Learn how to use prompt templates and schemas to manage complexity in your prompts.
topic -> haiku
mapping.
The rest of the prompt is a detail of the current implemention, and it might evolve over time.
Instead, let’s move the boilerplate for this user message to our configuration.
tensorzero.toml
.
raw_text
content block type instead of text
.system_text
, user_text
, and assistant_text
, which you can optionally use in your template.
These variables include the content of the text content block provided at inference time.tensorzero.toml
are relative to its location, so we don’t specify the parent folder config/
.Docker Compose Configuration
Sample Output
input
field will be structured according to our schema.
Let’s check our database.
Sample Output