Dotprompt: Executable GenAI Prompt Templates

Dotprompt is an executable prompt template file format for Generative AI. It is designed to be agnostic to programming language and model provider to allow for maximum flexibility in usage. Dotprompt extends the popular Handlebars templating language with GenAI-specific features.

What's an executable prompt template?

An executable prompt template is a file that contains not only the text of a prompt but also metadata and instructions for how to use that prompt with a generative AI model. Here's what makes Dotprompt files executable:

• Metadata Inclusion: Dotprompt files include metadata about model configuration, input requirements, and expected output format. This information is typically stored in a YAML frontmatter section at the beginning of the file.

• Self-Contained Entity: Because a Dotprompt file contains all the necessary information to execute a prompt, it can be treated as a self-contained entity. This means you can "run" a Dotprompt file directly, without needing additional configuration or setup in your code.

• Model Configuration: The file specifies which model to use and how to configure it (e.g., temperature, max tokens).

• Input Schema: It defines the structure of the input data expected by the prompt, allowing for validation and type-checking.

• Output Format: The file can specify the expected format of the model's output, which can be used for parsing and validation.

• Templating: The prompt text itself uses Handlebars syntax, allowing for dynamic content insertion based on input variables.

This combination of features makes it possible to treat a Dotprompt file as an executable unit, streamlining the process of working with AI models and ensuring consistency across different uses of the same prompt.

Example .prompt file

Here's an example of a Dotprompt file that extracts structured data from provided text:

---
model: googleai/gemini-flash-latest
input:
  schema:
    text: string
output:
  format: json
  schema:
    name?: string, the full name of the person
    age?: number, the age of the person
    occupation?: string, the person's occupation
---
Extract the requested information from the given text. If a piece of information is not
present, omit that field from the output. Text:
{{text}}

This Dotprompt file:

1. Specifies the use of the googleai/gemini-flash-latest model.
2. Defines an input schema expecting a text string.
3. Specifies that the output should be in JSON format.
4. Provides a schema for the expected output, including fields for name, age, and occupation.
5. Uses Handlebars syntax ({{text}}) to insert the input text into the prompt.

When executed, this prompt would take a text input, analyze it using the specified AI model, and return a structured JSON object with the extracted information.

Runtime context

Prompt input and runtime context are separate namespaces. Use {{name}} for input and {{@name}} for context:

from dotpromptz import DataArgument, Dotprompt

# 1. Initialize compiler
prompt = Dotprompt()

# 2. Render prompt with isolated input and context
result = await prompt.render(
    '{{name}} is signed in as {{@name}}',
    DataArgument(
        input={'name': 'Ada'},
        context={'name': 'admin'},
    ),
)

# 3. Access rendered output
print(result.messages[0].content[0].text)
# => Ada is signed in as admin