Prompt Buddy logoPrompt Buddy

openai · OpenAI Platform Docs

Graders | OpenAI API

Teaches how to implement LLM-based grading patterns to evaluate the quality, accuracy, or adherence of model outputs against specific criteria.

Import to Prompt Buddy

Derived skill

Files assembled from official documentation

Viewing SKILL.md

Graders | OpenAI API

Teaches how to implement LLM-based grading patterns to evaluate the quality, accuracy, or adherence of model outputs against specific criteria.

When To Use

Use when you need to automate the evaluation of model outputs using a secondary LLM to score performance or verify compliance with specific instructions.

Reference Files

FileContainsUse For
SKILL.mdEntry point: scope, routing table, and workflow.Start here.
docs/graders-openai-api-workflow-guide.mdA technical guide detailing the implementation of multigraders, design tips, and technical constraints for using the OpenAI API for grading tasks.Questions about a technical guide detailing the implementation of multigraders, design tips, and technical constraints for using the...
examples/graders-openai-api-openai-api-graders.textA text-based example demonstrating the structure of a grader response including lead, excerpt, and reference answer fields.Exact payloads, commands, or snippets shown in A text-based example demonstrating the structure of a grader response including lead, excerpt, and reference answer f...
examples/graders-openai-api-openai-api-graders-json-configuration.textA JSON configuration object defining multi-type grader rules and stringcheck operations for evaluating API outputs.Exact payloads, commands, or snippets shown in A JSON configuration object defining multi-type grader rules and stringcheck operations for evaluating API outputs.
examples/graders-openai-api-openai-api-graders-definition.textA text representation of the JSON schema structure used for defining grading operations and string comparison rules in the OpenAI API.Exact payloads, commands, or snippets shown in A text representation of the JSON schema structure used for defining grading operations and string comparison rules i...
examples/graders-openai-api-openai-api-graders-textsimilarity.textA text-based schema definition for the textsimilarity grader type including evaluation metrics like bleu, rouge, and cosine similarity.Exact payloads, commands, or snippets shown in A text-based schema definition for the textsimilarity grader type including evaluation metrics like bleu, rouge, and...
examples/graders-openai-api-openai-api-grader-scoremodel.textA text representation of the scoremodel JSON schema used for defining grader configurations in the OpenAI API.Exact payloads, commands, or snippets shown in A text representation of the scoremodel JSON schema used for defining grader configurations in the OpenAI API.
examples/graders-openai-api-openai-api-graders-text-format.textA text representation of the grading structure including roles and content excerpts for the OpenAI API.Exact payloads, commands, or snippets shown in A text representation of the grading structure including roles and content excerpts for the OpenAI API.
examples/graders-openai-api-openai-api-graders-scoremodel-python.textA Python code example demonstrating how to define a dummy scoremodel grader for the OpenAI API.Exact payloads, commands, or snippets shown in A Python code example demonstrating how to define a dummy scoremodel grader for the OpenAI API.
examples/graders-openai-api-openai-api-graders-json.textA text representation of the JSON schema used for defining grader output structures including results and reasoning steps.Exact payloads, commands, or snippets shown in A text representation of the JSON schema used for defining grader output structures including results and reasoning s...
examples/graders-openai-api-openai-api-graders-text-format-2.textA text file demonstrating the structured format for grader outputs including lead, excerpt, description, and conclusion.Exact payloads, commands, or snippets shown in A text file demonstrating the structured format for grader outputs including lead, excerpt, description, and conclusion.
examples/graders-openai-api-openai-api-graders-comparison-format.textA text representation of the comparison format used by the OpenAI API graders to evaluate ranked answers.Exact payloads, commands, or snippets shown in A text representation of the comparison format used by the OpenAI API graders to evaluate ranked answers.
examples/graders-openai-api-openai-api-graders-model-grader-comparison-logic.textA text representation of the model_grader function logic used to compare multiple answers against a reference answer.Exact payloads, commands, or snippets shown in A text representation of the modelgrader function logic used to compare multiple answers against a reference answer.
examples/graders-openai-api-openai-api-graders-python-implementation.textA Python function demonstrating how to implement a grading logic for the OpenAI API graders guide.Exact payloads, commands, or snippets shown in A Python function demonstrating how to implement a grading logic for the OpenAI API graders guide.
examples/graders-openai-api-openai-api-graders-python-implementation-2.textA Python code snippet demonstrating the implementation of a grading function for the OpenAI API graders guide.Exact payloads, commands, or snippets shown in A Python code snippet demonstrating the implementation of a grading function for the OpenAI API graders guide.
examples/graders-openai-api-openai-api-graders-format-examples.textA text file demonstrating various output formats including text, JSON, tools, and audio for the OpenAI API graders guide.Exact payloads, commands, or snippets shown in A text file demonstrating various output formats including text, JSON, tools, and audio for the OpenAI API graders gu...
examples/graders-openai-api-openai-api-graders-format.textA text representation of the grading data structure including reference answers and scoring keys for the OpenAI API graders guide.Exact payloads, commands, or snippets shown in A text representation of the grading data structure including reference answers and scoring keys for the OpenAI API g...
examples/graders-openai-api-openai-api-graders-python-grading-function-implementa.textA Python implementation of a grading function using the RapidFuzz library to compare sample text against items.Exact payloads, commands, or snippets shown in A Python implementation of a grading function using the RapidFuzz library to compare sample text against items.
examples/graders-openai-api-openai-api-graders-python-implementation-3.textA Python code snippet demonstrating how to implement and use the grader module within the OpenAI API framework.Exact payloads, commands, or snippets shown in A Python code snippet demonstrating how to implement and use the grader module within the OpenAI API framework.
examples/graders-openai-api-openai-api-graders-python-dependencies.textA list of required Python library versions including numpy, scipy, and scikit-learn for implementing OpenAI API graders.Exact payloads, commands, or snippets shown in A list of required Python library versions including numpy, scipy, and scikit-learn for implementing OpenAI API graders.
examples/graders-openai-api-openai-api-graders-punkt-nltk-data.textA text file containing NLTK data components including punkt stopwords and wordnet used for the graders guide.Exact payloads, commands, or snippets shown in A text file containing NLTK data components including punkt stopwords and wordnet used for the graders guide.
examples/graders-openai-api-openai-api-graders-2.textA text-based example demonstrating the structure of grader data including scores and metadata for evaluating model outputs.Exact payloads, commands, or snippets shown in A text-based example demonstrating the structure of grader data including scores and metadata for evaluating model ou...
examples/graders-openai-api-openai-api-graders-configuration-json.textA JSON configuration object defining multi-type graders including text similarity and string checks for evaluating model outputs.Exact payloads, commands, or snippets shown in A JSON configuration object defining multi-type graders including text similarity and string checks for evaluating mo...

What This Skill Covers

  • get the API key from environment apikey = os.environ["OPENAIAPIKEY"] headers = {"Authorization": f"Bearer {apikey}"}
  • Main sections: Technical constraints, Multigraders, Limitations and tips, Design tips.

Workflow

  1. Open the most relevant file under docs/ for the exact documented workflow and wording.
  2. Open schemas/ files for exact structured contracts.
  3. Open examples/ files for concrete requests, commands, snippets, and manifests.
  4. Do not add behavior or configuration that is not present in the attached source files.

Canonical source: https://developers.openai.com/api/docs/guides/graders