- Documentation
- API Reference
- POSTGet Model Prameters
- GETGet Prompt
- PUTUpdate Prompt
- DELDelete Prompt
- GETList Prompts
- POSTCreate Prompt
- GETList tools
- POSTCreates tool
- GETGet Tool
- PUTUpdate tool
- DELDelete tool
- GETList Evaluation Assertions
- POSTCreate Evaluation Assertion
- GETGet Evaluation Assertion
- PUTUpdate Evaluation Assertion
- DELDelete Evaluation Assertion
- GETList Evaluations
- POSTCreate Evaluation
- GETGet Evaluation
- PUTUpdate Evaluation
- DELDelete Evaluation
Endpoints
Get Model Prameters
Fetches the model configuration parameters for a specified prompt, including penalty settings, response format, and the model messages rendered with the given variables mapped to the set LLM provider.
The template variables added to the prompt when executing the prompt.
Replaces the configured prompt messages when running the prompt.
Appended the the end of the configured prompt messages before running the prompt.
A unique identifier representing your end-user, which can help monitor and detect abuse.
curl --request POST \
--url https://api.promptfoundry.ai/sdk/v1/prompts/{id} \
--header 'Content-Type: application/json'
{
"provider": "anthropic",
"name": "<string>",
"parameters": {
"max_tokens": 123,
"messages": [
{
"content": "<string>",
"role": "user"
}
],
"model": "<string>",
"metadata": {
"user_id": "<string>"
},
"stop_sequences": [
"<string>"
],
"stream": true,
"system": "<string>",
"temperature": 123,
"tool_choice": {
"type": "auto"
},
"tools": [
{
"input_schema": {
"type": "object",
"properties": "<any>"
},
"name": "<string>",
"description": "<string>"
}
],
"top_k": 123,
"top_p": 123
}
}
Path Parameters
Body
The template variables added to the prompt when executing the prompt.
Replaces the configured prompt messages when running the prompt.
Example: "Hello, {{city}}!"
assistant
, system
, tool
, user
TOOL_CALL_1
The type of the tool. Currently, only function
is supported.
function
The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
The name of the function to call.
Appended the the end of the configured prompt messages before running the prompt.
Example: "Hello, {{city}}!"
assistant
, system
, tool
, user
TOOL_CALL_1
The type of the tool. Currently, only function
is supported.
function
The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function.
The name of the function to call.
A unique identifier representing your end-user, which can help monitor and detect abuse.
Response
anthropic
user
, assistant
auto
object
curl --request POST \
--url https://api.promptfoundry.ai/sdk/v1/prompts/{id} \
--header 'Content-Type: application/json'
{
"provider": "anthropic",
"name": "<string>",
"parameters": {
"max_tokens": 123,
"messages": [
{
"content": "<string>",
"role": "user"
}
],
"model": "<string>",
"metadata": {
"user_id": "<string>"
},
"stop_sequences": [
"<string>"
],
"stream": true,
"system": "<string>",
"temperature": 123,
"tool_choice": {
"type": "auto"
},
"tools": [
{
"input_schema": {
"type": "object",
"properties": "<any>"
},
"name": "<string>",
"description": "<string>"
}
],
"top_k": 123,
"top_p": 123
}
}