Skip to content

Data Models

Core data models used throughout GeoAgent for structured data exchange between agents.

geoagent.core.models

Shared Pydantic models for GeoAgent components.

This module contains all shared data models used across the GeoAgent pipeline to avoid circular dependencies between modules.

AnalysisResult (BaseModel)

Result from the Analysis Agent containing computed analysis.

Source code in geoagent/core/models.py 
class AnalysisResult(BaseModel):
    """Result from the Analysis Agent containing computed analysis."""

    result_data: Union[Dict[str, Any], List[Any]] = Field(
        description="The computed analysis results (summary statistics, arrays, etc.)"
    )
    code_generated: str = Field(
        description="Python code that was generated and executed for transparency"
    )
    visualization_hints: Dict[str, Any] = Field(
        default_factory=dict,
        description="Suggested visualization parameters (colormap, ranges, etc.)",
    )
    success: bool = Field(
        default=True, description="Whether the analysis completed successfully"
    )
    error_message: Optional[str] = Field(
        default=None, description="Error message if analysis failed"
    )
__class_vars__ special

The names of the class variables defined on the model.

__private_attributes__ special

Metadata about the private attributes of the model.

__pydantic_complete__ special

Whether model building is completed, or if there are still undefined fields.

__pydantic_computed_fields__ special

A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_custom_init__ special

Whether the model has a custom __init__ method.

__pydantic_decorators__ special

Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_fields__ special

A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects. This replaces Model.__fields__ from Pydantic V1.

__pydantic_generic_metadata__ special

Metadata for generic models; contains data used for a similar purpose to args, origin, parameters in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__ special

Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__ special

The name of the post-init method for the model, if defined.

__pydantic_setattr_handlers__ special

__setattr__ handlers. Memoizing the handlers leads to a dramatic performance improvement in __setattr__

__signature__ special

The synthesized __init__ [Signature][inspect.Signature] of the model.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

DataResult (BaseModel)

Result from the Data Agent containing retrieved geospatial data.

Source code in geoagent/core/models.py 
class DataResult(BaseModel):
    """Result from the Data Agent containing retrieved geospatial data."""

    items: List[Dict[str, Any]] = Field(
        description="List of STAC items or data references"
    )
    metadata: Dict[str, Any] = Field(
        default_factory=dict, description="Additional metadata about the data search"
    )
    data_type: str = Field(
        description="Type of data retrieved: 'raster', 'vector', or 'tabular'"
    )
    total_items: int = Field(description="Total number of items found")
    search_query: Optional[Dict[str, Any]] = Field(
        default=None, description="The search query that was executed"
    )
__class_vars__ special

The names of the class variables defined on the model.

__private_attributes__ special

Metadata about the private attributes of the model.

__pydantic_complete__ special

Whether model building is completed, or if there are still undefined fields.

__pydantic_computed_fields__ special

A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_custom_init__ special

Whether the model has a custom __init__ method.

__pydantic_decorators__ special

Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_fields__ special

A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects. This replaces Model.__fields__ from Pydantic V1.

__pydantic_generic_metadata__ special

Metadata for generic models; contains data used for a similar purpose to args, origin, parameters in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__ special

Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__ special

The name of the post-init method for the model, if defined.

__pydantic_setattr_handlers__ special

__setattr__ handlers. Memoizing the handlers leads to a dramatic performance improvement in __setattr__

__signature__ special

The synthesized __init__ [Signature][inspect.Signature] of the model.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

GeoAgentResponse (BaseModel)

Complete response from GeoAgent containing all pipeline results.

Source code in geoagent/core/models.py 
class GeoAgentResponse(BaseModel):
    """Complete response from GeoAgent containing all pipeline results."""

    plan: PlannerOutput = Field(description="The parsed query plan")
    data: Optional[DataResult] = Field(
        default=None, description="Data retrieval results"
    )
    analysis: Optional[AnalysisResult] = Field(
        default=None, description="Analysis results if analysis was performed"
    )
    map: Optional[Any] = Field(  # leafmap.Map - using Any to avoid import issues
        default=None, description="Generated leafmap visualization"
    )
    code: str = Field(
        default="", description="All generated Python code from the pipeline"
    )
    success: bool = Field(
        default=True, description="Whether the overall pipeline succeeded"
    )
    error_message: Optional[str] = Field(
        default=None, description="Error message if pipeline failed"
    )
    execution_time: Optional[float] = Field(
        default=None, description="Total execution time in seconds"
    )
__class_vars__ special

The names of the class variables defined on the model.

__private_attributes__ special

Metadata about the private attributes of the model.

__pydantic_complete__ special

Whether model building is completed, or if there are still undefined fields.

__pydantic_computed_fields__ special

A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_custom_init__ special

Whether the model has a custom __init__ method.

__pydantic_decorators__ special

Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_fields__ special

A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects. This replaces Model.__fields__ from Pydantic V1.

__pydantic_generic_metadata__ special

Metadata for generic models; contains data used for a similar purpose to args, origin, parameters in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__ special

Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__ special

The name of the post-init method for the model, if defined.

__pydantic_setattr_handlers__ special

__setattr__ handlers. Memoizing the handlers leads to a dramatic performance improvement in __setattr__

__signature__ special

The synthesized __init__ [Signature][inspect.Signature] of the model.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

Intent (str, Enum)

Supported query intents.

Source code in geoagent/core/models.py 
class Intent(str, Enum):
    """Supported query intents."""

    SEARCH = "search"
    ANALYZE = "analyze"
    VISUALIZE = "visualize"
    COMPARE = "compare"
__format__(self, format_spec) special

Default object formatter.

Return str(self) if format_spec is empty. Raise TypeError otherwise.

Source code in geoagent/core/models.py 
def __format__(self, format_spec):
    return str.__format__(str(self), format_spec)

PlannerOutput (BaseModel)

Output from the Planner Agent containing structured query parameters.

Source code in geoagent/core/models.py 
class PlannerOutput(BaseModel):
    """Output from the Planner Agent containing structured query parameters."""

    intent: str = Field(
        description="The analysis intent (e.g., 'compute_ndvi', 'find_deforestation')"
    )
    location: Optional[Dict[str, Any]] = Field(
        default=None,
        description="Location information (bounding box, geometry, place name)",
    )
    time_range: Optional[Dict[str, Union[str, datetime]]] = Field(
        default=None, description="Temporal range with start_date and end_date"
    )
    dataset: Optional[str] = Field(
        default=None,
        description="Preferred dataset or catalog (e.g., 'sentinel-2', 'landsat')",
    )
    analysis_type: Optional[str] = Field(
        default=None,
        description="Type of analysis requested (e.g., 'ndvi', 'change_detection')",
    )
    parameters: Dict[str, Any] = Field(
        default_factory=dict, description="Additional analysis parameters"
    )
    confidence: float = Field(
        default=1.0, description="Confidence score of the parsing (0-1)"
    )
__class_vars__ special

The names of the class variables defined on the model.

__private_attributes__ special

Metadata about the private attributes of the model.

__pydantic_complete__ special

Whether model building is completed, or if there are still undefined fields.

__pydantic_computed_fields__ special

A dictionary of computed field names and their corresponding [ComputedFieldInfo][pydantic.fields.ComputedFieldInfo] objects.

__pydantic_custom_init__ special

Whether the model has a custom __init__ method.

__pydantic_decorators__ special

Metadata containing the decorators defined on the model. This replaces Model.__validators__ and Model.__root_validators__ from Pydantic V1.

__pydantic_fields__ special

A dictionary of field names and their corresponding [FieldInfo][pydantic.fields.FieldInfo] objects. This replaces Model.__fields__ from Pydantic V1.

__pydantic_generic_metadata__ special

Metadata for generic models; contains data used for a similar purpose to args, origin, parameters in typing-module generics. May eventually be replaced by these.

__pydantic_parent_namespace__ special

Parent namespace of the model, used for automatic rebuilding of models.

__pydantic_post_init__ special

The name of the post-init method for the model, if defined.

__pydantic_setattr_handlers__ special

__setattr__ handlers. Memoizing the handlers leads to a dramatic performance improvement in __setattr__

__signature__ special

The synthesized __init__ [Signature][inspect.Signature] of the model.

model_config

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].