Create Evaluation

ImageBase64ContentBlock

The template variables added to the prompt when executing the prompt.

TextContentBlock

ToolCallContentBlock

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 type of the tool. Currently, only `function` is supported.

ToolResultContentBlock

X-API-KEY

PROMPT FOUNDRY

The ultimate prompt engineering, prompt management, and LLM evaluation tool.

Welcome

Getting Started

Why Prompt Management?

Frequently Asked Questions

Overview

Playground

Evaluations

Prompt Management

AI Gateway

Observability

Tools

Supported Models

Check Weather - Tool Use

Not a Hotdog - Vision

Automatically Create Evaluations from Conversations

Your first prompt

Evaluating your prompt

Deploying

Prompt Foundry is a comprehensive tool for prompt engineering, management, and evaluation. It is designed to simplify the development and integration process for teams working on TypeScript, JavaScript, and NodeJS AI applications utilizing large language models (LLMs).

Node.js

Prompt Foundry is a comprehensive tool for prompt engineering, management, and evaluation. It is designed to simplify the development and integration process for teams working on Python AI applications utilizing large language models (LLMs).

Python

OpenAPI

The prompt engineering, prompt management, and prompt evaluation tool for Java.

Java

The prompt engineering, prompt management, and prompt evaluation tool for Go.

The prompt engineering, prompt management, and prompt evaluation tool for C# and .NET.

The prompt engineering, prompt management, and prompt evaluation tool for Ruby and Ruby on Rails.

Ruby

The prompt engineering, prompt management, and prompt evaluation tool for Kotlin.

Kotlin

Initiates a completion request to the configured LLM provider using specified parameters and provided variables. This endpoint abstracts the integration with different model providers, enabling seamless switching between models while maintaining a consistent data model for your application.

Completion

Get the configuration of an existing prompt.

Get Prompt

Update the configuration of an existing prompt and deploys it.

Update Prompt

Fetches the configured model parameters and messages rendered with the provided variables mapped to the set LLM provider. This endpoint abstracts the need to handle mapping between different providers, while still allowing direct calls to the providers.

Get Model Parameters

Delete a prompt configuration by ID. This will remove the prompt from the system and all associated data including evaluations.

Delete Prompt

List Prompts

Create Prompt

List tools

Creates tool

Fetch the details of a specific tool using its ID.

Get Tool

Update the configuration of an existing tool by providing its ID and new data.

Update tool

Delete tool

Retrieve all evaluation assertions optionally filtered by evaluation ID

List Evaluation Assertions

Create Evaluation Assertion

Retrieve the details of an evaluation assertion using its ID.

Get Evaluation Assertion

Update an existing evaluation assertion by providing its ID and new data.

Update Evaluation Assertion

Delete an evaluation assertion by providing its ID.

API Reference

Create Evaluation

Body

Response