Requirements:β
- Uses default vision models in ModelLock.
Multimedia processingβ
-
Download Web Video: Download web videos.
Requirements:β
- Requires the Internet Access tool to be enabled.
- Shell Scripting tool must be enabled as a prerequisite.
-
Ask Question About Image: Query and analyze visual data.
Requirements:β
- Requires a vision model configured in ModelLock.
Software Development Toolsβ
-
Aider Code Generation: Automatically generate code snippets to accelerate development tasks, particularly for data science and machine learning models.
Requirements:β
- Models are fetched from ModelLock.
- No additional configuration required.
-
GitHub: Integrates with the GitHub platform for version control, code repository browsing, and collaboration.
Requirements:β
- Requires configuring
GITHUB_TOKEN
as a secret:GITHUB_TOKEN: <your-github-token>
- Requires configuring
-
Evaluate Answer: Provides automated evaluation of responses generated by agents.
Requirements:β
- Basic agent configuration:
ALLOW_API: "1"
- Basic agent configuration:
-
SWEBench Evaluate Patch: Evaluates software patches by running automated tests, quality checks, and performance benchmarks.
Requirements:β
- Basic agent configuration:
ALLOW_API: "1"
- Basic agent configuration:
To use tools that require internet access, such as GitHub, Wikipedia Articles Search, Web Image Search, etc., ensure that the Internet Access tool is selected.
- Submit and view feedback for this page
- Send feedback about Enterprise h2oGPTe to cloud-feedback@h2o.ai