Skip to main content

​
PromptVariable

Types for prompt variables with modality definitions.

​
Overview

Variable types define dynamic content that can be injected into prompts, with support for multiple modalities.

​
PromptVariable

Prompt variable with name and modality. 
from adaline_api.models.prompt_variable import PromptVariable

​
Fields

​
name
str
required
The variable name as it appears in the prompt template (used as {{variable_name}} in prompts).
​
modality
VariableModality
required
The variable modality type. See VariableModality.

​
Example

from adaline_api.models.prompt_variable import PromptVariable
from adaline_api.models.variable_modality import VariableModality

variables: list[PromptVariable] = [
    PromptVariable(name="user_name", modality=VariableModality.TEXT),
    PromptVariable(name="company_name", modality=VariableModality.TEXT),
    PromptVariable(name="company_logo", modality=VariableModality.IMAGE),
    PromptVariable(name="report", modality=VariableModality.PDF),
    PromptVariable(name="external_data", modality=VariableModality.API),
    PromptVariable(name="nested_prompt", modality=VariableModality.PROMPT),
]
JSON: 
[
  { "name": "user_name", "modality": "text" },
  { "name": "company_name", "modality": "text" },
  { "name": "company_logo", "modality": "image" },
  { "name": "report", "modality": "pdf" }
]

​
VariableModality

See the dedicated VariableModality page for full documentation. Variable modality type enumeration. 
from adaline_api.models.variable_modality import VariableModality
VariableModality is a str enum with the following values:
ValueEnum MemberDescription
"text"VariableModality.TEXTPlain text content
"image"VariableModality.IMAGEImage content (URL or base64)
"pdf"VariableModality.PDFPDF document content
"api"VariableModality.APIExternal API data source
"prompt"VariableModality.PROMPTNested prompt reference

​
Example

from adaline_api.models.variable_modality import VariableModality

modality = VariableModality.TEXT       # 'text'
modality = VariableModality.IMAGE      # 'image'

# String comparison works
assert VariableModality.TEXT == "text"

​
Using with Deployments

from adaline.main import Adaline
from adaline_api.models.prompt_variable import PromptVariable

adaline = Adaline()

deployment = await adaline.get_latest_deployment(
    prompt_id="prompt_abc123",
    deployment_environment_id="environment_abc123"
)

# Access variable definitions from the deployment
variables: list[PromptVariable] = deployment.prompt.variables

for v in variables:
    print(f"Variable: {v.name}, Modality: {v.modality}")
    # e.g. "Variable: user_name, Modality: text"

​
Replacing Variables with replace_prompt_variables

The replace_prompt_variables utility substitutes {{variable_name}} placeholders in a prompt’s text messages with actual values. 
from adaline.utils import replace_prompt_variables, OuterVariableValue, InnerVariableValue

​
Usage

from adaline.main import Adaline
from adaline.utils import replace_prompt_variables, OuterVariableValue, InnerVariableValue

adaline = Adaline()

deployment = await adaline.get_latest_deployment(
    prompt_id="prompt_abc123",
    deployment_environment_id="environment_abc123"
)

# Define variable values
variable_values = [
    OuterVariableValue(
        name="user_name",
        value=InnerVariableValue(modality="text", value="Alice")
    ),
    OuterVariableValue(
        name="company_name",
        value=InnerVariableValue(modality="text", value="Acme Corp")
    ),
]

# Replace placeholders in the prompt
resolved_prompt = replace_prompt_variables(
    prompt=deployment.prompt,
    variable_values=variable_values
)
The function returns a deep copy of the prompt with all {{variable_name}} placeholders in TextContent messages replaced with the provided values. Variables that don’t have a matching value are left as-is.

​
Complete Example

from adaline.main import Adaline
from adaline.utils import replace_prompt_variables, OuterVariableValue, InnerVariableValue
from openai import OpenAI

adaline = Adaline()
openai_client = OpenAI()

async def use_prompt_with_variables():
    deployment = await adaline.get_latest_deployment(
        prompt_id="prompt_abc123",
        deployment_environment_id="environment_abc123"
    )

    # Inspect available variables
    for v in deployment.prompt.variables:
        print(f"{v.name} ({v.modality})")

    # Replace text variables
    resolved = replace_prompt_variables(
        prompt=deployment.prompt,
        variable_values=[
            OuterVariableValue(
                name="user_name",
                value=InnerVariableValue(modality="text", value="Alice")
            ),
        ]
    )

    # Use resolved messages with your provider
    config = resolved.config
    response = openai_client.chat.completions.create(
        model=config.model,
        messages=[...],  # Build from resolved.messages
        temperature=config.settings.get("temperature"),
    )