> For the complete documentation index, see [llms.txt](https://docs.ondeva.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ondeva.com/workflow/steps-reference/ai-integration.md). # AI Integration Ondeva integrates AI directly into your workflows — allowing you to generate, extract, and analyze data using Large Language Models (LLMs) without needing to wire up external services. AI becomes just another building block in your application logic, enabling personalized automation, rich content generation, and powerful classification. All AI steps store their results in session variables or table entries, making them immediately usable in downstream logic, queries, and UI components. ### **Text to Variable** **Purpose:** Generates AI-powered text from a prompt and stores the result in a session variable. **Key Options:** * **Prompt**: The input text, question, or command given to the model (can include dynamic variables) * **Variable**: Name of the variable to store the result **When to Use:** * Generate product descriptions or summaries * Rephrase or complete user input * Dynamically fill message templates or notification content *** ### **Image to Content Field** **Purpose:** Generates an image based on a prompt and saves it into a specific field in a table entry. **Key Options:** * **Prompt**: Describes what the AI should generate * **Target Table, Entry ID, Field**: Where to store the resulting image **When to Use:** * Automatically generate hero or thumbnail images for new content * Create profile avatars or decorative assets from user prompts *** ### **Keywords Saved as List** **Purpose:** Extracts keywords from a text prompt and stores them as an array of strings in a variable. **Key Options:** * **Prompt**: Text to analyze (e.g., a blog post or support ticket) * **Variable**: Where the array of keywords will be saved **When to Use:** * Tag content for search or filtering * Analyze sentiment topics in support logs or survey data *** ### **Text Summarization** **Purpose:** Condenses a long input text into a shorter, coherent summary. **Key Options:** * **Prompt**: The original long-form text * **Variable**: Where the summary is stored **When to Use:** * Summarize meeting notes, emails, or documentation * Offer TL;DR versions of user-generated content *** ### **Audio to Text** **Purpose:** Transcribes an audio file into plain text using AI. **Key Options:** * **Variable**: Name of the session variable holding the audio input * **Target Table / Entry / Field**: Where to store the transcription result **When to Use:** * Process voice submissions (e.g., customer feedback, voice forms) * Extract speech from uploaded interviews or podcast clips *** ### Best practices: * AI prompts support full use of `{parameters_x}` and `{var_x}` references, allowing you to dynamically personalize inputs per user/session. * Results can be directly used in downstream steps like `Save Entry` or `Send Mail`. * Use **Text to Variable** before API calls or UI rendering to dynamically generate values based on live context. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter: ``` GET https://docs.ondeva.com/workflow/steps-reference/ai-integration.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.