# Prompt Flow > For a smooth development flow that transitions from cloud (Azure AI) to local environments, you can directly utilize the connection already established on the cloud by setting the connection provider ## Pages - [Consume connections from Azure AI](cloud-azureai-consume-connections-from-azure-ai.md): For a smooth development flow that transitions from cloud (Azure AI) to local environments, you can directly utilize ... - [Create run with compute session](cloud-azureai-create-run-with-compute-session.md): :::{admonition} Experimental feature - [Deploy to Azure App Service](cloud-azureai-deploy-to-azure-appservice.md): [Azure App Service](https://learn.microsoft.com/azure/app-service/) is an HTTP-based service for hosting web applicat... - [Frequency asked questions (FAQ)](cloud-azureai-faq.md): For azure portal experience related issues, please create feedback on azure portal. - [How to generate test data in cloud based on documents](cloud-azureai-generate-test-data-cloud.md): This guide will help you learn how to generate test data on Azure AI, so that you can integrate the created flow and ... - [Manage flows](cloud-azureai-manage-flows.md): This documentation will walk you through how to manage your flow with CLI and SDK on [Azure AI](https://learn.microso... - [Run prompt flow in Azure AI](cloud-azureai-run-promptflow-in-azure-ai.md): Assuming you have learned how to create and run a flow following [Quick start](../../how-to-guides/quick-start.md). T... - [Change log of default runtime image](cloud-azureai-runtime-change-log.md): In Azure Machine Learning prompt flow, runtime provides the environment to execute flows. The default runtime include... - [Use flow in Azure ML pipeline job](cloud-azureai-use-flow-in-azure-ml-pipeline.md): In practical scenarios, flows fulfill various functions. For example, consider an offline flow specifically designed ... - [Cloud](cloud.md): Prompt flow streamlines the process of developing AI applications based on LLM, easing prompt engineering, prototypin... - [Connections](concepts-concept-connections.md): In prompt flow, you can utilize connections to securely manage credentials or secrets for external services. - [Flows](concepts-concept-flows.md): While how LLMs work may be elusive to many developers, how LLM apps work is not - they essentially involve a series o... - [Tools](concepts-concept-tools.md): Tools are the fundamental building blocks of a [flow](./concept-flows.md). - [Variants](concepts-concept-variants.md): With prompt flow, you can use variants to tune your prompt. In this article, you'll learn the prompt flow variants co... - [Design principles](concepts-design-principles.md): When we started this project, [LangChain](https://www.langchain.com/) already became popular esp. after the ChatGPT l... - [Concepts](concepts.md): In this section, you will learn the basic concepts of prompt flow. - [Dev Setup](dev-dev-setup.md): Select either Conda or Poetry to set up your development environment. - [Promptflow Reference Documentation Guide](dev-documentation-guidelines.md): This guide describes how to author Python docstrings for promptflow public interfaces. See our doc site at [Promptflo... - [Replay end-to-end tests](dev-replay-e2e-test.md): * This document introduces replay tests for those located in [sdk_cli_azure_test](../../src/promptflow-azure/tests/sd... - [Rotate_Aoai_Keys](dev-rotate-aoai-keys.md): Here is a checklist to rotate the AOAI keys: - [Chat with a flow](how-to-guides-chat-with-a-flow.md): :::{admonition} Experimental feature - [Deploy a flow using development server](how-to-guides-deploy-a-flow-deploy-using-dev-server.md): Once you have created and thoroughly tested a flow, you can use it as an HTTP endpoint. - [Deploy a flow using Docker](how-to-guides-deploy-a-flow-deploy-using-docker.md): There are two steps to deploy a flow using docker: - [Deploy a flow using Kubernetes](how-to-guides-deploy-a-flow-deploy-using-kubernetes.md): There are four steps to deploy a flow using Kubernetes: - [Distribute flow as executable app](how-to-guides-deploy-a-flow-distribute-flow-as-executable-app.md): We are going to use the [web-classification](https://github.com/microsoft/promptflow/tree/main/examples/flows/standar... - [Deploy a flow](how-to-guides-deploy-a-flow.md): A flow can be deployed to multiple platforms, such as a local development service, Docker container, Kubernetes clust... - [Add conditional control to a flow](how-to-guides-develop-a-dag-flow-add-conditional-control-to-a-flow.md): :::{admonition} Experimental feature - [Develop chat flow](how-to-guides-develop-a-dag-flow-develop-chat-flow.md): From this document, you can learn how to develop a chat flow by writing a flow yaml from scratch. You can - [Develop evaluation flow](how-to-guides-develop-a-dag-flow-develop-evaluation-flow.md): The evaluation flow is a flow to test/evaluate the quality of your LLM application (standard/chat flow). It usually r... - [Develop standard flow](how-to-guides-develop-a-dag-flow-develop-standard-flow.md): From this document, you can learn how to develop a standard flow by writing a flow yaml from scratch. You can - [Develop a dag flow](how-to-guides-develop-a-dag-flow.md): LLM apps can be defined as Directed Acyclic Graphs (DAGs) of function calls. These DAGs are flows in prompt flow. - [Initialize and test a flow](how-to-guides-develop-a-dag-flow-init-and-test-a-flow.md): From this document, customer can initialize a flow and test it. - [Process image in flow](how-to-guides-develop-a-dag-flow-process-image-in-flow.md): :::{admonition} Experimental feature - [Quick start](how-to-guides-develop-a-dag-flow-quick-start.md): This guide will walk you through the fist step using of prompt flow code-first experience. - [Referencing external files/folders in a flow](how-to-guides-develop-a-dag-flow-referencing-external-files-or-folders-in-a-flow.md): Sometimes, pre-existing code assets are essential for the flow reference. In most cases, you can accomplish this by i... - [Class based flow](how-to-guides-develop-a-flex-flow-class-based-flow.md): :::{admonition} Experimental feature - [Use connections in flow](how-to-guides-develop-a-flex-flow-connection-support.md): The [`connection`](../../concepts/concept-connections.md) helps securely store and manage secret keys or other sensit... - [Function based flow](how-to-guides-develop-a-flex-flow-function-based-flow.md): :::{admonition} Experimental feature - [Develop a flow](how-to-guides-develop-a-flex-flow.md): :::{admonition} Experimental feature - [Input output format](how-to-guides-develop-a-flex-flow-input-output-format.md): :::{admonition} Experimental feature - [Model Configuration](how-to-guides-develop-a-flex-flow-model-config.md): Tailoring your AI applications to use specific models with desired parameters is now easier than ever with the Prompt... - [Develop a prompty](how-to-guides-develop-a-prompty.md): :::{admonition} Experimental feature - [Prompty output format](how-to-guides-develop-a-prompty-prompty-output-format.md): :::{admonition} Experimental feature - [Using prompty in flow](how-to-guides-develop-a-prompty-use-prompty-in-flow.md): :::{admonition} Experimental feature - [Adding a Tool Icon](how-to-guides-develop-a-tool-add-a-tool-icon.md): A tool icon serves as a graphical representation of your tool in the user interface (UI). Follow this guidance to add... - [Adding Category and Tags for Tool](how-to-guides-develop-a-tool-add-category-and-tags-for-tool.md): This document is dedicated to guiding you through the process of categorizing and tagging your tools for optimal orga... - [Create and Use Tool Package](how-to-guides-develop-a-tool-create-and-use-tool-package.md): In this document, we will guide you through the process of developing your own tool package, offering detailed steps ... - [Creating Cascading Tool Inputs](how-to-guides-develop-a-tool-create-cascading-tool-inputs.md): Cascading input settings are useful when the value of one input field determines which subsequent inputs are shown. T... - [Creating a Dynamic List Tool Input](how-to-guides-develop-a-tool-create-dynamic-list-tool-input.md): Tool input options can be generated on the fly using a dynamic list. Instead of having predefined static options, the... - [Create and Use Your Own Custom Strong Type Connection](how-to-guides-develop-a-tool-create-your-own-custom-strong-type-connection.md): Connections provide a secure method for managing credentials for external APIs and data sources in prompt flow. This ... - [Customizing an LLM Tool](how-to-guides-develop-a-tool-customize-an-llm-tool.md): In this document, we will guide you through the process of customizing an LLM tool, allowing users to seamlessly conn... - [Develop a tool](how-to-guides-develop-a-tool.md): We provide guides on how to develop a tool and use it. - [Using File Path as Tool Input](how-to-guides-develop-a-tool-use-file-path-as-tool-input.md): Users sometimes need to reference local files within a tool to implement specific logic. To simplify this, we've intr... - [Use streaming endpoints deployed from prompt flow](how-to-guides-enable-streaming-mode.md): In prompt flow, you can [deploy flow as REST endpoint](./deploy-a-flow/index.md) for real-time inference. - [Execute flow as a function](how-to-guides-execute-flow-as-a-function.md): :::{admonition} Experimental feature - [Frequency asked questions (FAQ)](how-to-guides-faq.md): Prompt flow provides both stable and experimental features in the same SDK. - [How-to Guides](how-to-guides.md): Simple and short articles grouped by topics, each introduces a core feature of prompt flow and how you can use it to ... - [Installation](how-to-guides-installation.md): The prompt flow SDK and CLI are under active development, with regular stable releases on PyPI: - [Standalone CLI](how-to-guides-installation-standalone.md): :::{admonition} Experimental feature - [Manage connections](how-to-guides-manage-connections.md): [Connection](../../concepts/concept-connections.md) helps securely store and manage secret keys or other sensitive cr... - [Quick start](how-to-guides-quick-start.md): This guide will walk you through the first steps of the prompt flow code-first experience. - [Run and evaluate a flow](how-to-guides-run-and-evaluate-a-flow.md): After you have developed and tested the flow in [init and test a flow](../develop-a-dag-flow/init-and-test-a-flow.md)... - [Manage runs](how-to-guides-run-and-evaluate-a-flow-manage-runs.md): This documentation will walk you through how to manage your runs with CLI, SDK and VS Code Extension. - [Use column mapping](how-to-guides-run-and-evaluate-a-flow-use-column-mapping.md): In this document, we will introduce how to map inputs with column mapping when running a flow. - [Set promptflow configs](how-to-guides-set-promptflow-configs.md): :::{admonition} Experimental feature - [Tracing](how-to-guides-tracing.md): :::{admonition} Experimental feature - [Manage traces](how-to-guides-tracing-manage.md): :::{admonition} Experimental feature - [Visualize traces](how-to-guides-tracing-trace-ui.md): :::{admonition} Experimental feature - [Tune prompts using variants](how-to-guides-tune-prompts-with-variants.md): :::{admonition} Experimental feature - [Prompt flow](index.md): [**Prompt flow**](https://github.com/microsoft/promptflow) is a suite of development tools designed to streamline the... - [Integrations](integrations.md): The Integrations section contains documentation on custom extensions created by the community that expand prompt flow... - [Alternative LLMs](integrations-llms.md): This section provides tutorials on incorporating alternative large language models into prompt flow. - [Azure AI Language](integrations-tools-azure-ai-language-tool.md): Azure AI Language enables users with task-oriented and optimized pre-trained or custom language models to effectively... - [Custom Tools](integrations-tools.md): This section contains documentation for custom tools created by the community to extend Prompt flow's capabilities fo... - [LLMLingua Prompt Compression](integrations-tools-llmlingua-prompt-compression-tool.md): LLMLingua Prompt Compression tool enables you to speed up large language model's inference and enhance large language... - [Flow YAML Schema](reference-flow-yaml-schema-reference.md): :::{admonition} Experimental feature - [Reference](reference.md): **Current stable version:** - [pf](reference-pf-command-reference.md): Manage prompt flow resources with the prompt flow CLI. - [pfazure](reference-pfazure-command-reference.md): :::{admonition} Experimental feature - [Run YAML Schema](reference-run-yaml-schema-reference.md): :::{admonition} Experimental feature - [Azure OpenAI GPT-4 Turbo with Vision](reference-tools-reference-aoai-gpt4-turbo-vision.md): Azure OpenAI GPT-4 Turbo with Vision tool enables you to leverage your AzureOpenAI GPT-4 Turbo with Vision model depl... - [Content Safety (Text)](reference-tools-reference-contentsafety-text-tool.md): Azure Content Safety is a content moderation service developed by Microsoft that help users detect harmful content fr... - [Embedding](reference-tools-reference-embedding-tool.md): OpenAI's embedding models convert text into dense vector representations for various NLP tasks. See the [OpenAI Embed... - [Faiss Index Lookup](reference-tools-reference-faiss-index-lookup-tool.md): Faiss Index Lookup is a tool tailored for querying within a user-provided Faiss-based vector store. In combination wi... - [LLM](reference-tools-reference-llm-tool.md): Prompt flow LLM tool enables you to leverage widely used large language models like [OpenAI](https://platform.openai.... - [LLM Vision](reference-tools-reference-llm-vision-tool.md): Prompt flow LLM vision tool enables you to leverage your AzureOpenAI GPT-4 Turbo or OpenAI's GPT-4 with vision to ana... - [Open Model LLM](reference-tools-reference-open-model-llm-tool.md): The Open Model LLM tool enables the utilization of a variety of Open Model and Foundational Models, such as [Falcon](... - [OpenAI GPT-4V](reference-tools-reference-openai-gpt-4v-tool.md): OpenAI GPT-4V tool enables you to leverage OpenAI's GPT-4 with vision, also referred to as GPT-4V or gpt-4-vision-pre... - [Prompt](reference-tools-reference-prompt-tool.md): The Prompt Tool in PromptFlow offers a collection of textual templates that serve as a starting point for creating pr... - [Python](reference-tools-reference-python-tool.md): Users are empowered by the Python Tool to offer customized code snippets as self-contained executable nodes in Prompt... - [Rerank](reference-tools-reference-rerank-tool.md): Rerank is a semantic search tool that improves search quality with a semantic-based reranking system which can contex... - [SerpAPI](reference-tools-reference-serp-api-tool.md): The SerpAPI API is a Python tool that provides a wrapper to the [SerpAPI Google Search Engine Results API](https://se... - [Vector DB Lookup](reference-tools-reference-vector-db-lookup-tool.md): Vector DB Lookup is a vector search tool that allows users to search top k similar vectors from vector database. This... - [Trace Span Specification](reference-trace-span-spec-reference.md): :::{admonition} Experimental feature - [Tutorials](tutorials.md): This section contains a collection of flow samples and step-by-step tutorials.