Membuat template prompt
Membuat template prompt dengan mengidentifikasi dan mengekstrak variabel
API alat prompt sedang dalam pratinjau penelitian tertutup. Minta untuk bergabung dengan pratinjau penelitian tertutup.
Sebelum Anda memulai
Alat prompt adalah serangkaian API untuk menghasilkan dan meningkatkan prompt. Tidak seperti API kami yang lain, ini adalah API eksperimental: Anda perlu meminta akses, dan tidak memiliki tingkat komitmen yang sama untuk dukungan jangka panjang seperti API lainnya.
API ini mirip dengan yang tersedia di Anthropic Workbench, dan ditujukan untuk digunakan oleh platform rekayasa prompt dan playground lainnya.
Memulai dengan peningkat prompt
Untuk menggunakan API generasi prompt, Anda perlu:
- Telah bergabung dengan pratinjau penelitian tertutup untuk API alat prompt
- Menggunakan API secara langsung, bukan SDK
- Menambahkan header beta
prompt-tools-2025-04-02
API ini tidak tersedia di SDK
Membuat template prompt
Headers
Optional header to specify the beta version(s) you want to use.
To use multiple betas, use a comma separated list like beta1,beta2
or specify the header multiple times for each beta.
Body
The prompt to templatize, structured as a list of message
objects.
Each message in the messages
array must:
- Contain only text-only content blocks
- Not include tool calls, images, or prompt caching blocks
Example of a simple text prompt:
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "Translate hello to German"
}
]
}
]
Note that only contiguous user messages with text content are allowed. Assistant prefill is permitted, but other content types will cause validation errors.
[
{
"content": [
{
"text": "Translate hello to German",
"type": "text"
}
],
"role": "user"
}
]
The existing system prompt to templatize.
{
"system": "You are a professional English to German translator",
[...]
}
Note that this differs from the Messages API; it is strictly a string.
"You are a professional English to German translator"
Response
The templatized prompt with variable placeholders.
The response includes the input messages with specific values replaced by variable placeholders. These messages maintain the original message structure but contain uppercase variable names in place of concrete values.
For example, an input message content like "Translate hello to German"
would be transformed to "Translate {{WORD_TO_TRANSLATE}} to {{TARGET_LANGUAGE}}"
.
{
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "Translate {{WORD_TO_TRANSLATE}} to {{TARGET_LANGUAGE}}"
}
]
}
]
}
[
{
"content": [
{
"text": "Translate {{WORD_TO_TRANSLATE}} to {{TARGET_LANGUAGE}}",
"type": "text"
}
],
"role": "user"
}
]
The input system prompt with variables identified and replaced.
If no system prompt was provided in the original request, this field will be an empty string.
"You are a professional English to {{TARGET_LANGUAGE}} translator"
Usage information
A mapping of template variable names to their original values, as extracted from the input prompt during templatization. Each key represents a variable name identified in the templatized prompt, and each value contains the corresponding content from the original prompt that was replaced by that variable.
Example:
"variable_values": {
"WORD_TO_TRANSLATE": "hello",
"TARGET_LANGUAGE": "German"
}
In this example response, the original prompt – Translate hello to German
– was templatized to Translate WORD_TO_TRANSLATE to TARGET_LANGUAGE
, with the variable values extracted as shown.
{
"TARGET_LANGUAGE": "German",
"WORD_TO_TRANSLATE": "hello"
}