Conversations

Conversations allow you to exchange multiple messages with AI that maintains them in its context. Conversations can be extended by external context sources like websites or files, and have the ability to refer to editor content and suggest modifications.

Upload PDFs, Word docs, and images for the AI to read and understand. Ask questions about specific sections and get intelligent answers. The AI extracts text while preserving structure from PDFs, maintains formatting context from Word documents, parses web content from HTML files, and processes images with OCR and object recognition.

Each conversation builds on previous messages, so the AI keeps track of your entire discussion and any files you have shared. You can mix documents, images, web links, and text in one conversation, and the AI connects information across all formats. Enable web search for real-time research while keeping your conversation context.

1. Upload product spec → “What are the key features for marketing?”
2. Add competitor analysis → “How do we compare to competitors?”
3. Reference blog post → “Write a press release using this blog post and our competitive advantages”
4. Include brand guidelines → “Match our brand voice and key messaging”

The AI remembers everything you have shared and builds on it throughout your conversation.

Enable real-time web search to access current information during conversations. The AI searches the web for relevant content, processes and analyzes the results, and integrates findings into responses while maintaining conversation context. Configure via the webSearch capability in API requests.

Enable step-by-step reasoning to see the AI’s problem-solving process. The AI breaks down complex queries into logical steps, considers multiple approaches, and can revise conclusions when new information emerges. Configure via the reasoning capability in API requests.

For complete API documentation including endpoints, parameters, and response schemas, see the REST API documentation.

POST /v1/conversations
Content-Type: application/json
Authorization: Bearer <your-token>

{
  "id": "my-conversation-123",
  "title": "Document Analysis Session",
  "group": "research"
}

Before you can reference documents in conversations, you need to upload them first:

POST /v1/conversations/my-conversation-123/documents
Content-Type: multipart/form-data
Authorization: Bearer <your-token>

file: [your-document.pdf]

Response:

{
  "id": "doc-123",
}

You can see how to upload other resources, including web resources and files using REST API documentation.

POST /v1/conversations/my-conversation-123/messages
Content-Type: application/json
Authorization: Bearer <your-token>

{
  "prompt": "Analyze the attached document and provide a summary of the key points",
  "model": "agent-1",
  "content": [
    {
      "type": "document",
      "id": "doc-123"
    }
  ],
  "capabilities": {
    "webSearch": {},
    "reasoning": {}
  }
}

POST /v1/conversations/my-conversation-123/messages
Content-Type: application/json
Authorization: Bearer <your-token>

{
  "prompt": "Compare the attached document with the information from the web resource",
  "model": "agent-1",
  "content": [
    {
      "type": "document",
      "id": "doc-123"
    },
    {
      "type": "web-resource",
      "id": "web-123"
    },
  ],
  "capabilities": {
    "webSearch": {}
  }
}

Conversations use Server-Sent Events (SSE) for real-time streaming responses. See the Streaming Responses guide for detailed implementation information and code examples.

• Reviews – Content quality analysis and improvement suggestions.
• Actions – Content transformation and batch processing.
• AI Models – Choosing the right AI model for your conversations.
• Streaming Responses – Implementing real-time conversation features.