AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
TypeScript ai-agentai-agent-toolsai-agentsai-agents-frameworkmcpmcp-servermcp-toolsmcpsn8n-alternativeno-code-automationworkflowworkflow-automationworkflows
feat(ai): ui improvement (#16362)
Talal Jaber01d2484265f2
diff --git a/bun.lock b/bun.lockindex 11ba8204608..95841cefe31 100644--- a/bun.lock+++ b/bun.lock@@ -349,7 +349,7 @@},"packages/pieces/community/ai": {"name": "@activepieces/piece-ai",- "version": "0.13.1",+ "version": "0.14.0","dependencies": {"@activepieces/core-piece-types": "workspace:*","@activepieces/core-utils": "workspace:*",diff --git a/packages/pieces/community/ai/package.json b/packages/pieces/community/ai/package.jsonindex 6f71387d99a..dd253bd6ca5 100644--- a/packages/pieces/community/ai/package.json+++ b/packages/pieces/community/ai/package.json@@ -1,6 +1,6 @@{"name": "@activepieces/piece-ai",- "version": "0.13.1",+ "version": "0.14.0","type": "commonjs","main": "./dist/src/index.js","types": "./dist/src/index.d.ts",diff --git a/packages/pieces/community/ai/src/lib/actions/image/generate-image.ts b/packages/pieces/community/ai/src/lib/actions/image/generate-image.tsindex e9ab58a4a7b..4082660e913 100644--- a/packages/pieces/community/ai/src/lib/actions/image/generate-image.ts+++ b/packages/pieces/community/ai/src/lib/actions/image/generate-image.ts@@ -22,6 +22,22 @@ export const generateImageAction = createAction({displayName: 'Generate Image',description: 'Create or edit images from a text description.',aiMetadata: { description: 'Generates an image from a text prompt with an image-capable model and writes it out as a flow file; when Input Images are attached and the model supports editing, it edits, varies, or merges those images instead of generating from scratch. Pick it for any image creation or edit step; use askAi or run_agent when you need text output. Requires a prompt plus an image-capable provider/model, and input images fail on a model that cannot accept them; not idempotent, as each call generates and stores a new image file.', idempotent: false },+ propertyGroups: [+ {+ key: 'ai_model',+ display: 'section',+ label: 'AI Model',+ icon: 'sliders',+ props: ['provider', 'model'],+ },+ {+ key: 'image',+ display: 'section',+ label: 'Image',+ icon: 'file',+ props: ['prompt', 'inputImages', 'advancedOptions'],+ },+ ],props: {provider: aiProps({ modelType: 'image' }).provider,model: aiProps({ modelType: 'image' }).model,diff --git a/packages/pieces/community/ai/src/lib/actions/text/ask-ai.ts b/packages/pieces/community/ai/src/lib/actions/text/ask-ai.tsindex 6e07304e711..ca5d17e9530 100644--- a/packages/pieces/community/ai/src/lib/actions/text/ask-ai.ts+++ b/packages/pieces/community/ai/src/lib/actions/text/ask-ai.ts@@ -10,6 +10,22 @@ export const askAI = createAction({displayName: 'Ask AI',description: 'Ask AI to analyze, explain, draft or decide using your flow data.',aiMetadata: { description: 'Sends a free-form prompt to a text model and returns its answer, optionally continuing a multi-turn thread via a Conversation Key or grounding the reply with web search. Pick it for open-ended reasoning, drafting, or judgement over flow data; prefer summarizeText to condense text, classifyText for a fixed label set, extractStructuredData for typed fields, or run_agent when the task needs tools and multiple steps. Requires a provider/model plus a prompt; not idempotent, since each call generates a fresh answer and a Conversation Key appends the exchange to stored history.', idempotent: false },+ propertyGroups: [+ {+ key: 'ai_model',+ display: 'section',+ label: 'AI Model',+ icon: 'sliders',+ props: ['provider', 'model'],+ },+ {+ key: 'request',+ display: 'section',+ label: 'Request',+ icon: 'text',+ props: ['prompt', 'conversationKey', 'webSearch', 'webSearchOptions'],+ },+ ],props: {provider: aiProps({ modelType: 'text' }).provider,model: aiProps({ modelType: 'text' }).model,@@ -28,6 +44,10 @@ export const askAI = createAction({displayName: 'Creativity',required: false,description: 'From 0 to 100. Lower is focused, higher is creative.',+ display: 'stepper',+ min: 0,+ max: 100,+ step: 10,advanced: true,}),maxOutputTokens: Property.Number({diff --git a/packages/pieces/community/ai/src/lib/actions/utility/extract-structured-data.ts b/packages/pieces/community/ai/src/lib/actions/utility/extract-structured-data.tsindex 5e9068b40ea..2b61238f3b6 100644--- a/packages/pieces/community/ai/src/lib/actions/utility/extract-structured-data.ts+++ b/packages/pieces/community/ai/src/lib/actions/utility/extract-structured-data.ts@@ -11,6 +11,29 @@ export const extractStructuredData = createAction({displayName: 'Extract Structured Data',description: 'Pull names, amounts and other fields from text, images or PDFs.',aiMetadata: { description: 'Pulls typed fields out of unstructured input (text, images or PDFs) against a schema supplied either in simple mode, a list of field definitions, or advanced mode, a raw JSON Schema. Pick it when you need specific named values from documents such as invoices, receipts or emails; use classifyText for a single label, summarizeText for prose condensation, or askAi for open-ended analysis. At least one of Text or Files is required or the step throws; read-only and idempotent.', idempotent: true },+ propertyGroups: [+ {+ key: 'ai_model',+ display: 'section',+ label: 'AI Model',+ icon: 'sliders',+ props: ['provider', 'model'],+ },+ {+ key: 'source',+ display: 'section',+ label: 'Extract from',+ icon: 'file',+ props: ['text', 'files'],+ },+ {+ key: 'output',+ display: 'section',+ label: 'Data to extract',+ icon: 'tag',+ props: ['prompt', 'mode', 'schema'],+ },+ ],props: {provider: aiProps({ modelType: 'text' }).provider,model: aiProps({ modelType: 'text' }).model,