Skip to content
Divinci AI SDK

Quick Start

Quick Start

Get up and running with Divinci AI in minutes.

Browser Chat (Client SDK)

  1. Install the package

    Terminal window
    npm install @divinci-ai/client

  2. Initialize the client

    import { DivinciClient } from "@divinci-ai/client";
    

    const client = new DivinciClient({
      releaseId: "rel_your-release-id",
      apiKey: "divinci_key_...",
    });

  3. Send a message

    const response = await client.chat.send("Hello, how can you help me?");
    console.log(response.content);

Streaming Responses

for await (const chunk of client.chat.stream("Tell me a story")) {
  process.stdout.write(chunk.content);
}

Server-Side Operations (Server SDK)

  1. Install the package

    Terminal window
    npm install @divinci-ai/server

  2. Initialize the client

    import { DivinciServer } from "@divinci-ai/server";
    

    const divinci = new DivinciServer({
      apiKey: process.env.DIVINCI_API_KEY,
    });

  3. Create a workspace

    const workspace = await divinci.workspaces.create({
      name: "My AI Assistant",
    });

Upload Documents

await divinci.rag.uploadDocument({
  workspaceId: workspace._id,
  ragVectorId: "rag_xyz",
  file: fs.createReadStream("./knowledge.pdf"),
});

MCP Integration

  1. Install the package

    Terminal window
    npm install @divinci-ai/mcp

  2. Connect to the server

    import { McpClient } from "@divinci-ai/mcp";
    

    const client = new McpClient({
      serverUrl: "https://mcp.divinci.app",
      apiKey: "divinci_key_...",
    });
    

    await client.connect();

  3. Use tools

    const tools = await client.listTools();
    const result = await client.callTool("search_knowledge", {
      query: "return policy",
    });

Next Steps