Skip to main content
The Assistants API will be deprecated in a future release.For new projects, we recommend using the Agents API. The Agents API provides native Vercel AI SDK compatibility and removes custom transformations.See the migration guide to learn about the differences.
This guide explains how to migrate Assistants from one Langdock workspace to another using the Assistant API. This is useful when you want to replicate assistant configurations across different workspaces, move assistants during organizational restructuring, or create backup copies of your assistants.

​
Overview

The migration process involves two main steps:
  1. Export: Retrieve the Assistant configuration from the source workspace using the assistant Get API
  2. Import: Create a new Assistant in the target workspace using the assistant Create API

​
Prerequisites

Before you begin, ensure you have:
  1. Two API keys with AGENT_API scope:
    • One API key for the source workspace (where the Assistant currently exists)
    • One API key for the target workspace (where you want to migrate the Assistant)
  2. Access to the Assistant: Your source workspace API key must have access to the assistant you want to migrate
  3. Matching resources in target workspace (if applicable):
    • The model will need to be manually adjusted in the Langdock UI after migration
    • If the Assistant uses custom actions, those integrations must be enabled in the target workspace
    • Attachments need to be re-uploaded separately (they are not transferred automatically)

​
Step 1: Export the Assistant from Source Workspace

Use the Assistant Get API to retrieve the complete configuration of your assistant: 
const axios = require("axios");

async function getAssistantFromSource(assistantId, sourceApiKey) {
  const response = await axios.get(
    "https://api.langdock.com/assistant/v1/get",
    {
      params: {
        assistantId: assistantId
      },
      headers: {
        Authorization: `Bearer ${sourceApiKey}`
      }
    }
  );

  return response.data.Assistant;
}

​
Understanding the Response

The Get API returns the complete Assistant configuration including:
  • name, description, instruction - The Assistant’s identity and system prompt
  • emojiIcon - The emoji icon displayed for the Assistant
  • model - UUID of the model being used
  • temperature - Creativity setting (0-1)
  • conversationStarters - Suggested prompts for users
  • inputType - Either “PROMPT” or “STRUCTURED”
  • inputFields - Form field definitions (for STRUCTURED input type)
  • webSearchEnabled, imageGenerationEnabled, codeInterpreterEnabled, canvasEnabled - Capability flags
  • actions - Custom integration actions
  • attachments - UUIDs of attached files

​
Step 2: Transform the Configuration

The Get API response uses slightly different field names than the Create API expects. You need to map the fields: 
function transformForCreate(sourceAssistant) {
  return {
    // Basic information
    name: sourceAssistant.name,
    description: sourceAssistant.description || undefined,
    emoji: sourceAssistant.emojiIcon || undefined,
    instruction: sourceAssistant.instruction || undefined,
    
    // Settings
    creativity: sourceAssistant.temperature,
    inputType: sourceAssistant.inputType,
    conversationStarters: sourceAssistant.conversationStarters || [],
    
    // Capabilities
    webSearch: sourceAssistant.webSearchEnabled,
    imageGeneration: sourceAssistant.imageGenerationEnabled,
    dataAnalyst: sourceAssistant.codeInterpreterEnabled,
    canvas: sourceAssistant.canvasEnabled,
    
    // Input fields (for STRUCTURED input type)
    inputFields: sourceAssistant.inputFields || [],
    
    // Note: actions and attachments require special handling (see below)
  };
}

​
Field Mapping Reference

Get API Response FieldCreate API Request Field
namename
descriptiondescription
emojiIconemoji
instructioninstruction
temperaturecreativity
inputTypeinputType
conversationStartersconversationStarters
webSearchEnabledwebSearch
imageGenerationEnabledimageGeneration
codeInterpreterEnableddataAnalyst
canvasEnabledcanvas
inputFieldsinputFields
actionsactions
attachmentsattachments

​
Step 3: Create the Assistant in Target Workspace

Use the Assistant Create API to create the assistant in the target workspace: 
async function createAssistantInTarget(assistantConfig, targetApiKey) {
  const response = await axios.post(
    "https://api.langdock.com/assistant/v1/create",
    AssistantConfig,
    {
      headers: {
        Authorization: `Bearer ${targetApiKey}`,
        "Content-Type": "application/json"
      }
    }
  );

  return response.data.Assistant;
}

​
Complete Migration Script

Here’s a complete script that combines all steps: 
const axios = require("axios");

// Configuration
const SOURCE_API_KEY = "your-source-workspace-api-key";
const TARGET_API_KEY = "your-target-workspace-api-key";
const AGENT_ID_TO_MIGRATE = "550e8400-e29b-41d4-a716-446655440000";

async function migrateAssistant() {
  try {
    // Step 1: Get Assistant from source workspace
    console.log("Fetching Assistant from source workspace...");
    const getResponse = await axios.get(
      "https://api.langdock.com/assistant/v1/get",
      {
        params: { assistantId: AGENT_ID_TO_MIGRATE },
        headers: { Authorization: `Bearer ${SOURCE_API_KEY}` }
      }
    );
    
    const sourceAssistant = getResponse.data.assistant;
    console.log(`Found Assistant: "${sourceassistant.name}"`);

    // Step 2: Transform configuration for Create API
    const createConfig = {
      name: sourceAssistant.name,
      description: sourceAssistant.description || undefined,
      emoji: sourceAssistant.emojiIcon || undefined,
      instruction: sourceAssistant.instruction || undefined,
      creativity: sourceAssistant.temperature,
      inputType: sourceAssistant.inputType,
      conversationStarters: sourceAssistant.conversationStarters || [],
      webSearch: sourceAssistant.webSearchEnabled,
      imageGeneration: sourceAssistant.imageGenerationEnabled,
      dataAnalyst: sourceAssistant.codeInterpreterEnabled,
      canvas: sourceAssistant.canvasEnabled,
      inputFields: sourceAssistant.inputFields || [],
      // Note: actions and attachments excluded - see "Handling Special Cases"
    };

    // Remove undefined values
    Object.keys(createConfig).forEach(key => {
      if (createConfig[key] === undefined) {
        delete createConfig[key];
      }
    });

    // Step 3: Create Assistant in target workspace
    console.log("Creating Assistant in target workspace...");
    const createResponse = await axios.post(
      "https://api.langdock.com/assistant/v1/create",
      createConfig,
      {
        headers: {
          Authorization: `Bearer ${TARGET_API_KEY}`,
          "Content-Type": "application/json"
        }
      }
    );

    const newAssistant = createResponse.data.assistant;
    console.log(`Migration successful!`);
    console.log(`New Assistant ID: ${newassistant.id}`);
    console.log(`Assistant name: ${newassistant.name}`);
    
    return newAssistant;

  } catch (error) {
    if (error.response) {
      console.error(`Error ${error.response.status}: ${JSON.stringify(error.response.data)}`);
    } else {
      console.error("Error:", error.message);
    }
    throw error;
  }
}

migrateAssistant();

​
Handling Special Cases

​
Actions (Custom Integrations)

Actions reference integrations that must be enabled in the target workspace. Action UUIDs are specific to each workspace’s integration setup.
Exclude actions from the initial migration and manually configure them in the target workspace after the Assistant is created.

​
Attachments

Attachment UUIDs reference files stored in the source workspace. These files are not automatically transferred. To migrate attachments:
  1. Download the files from the source workspace
  2. Re-upload them to the target workspace using the Upload Attachment API
  3. Update the Assistant with the new attachment UUIDs

​
OAuth Connections

Pre-selected OAuth connections are not supported via the API. Users must configure OAuth connections through the Langdock UI after migration.

​
Migrating Multiple Assistants

To migrate multiple Assistants, simply loop through a list of assistant IDs: 
const AGENT_IDS = [
  "Assistant-uuid-1",
  "Assistant-uuid-2",
  "Assistant-uuid-3"
];

async function migrateMultipleAssistants() {
  const results = [];
  
  for (const assistantId of AGENT_IDS) {
    try {
      console.log(`\nMigrating Assistant: ${assistantId}`);
      const newAssistant = await migrateassistant(assistantId);
      results.push({ 
        sourceId: assistantId, 
        targetId: newAssistant.id, 
        status: "success" 
      });
    } catch (error) {
      results.push({ 
        sourceId: assistantId, 
        status: "failed", 
        error: error.message 
      });
    }
  }
  
  console.log("\n=== Migration Summary ===");
  console.table(results);
}

​
Post-Migration Checklist

After migrating an Assistant, verify the following in the target workspace:
  • Assistant appears in the assistants list with correct name and emoji
  • Description and instructions are correctly transferred
  • Conversation starters are present
  • Capabilities (web search, image generation, etc.) are correctly enabled
  • Input fields are properly configured (for STRUCTURED input type)
  • Manually configure any OAuth connections through the UI
  • Re-upload and attach any necessary files
  • Configure custom actions/integrations if needed
  • Test the Assistant by sending a message

​
Limitations

Keep these limitations in mind when planning your migration:
  1. Attachments are not transferred - Files must be re-uploaded to the target workspace
  2. Actions may need reconfiguration - Integration action UUIDs are workspace-specific
  3. OAuth connections require manual setup - Cannot be configured via API
  4. Models require manual adjustment - The Assistant will use the workspace default model; adjust manually in the UI after migration
  5. Conversation history is not migrated - Only the Assistant configuration is transferred

​
Migrating to Agents API

The new Agents API offers improved compatibility with modern AI SDKs. The migration process is similar with updated parameter names. See the equivalent guide in the Agents API:
Langdock intentionally blocks browser-origin requests to protect your API key and ensure your applications remain secure. For more information, please see our guide on API Key Best Practices.