agents.memory.search.labs.agent¶

Labs Agent implementation.

Provides interactive project automation with tools and workflows. Similar to Perplexity’s Labs feature that creates apps, dashboards, and automated workflows.

Classes¶

LabsAgent

Agent for interactive project automation with tools and workflows.

Functions¶

`create_interactive_app`(app_type, title, description)	Create an interactive app.
`create_interactive_apps`(app_specs)	Create multiple interactive apps.
`create_project_assets`(project_name, asset_types)	Create project assets.
`create_visualization`(chart_type, data, title)	Create a data visualization.
`execute_python_code`(code[, description])	Execute Python code and return results.
`get_response_model`()	Get the response model for labs operations.
`get_search_instructions`()	Get specific search instructions for labs operations.
`get_system_prompt`()	Get the system prompt for labs operations.
`plan_project_workflow`(project_type, goals)	Plan a project workflow.
`process_data_file`(file_path, operations)	Process a data file with specified operations.

Module Contents¶

class agents.memory.search.labs.agent.LabsAgent(name='labs_agent', engine=None, search_tools=None, enable_code_execution=True, **kwargs)¶

Bases: haive.agents.memory.search.base.BaseSearchAgent

Agent for interactive project automation with tools and workflows.

Mimics Perplexity’s Labs feature by providing comprehensive project automation, including data analysis, visualization creation, app development, and workflow execution.

Features: - Multi-tool integration (Python, SQL, visualization libraries) - Interactive app creation (dashboards, websites, slideshows) - Code execution and data analysis - Asset management and organization - Workflow automation - Real-time collaboration tools

Capabilities: - Data analysis and visualization - Interactive dashboard creation - Basic web app development - Chart and image generation - CSV and data processing - Code execution and debugging

Examples

Basic usage:

agent = LabsAgent(
    name="labs",
    engine=AugLLMConfig(temperature=0.3)
)

response = await agent.process_labs_project(
    "Create a dashboard analyzing sales data",
    data_sources=["sales_data.csv"]
)

With specific tools:

response = await agent.process_labs_project(
    "Build an interactive chart showing trends",
    required_tools=["pandas", "plotly", "d3.js"],
    create_interactive_app=True
)

Initialize the Labs Agent.

Parameters:

name (str) – Agent identifier
engine (haive.core.engine.aug_llm.AugLLMConfig | None) – LLM configuration (defaults to optimized settings)
search_tools (list[langchain_core.tools.Tool] | None) – Optional search tools
enable_code_execution (bool) – Enable code execution capabilities
**kwargs – Additional arguments passed to parent

create_interactive_apps(workflow_steps)¶

Create interactive apps from workflow results.

Parameters:: workflow_steps (list[haive.agents.memory.search.labs.models.WorkflowStep]) – Completed workflow steps
Returns:: List of interactive apps
Return type:: list[haive.agents.memory.search.labs.models.InteractiveApp]

create_project_assets(workflow_steps)¶

Create project assets from workflow results.

Parameters:: workflow_steps (list[haive.agents.memory.search.labs.models.WorkflowStep]) – Completed workflow steps
Returns:: List of created assets
Return type:: list[haive.agents.memory.search.labs.models.ProjectAsset]

async execute_workflow_step(step_plan, step_index)¶

Execute a single workflow step.

Parameters:

step_plan (dict[str, Any]) – Planned step configuration
step_index (int) – Step index in workflow

Returns:

Executed workflow step

Return type:

haive.agents.memory.search.labs.models.WorkflowStep

get_response_model()¶

Get the response model for Labs.

Return type:: type[haive.agents.memory.search.base.SearchResponse]

get_search_instructions()¶

Get specific search instructions for Labs operations.

Return type:: str

get_system_prompt()¶

Get the system prompt for Labs operations.

Return type:: str

plan_project_workflow(query, project_type, data_sources)¶

Plan the workflow steps for a project.

Parameters:

query (str) – Project description
project_type (str) – Type of project
data_sources (list[str]) – Available data sources

Returns:

List of planned workflow steps

Return type:

list[dict[str, Any]]

async process_labs_project(query, project_type='analysis', data_sources=None, required_tools=None, create_interactive_app=True, max_work_time=600, save_to_memory=True)¶

Process a Labs project with comprehensive automation.

Parameters:

query (str) – Project description
project_type (str) – Type of project
data_sources (list[str] | None) – Available data sources
required_tools (list[str] | None) – Required tools
create_interactive_app (bool) – Whether to create interactive app
max_work_time (int) – Maximum work time in seconds
save_to_memory (bool) – Whether to save to memory

Returns:

Labs response with project results

Return type:

haive.agents.memory.search.labs.models.LabsResponse

async process_search(query, context=None, save_to_memory=True)¶

Process a search query with default Labs settings.

Parameters:

query (str) – Search query
context (dict[str, Any] | None) – Optional context
save_to_memory (bool) – Whether to save to memory

Returns:

Labs response

Return type:

haive.agents.memory.search.labs.models.LabsResponse

agents.memory.search.labs.agent.create_interactive_app(app_type, title, description)¶

Create an interactive app.

Parameters:

app_type (str)
title (str)
description (str)

Return type:

haive.agents.memory.search.labs.models.InteractiveApp

agents.memory.search.labs.agent.create_interactive_apps(app_specs)¶

Create multiple interactive apps.

Parameters:: app_specs (list[dict[str, Any]])
Return type:: list[haive.agents.memory.search.labs.models.InteractiveApp]

agents.memory.search.labs.agent.create_project_assets(project_name, asset_types)¶

Create project assets.

Parameters:

project_name (str)
asset_types (list[str])

Return type:

list[haive.agents.memory.search.labs.models.ProjectAsset]

agents.memory.search.labs.agent.create_visualization(chart_type, data, title)¶

Create a data visualization.

Parameters:

chart_type (str)
data (dict[str, Any])
title (str)

Return type:

dict[str, Any]

agents.memory.search.labs.agent.execute_python_code(code, description='')¶

Execute Python code and return results.

Parameters:

code (str)
description (str)

Return type:

dict[str, Any]

agents.memory.search.labs.agent.get_response_model()¶

Get the response model for labs operations.

Return type:: type[haive.agents.memory.search.base.SearchResponse]

agents.memory.search.labs.agent.get_search_instructions()¶

Get specific search instructions for labs operations.

Return type:: str

agents.memory.search.labs.agent.get_system_prompt()¶

Get the system prompt for labs operations.

Return type:: str

agents.memory.search.labs.agent.plan_project_workflow(project_type, goals)¶

Plan a project workflow.

Parameters:

project_type (str)
goals (list[str])

Return type:

list[haive.agents.memory.search.labs.models.WorkflowStep]

agents.memory.search.labs.agent.process_data_file(file_path, operations)¶

Process a data file with specified operations.

Parameters:

file_path (str)
operations (list[str])

Return type:

dict[str, Any]