Skip to content
Divinci AI SDK

Quick Start

Copy page

This page gets a working integration in front of you fast. Pick the package that matches where your code runs — see Introduction if you’re unsure.

Browser chat — Client SDK

Section titled “Browser chat — Client SDK”

The client works in terms of threads: you open a chat thread, then send or stream messages into it.

  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_...", // for browsers in production, prefer a user token — see Authentication
    });

  3. Open a thread and stream a reply

    const thread = await client.chat.create();
    

    const reply = await client.chat.stream(thread.id, "Hello, how can you help me?", {
      assistantName: "your-assistant-id", // the release's assistant/model id
      onChunk: (text) => process.stdout.write(text),
    });
    console.log(reply.content);

Why stream() and not send()?

Section titled “Why stream() and not send()?”

Replies are generated asynchronously: chat.send() returns an acknowledgement while generation continues server-side. chat.stream() holds the connection and resolves with the assistant’s message — it’s the right default. To fetch history later, use chat.getTranscript(thread.id).

Server-side operations — Server SDK

Section titled “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 a document to a knowledge base

Section titled “Upload a document to a knowledge base”

RAG documents belong to a collection (a vector index) inside a workspace. Create the collection, then upload a file buffer to it:

import { readFileSync } from "node:fs";


const collection = await divinci.rag.createCollection({
  workspaceId: workspace.id,
  name: "Product docs",
});


const file = readFileSync("./knowledge.pdf");


const doc = await divinci.rag.uploadDocument(
  workspace.id,
  collection.id,
  file,
  "knowledge.pdf",
  { mimeType: "application/pdf" },
);


// Wait for chunking + embedding to finish before querying
await divinci.rag.waitForProcessing(workspace.id, collection.id, doc.id);

MCP integration — MCP SDK

Section titled “MCP integration — MCP SDK”
import { McpClient } from "@divinci-ai/mcp";


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


await mcp.connect();


// Tool discovery and invocation live on the `tools` accessor
const tools = await mcp.tools.listTools();


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

Next steps

Section titled “Next steps”