> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://humanloop.com/docs/v4/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://humanloop.com/_mcp/server. # v4.0 ## Docs - [Overview](https://humanloop.com/docs/getting-started/overview.md): Learn how to use Humanloop for prompt engineering, evaluation and monitoring. Comprehensive guides and tutorials for LLMOps. - [Why Humanloop?](https://humanloop.com/docs/v4/why-humanloop.md): Humanloop is an enterprise-grade stack for product teams building with large language models. We are SOC-2 compliant, offer self-hosting and never train on your data. - [Quickstart Tutorial](https://humanloop.com/docs/v4/tutorials/quickstart.md): Getting up and running with Humanloop is quick and easy. This guide will run you through creating and managing your first Prompt in a few minutes. - [Create your first GPT-4 App](https://humanloop.com/docs/v4/tutorials/create-your-first-gpt-4-app.md): In this tutorial, you’ll use Humanloop to quickly create a GPT-4 chat app. You’ll learn how to create a Prompt, call GPT-4, and log your results. You’ll also learn how to capture feedback from your end users to evaluate and improve your model. - [ChatGPT clone with streaming](https://humanloop.com/docs/v4/tutorials/chatgpt-clone-in-nextjs.md): In this tutorial, you'll build a custom ChatGPT using Next.js and streaming using Humanloop TypeScript SDK. - [Create a Prompt](https://humanloop.com/docs/v4/guides/create-prompt.md): Learn how to create a Prompt in Humanloop using the UI or SDK, version it, and use it to generate responses from your AI models. Prompt management is a key part of the Humanloop platform. - [Overview](https://humanloop.com/docs/v4/guides/generate-and-log-with-the-sdk.md): Learn how to generate from large language models and log the results in Humanloop, with managed and versioned prompts. - [Generate completions](https://humanloop.com/docs/v4/guides/completion-using-the-sdk.md): Learn how to generate completions from a large language model and log the results in Humanloop, with managed and versioned prompts. - [Generate chat responses](https://humanloop.com/docs/v4/guides/chat-using-the-sdk.md): Learn how to generate chat completions from a large language model and log the results in Humanloop, with managed and versioned prompts. - [Capture user feedback](https://humanloop.com/docs/v4/guides/capture-user-feedback.md): Learn how to record user feedback on datapoints generated by your large language model using the Humanloop SDK. - [Upload historic data](https://humanloop.com/docs/v4/guides/upload-historic-data.md): Learn how to upload your historic model data to an existing Humanloop project to warm-start your project. - [Logging](https://humanloop.com/docs/v4/guides/use-your-own-model-provider.md): Integrating Humanloop and running an experiment when using your own models. - [Chaining calls (Sessions)](https://humanloop.com/docs/v4/guides/logging-session-traces.md): Learn how to log sequences of LLM calls to Humanloop, enabling you to trace through "sessions" and troubleshoot where your LLM chain went wrong or track sequences of actions taken by your LLM agent. - [Overview](https://humanloop.com/docs/v4/guides/evaluation/overview.md): Learn how to set up and use Humanloop's evaluation framework to test and track the performance of your prompts. - [Run an evaluation](https://humanloop.com/docs/v4/guides/evaluation/evaluate-models-offline.md): How do you evaluate your large language model use case using a dataset and an evaluator on Humanloop? - [Set up evaluations using API](https://humanloop.com/docs/v4/guides/evaluation/evaluations-using-api.md): How to use Humanloop to evaluate your large language model use-case, using a dataset and an evaluator. - [Use LLMs to evaluate logs](https://humanloop.com/docs/v4/guides/evaluation/use-llms-to-evaluate-logs.md): Learn how to use LLM as a judge to check for PII in Logs. - [Self-hosted evaluations](https://humanloop.com/docs/v4/guides/evaluation/self-hosted-evaluations.md): Learn how to run an evaluation in your own infrastructure and post the results to Humanloop. - [Evaluating externally generated Logs](https://humanloop.com/docs/v4/guides/evaluation/evaluating-externally-generated-logs.md): Learn how to use the Humanloop Python SDK to create an evaluation run and post-generated logs. - [Evaluating with human feedback](https://humanloop.com/docs/v4/guides/evaluation/evaluating-with-human-feedback.md): Learn how to set up a human evaluator to collect feedback on the output of your model. - [Set up Monitoring](https://humanloop.com/docs/v4/guides/evaluation/monitoring.md): Learn how to create and use online evaluators to observe the performance of your models. - [Overview](https://humanloop.com/docs/v4/guides/overview.md): Datasets are pre-defined collections of input-output pairs that you can use within Humanloop to define fixed examples for your projects. - [Create a dataset](https://humanloop.com/docs/v4/guides/create-dataset.md): Learn how to create Datasets in Humanloop to define fixed examples for your projects, and build up a collection of input-output pairs for evaluation and fine-tuning. - [Batch generate](https://humanloop.com/docs/v4/guides/batch-generate.md): This guide demonstrates how to run a batch generation using a large language model across all the datapoints in a dataset. - [Overview](https://humanloop.com/docs/v4/guides/run-an-experiment.md): Experiments allow you to set up A/B test between multiple different Prompts. - [Run an experiment](https://humanloop.com/docs/v4/guides/experiments-from-the-app.md): Experiments allow you to set up A/B tests between multiple model configs. - [Run experiments managing your own model](https://humanloop.com/docs/v4/guides/run-an-experiment-with-your-own-model-provider.md): Experiments allow you to set up A/B test between multiple different model configs. - [Tool Calling in Editor](https://humanloop.com/docs/v4/guides/tool-calling.md): Learn how to use tool calling in your large language models and interact with it in the Humanloop Playground. - [Tool Calling with the SDK](https://humanloop.com/docs/v4/guides/create-a-tool-with-the-sdk.md): Learn how to use OpenAI function calling in the Humanloop Python SDK. - [Link a JSON Schema Tool](https://humanloop.com/docs/v4/guides/link-jsonschema-tool.md): Learn how to create a JSON Schema tool that can be reused across multiple Prompts. - [Use the Snippet Tool](https://humanloop.com/docs/v4/guides/snippet-tool.md): Learn how to use the Snippet tool to manage common text snippets that you want to reuse across your different prompts. - [Set up semantic search (RAG)](https://humanloop.com/docs/v4/guides/set-up-semantic-search.md): Learn how to set up a RAG system using the Pinecone integration to enrich your prompts with relevant context from a data source of documents. - [Fine-tune a model](https://humanloop.com/docs/v4/guides/finetune-a-model.md): In this guide we will demonstrate how to use Humanloop’s fine-tuning workflow to produce improved models leveraging your user feedback data. - [Manage API keys](https://humanloop.com/docs/v4/guides/create-and-revoke-api-keys.md): How to create, share and manage you Humanloop API keys. The API keys allow you to access the Humanloop API programmatically in your app. - [Invite collaborators](https://humanloop.com/docs/v4/guides/invite-collaborators.md): Inviting people to your organization allows them to interact with your Humanloop projects. - [Deploy to environments](https://humanloop.com/docs/v4/guides/deploy-to-an-environment.md): Environments enable you to deploy model configurations and experiments, making them accessible via API, while also maintaining a streamlined production workflow. - [Prompts](https://humanloop.com/docs/v4/prompts.md): Discover how Humanloop manages prompts, with version control and rigorous evaluation for better performance. - [Tools](https://humanloop.com/docs/v4/tools.md): Discover how Humanloop manages tools for use with large language models (LLMs) with version control and rigorous evaluation for better performance. - [Datasets](https://humanloop.com/docs/v4/datasets.md): Discover how Humanloop manages datasets, with version control and collaboration to enable you to evaluate and fine-tune your models. - [Evaluators](https://humanloop.com/docs/v4/evaluators.md): Learn about LLM Evaluation using Evaluators. Evaluators are functions that can be used to judge the output of Prompts, Tools or other Evaluators. - [Logs](https://humanloop.com/docs/v4/logs.md): Logs contain the inputs and outputs of each time a Prompt, Tool or Evaluator is called. - [Environments](https://humanloop.com/docs/v4/environments.md): Deployment environments enable you to control the deployment lifecycle of your Prompts and other files between development and production environments. - [Key Concepts](https://humanloop.com/docs/v4/key-concepts.md): Learn about the core entities and concepts in Humanloop. Understand how to use them to manage your projects and improve your models. - [Supported Models](https://humanloop.com/docs/reference/models.md): Humanloop supports all the major large language model providers, including OpenAI, Anthropic, Google, AWS Bedrock, Azure, and more. Additionally, you can use your own custom models with with the API and still benefit from the Humanloop platform. - [Access Roles](https://humanloop.com/docs/reference/access-roles.md): Learn about the different roles and permissions in Humanloop to help you with prompt and data management for large language models. - [.prompt files](https://humanloop.com/docs/v4/prompt-file-format.md): The `.prompt` file format is a human-readable and version-control-friendly format for storing model configurations. - [Postman Workspace](https://humanloop.com/docs/v4/postman-workspace.md): Reference our Postman Workspace for examples of how to interact with the Humanloop API directly. - [SDKs](https://humanloop.com/docs/v4/sdk.md): Learn how to integrate Humanloop into your applications using our Python and TypeScript SDKs or REST API. - [Errors](https://humanloop.com/docs/introduction/errors.md): This page provides a list of the error codes and messages you may encounter when using the Humanloop API. - [Humanloop API](https://humanloop.com/docs/v4/api.md) - [November](https://humanloop.com/docs/changelog/2024/11.md) - [October](https://humanloop.com/docs/changelog/2024/10.md) - [September](https://humanloop.com/docs/changelog/2024/09.md) - [August](https://humanloop.com/docs/changelog/2024/08.md) - [July](https://humanloop.com/docs/changelog/2024/07.md) - [June](https://humanloop.com/docs/changelog/2024/06.md) - [May](https://humanloop.com/docs/changelog/2024/05.md) - [April](https://humanloop.com/docs/changelog/2024/04.md) - [March](https://humanloop.com/docs/changelog/2024/03.md) - [February](https://humanloop.com/docs/changelog/2024/02.md) - [January](https://humanloop.com/docs/changelog/2024/01.md) - [December](https://humanloop.com/docs/changelog/2023/12.md) - [November](https://humanloop.com/docs/changelog/2023/11.md) - [October](https://humanloop.com/docs/changelog/2023/10.md) - [September](https://humanloop.com/docs/changelog/2023/09.md) - [August](https://humanloop.com/docs/changelog/2023/08.md) - [July](https://humanloop.com/docs/changelog/2023/07.md) - [June](https://humanloop.com/docs/changelog/2023/06.md) - [May](https://humanloop.com/docs/changelog/2023/05.md) - [April](https://humanloop.com/docs/changelog/2023/04.md) - [March](https://humanloop.com/docs/changelog/2023/03.md) - [February](https://humanloop.com/docs/changelog/2023/02.md) ## API Docs - Humanloop API > Chats [Chat](https://humanloop.com/docs/v4/api/chats/create.md) - Humanloop API > Chats [Chat Deployed](https://humanloop.com/docs/v4/api/chats/create-deployed.md) - Humanloop API > Chats [Chat Model Config](https://humanloop.com/docs/v4/api/chats/create-config.md) - Humanloop API > Chats [Create Experiment](https://humanloop.com/docs/v4/api/chats/create-experiment.md) - Humanloop API > Completions [Create](https://humanloop.com/docs/v4/api/completions/create.md) - Humanloop API > Completions [Completion Deployed](https://humanloop.com/docs/v4/api/completions/create-deployed.md) - Humanloop API > Completions [Completion Model Config](https://humanloop.com/docs/v4/api/completions/create-config.md) - Humanloop API > Completions [Create Experiment](https://humanloop.com/docs/v4/api/completions/create-experiment.md) - Humanloop API > Datapoints [Get](https://humanloop.com/docs/v4/api/datapoints/get.md) - Humanloop API > Datapoints [Update](https://humanloop.com/docs/v4/api/datapoints/update.md) - Humanloop API > Datapoints [Delete](https://humanloop.com/docs/v4/api/datapoints/delete.md) - Humanloop API > Projects [List For Project](https://humanloop.com/docs/v4/api/projects/list-datasets.md) - Humanloop API > Projects [List](https://humanloop.com/docs/v4/api/projects/list.md) - Humanloop API > Projects [Create](https://humanloop.com/docs/v4/api/projects/create.md) - Humanloop API > Projects [Get](https://humanloop.com/docs/v4/api/projects/get.md) - Humanloop API > Projects [Delete](https://humanloop.com/docs/v4/api/projects/delete.md) - Humanloop API > Projects [Update](https://humanloop.com/docs/v4/api/projects/update.md) - Humanloop API > Projects [List Configs](https://humanloop.com/docs/v4/api/projects/list-configs.md) - Humanloop API > Projects [Create Feedback Type](https://humanloop.com/docs/v4/api/projects/create-feedback-type.md) - Humanloop API > Projects [Update Feedback Types](https://humanloop.com/docs/v4/api/projects/update-feedback-types.md) - Humanloop API > Projects [Export](https://humanloop.com/docs/v4/api/projects/export.md) - Humanloop API > Projects > Active Config [Get Active Config](https://humanloop.com/docs/v4/api/projects/active-config/get.md) - Humanloop API > Projects > Active Config [Deactivate Config](https://humanloop.com/docs/v4/api/projects/active-config/deactivate.md) - Humanloop API > Projects > Deployed Config [List Deployed Configs](https://humanloop.com/docs/v4/api/projects/deployed-config/list.md) - Humanloop API > Projects > Deployed Config [Deploy Config](https://humanloop.com/docs/v4/api/projects/deployed-config/deploy.md) - Humanloop API > Projects > Deployed Config [Delete Deployed Config](https://humanloop.com/docs/v4/api/projects/deployed-config/delete.md) - Humanloop API > Datasets [Create](https://humanloop.com/docs/v4/api/datasets/create.md) - Humanloop API > Datasets [List ](https://humanloop.com/docs/v4/api/datasets/list.md) - Humanloop API > Datasets [Get](https://humanloop.com/docs/v4/api/datasets/get.md) - Humanloop API > Datasets [Delete](https://humanloop.com/docs/v4/api/datasets/delete.md) - Humanloop API > Datasets [Update](https://humanloop.com/docs/v4/api/datasets/update.md) - Humanloop API > Datasets [Datapoints](https://humanloop.com/docs/v4/api/datasets/list-datapoints.md) - Humanloop API > Datasets [Create Datapoint](https://humanloop.com/docs/v4/api/datasets/create-datapoint.md) - Humanloop API > Evaluations [Get](https://humanloop.com/docs/v4/api/evaluations/get.md) - Humanloop API > Evaluations [List Datapoints](https://humanloop.com/docs/v4/api/evaluations/list-datapoints.md) - Humanloop API > Evaluations [Create](https://humanloop.com/docs/v4/api/evaluations/create.md) - Humanloop API > Evaluations [Log](https://humanloop.com/docs/v4/api/evaluations/log.md) - Humanloop API > Evaluations [Result](https://humanloop.com/docs/v4/api/evaluations/result.md) - Humanloop API > Evaluations [Update Status](https://humanloop.com/docs/v4/api/evaluations/update-status.md) - Humanloop API > Evaluations [Add Evaluators](https://humanloop.com/docs/v4/api/evaluations/add-evaluators.md) - Humanloop API > Evaluations [Get Evaluations](https://humanloop.com/docs/v4/api/evaluations/list.md) - Humanloop API > Evaluators [List](https://humanloop.com/docs/v4/api/evaluators/list.md) - Humanloop API > Evaluators [Create](https://humanloop.com/docs/v4/api/evaluators/create.md) - Humanloop API > Evaluators [Get](https://humanloop.com/docs/v4/api/evaluators/get.md) - Humanloop API > Evaluators [Delete](https://humanloop.com/docs/v4/api/evaluators/delete.md) - Humanloop API > Evaluators [Update](https://humanloop.com/docs/v4/api/evaluators/update.md) - Humanloop API > Feedback [Feedback](https://humanloop.com/docs/v4/api/feedback/feedback.md) - Humanloop API > Logs [List ](https://humanloop.com/docs/v4/api/logs/list.md) - Humanloop API > Logs [Log](https://humanloop.com/docs/v4/api/logs/log.md) - Humanloop API > Logs [Delete](https://humanloop.com/docs/v4/api/logs/delete.md) - Humanloop API > Logs [Update By Reference](https://humanloop.com/docs/v4/api/logs/update-by-ref.md) - Humanloop API > Logs [Get](https://humanloop.com/docs/v4/api/logs/get.md) - Humanloop API > Logs [Update](https://humanloop.com/docs/v4/api/logs/update.md) - Humanloop API > Model Configs [Register](https://humanloop.com/docs/v4/api/model-configs/register.md) - Humanloop API > Model Configs [Get](https://humanloop.com/docs/v4/api/model-configs/get.md) - Humanloop API > Model Configs [Export by ID](https://humanloop.com/docs/v4/api/model-configs/export.md) - Humanloop API > Model Configs [Serialize](https://humanloop.com/docs/v4/api/model-configs/serialize.md) - Humanloop API > Model Configs [Deserialize](https://humanloop.com/docs/v4/api/model-configs/deserialize.md) - Humanloop API > Sessions [List ](https://humanloop.com/docs/v4/api/sessions/list.md) - Humanloop API > Sessions [Create](https://humanloop.com/docs/v4/api/sessions/create.md) - Humanloop API > Sessions [Get](https://humanloop.com/docs/v4/api/sessions/get.md) ## OpenAPI Specification The raw OpenAPI 3.1 specification for this API is available at: - [OpenAPI JSON](https://humanloop.com/docs/v4/openapi.json) - [OpenAPI YAML](https://humanloop.com/docs/v4/openapi.yaml)