This post has been republished via RSS; it originally appeared at: Microsoft Tech Community - Latest Blogs - .
Prompt flow in Azure AI Studio is a development tool designed to streamline the entire development cycle of AI applications powered by Large Language Models (LLMs). Last Ignite, we announced Azure AI Language prompt flow available on GitHub. Today, we are excited to announce that Azure AI Language tooling is now available in prompt flow natively. With that, you can explore, quickly start to use and fine-tune various natural language processing capabilities from Azure AI Language, reducing your time to valueand deploying solutions with reliable evaluation.
The Azure AI Language sample flows in Azure AI prompt flow gallery are good starting point for you. You can simply start by cloning one of the two sample flows:
- Analyze Documents: This flow is designed to analyze and extract insights from textual document input, such as identifying named entities, redacting Personal Identifiable Information (PII), analyzing sentiments, summarizing main points and translating to other languages.
- Analyze Conversations: This flow is designed for conversational input and particularly useful for contact center analytics or meeting review, such as summarizing customer issues and resolution, analyzing customer sentiment trend during calls, redacting PII, chaptering long meeting into segments making it easy to navigate and find topics of interest.
Then you will see a wizard that guides you to configure tools in your flow, and run, evaluate, and deploy your flow:
- Graph view of your flow
- Files in your flow
- Azure AI Language tools in the “More tools” dropdown menu, which you can add capabilities that you need for your flow. There are more tools that you can add from LLM, Prompt, and Python menu.
- Configure output
- Configure steps (or tools) in the flow
- Run, evaluate, and deploy your flow
What’s Next
We will continue enhancing the underlying capabilities by leveraging state-of-the-art SLMs and LLMs, and enriching prompt flow offerings to further ease your effort in utilizing the best service Azure AI offers.
Learn more about Azure AI Language in the following resources:
- Azure AI Language homepage: https://aka.ms/azure-language
- Azure AI Language product documentation: https://aka.ms/language-docs
- Azure AI Language product demo videos: https://aka.ms/language-videos
- Explore Azure AI Language in Azure AI Studio: https://aka.ms/AzureAiLanguage
- Prompt flow in Azure AI Studio: https://learn.microsoft.com/en-us/azure/ai-studio/how-to/prompt-flow
- PyPl package (includes general documentation): promptflow-azure-ai-language · PyPI
- Azure AI Language prompt flow github examples (includes READMEs): promptflow/examples/flows/integrations/azure-ai-language at main · microsoft/promptflow · GitHub