Multi-Turn Conversation with Context

User Intent

"How do I maintain context across multiple questions? Show me conversation memory."

Operation

SDK Method: promptConversation() with conversation history Use Case: Contextual multi-turn Q&A

---

Code Example (TypeScript)

import { Graphlit } from 'graphlit-client';

const graphlit = new Graphlit();

// Create conversation
const conversation = await graphlit.createConversation({
  name: "Multi-turn Q&A"
});

const conversationId = conversation.createConversation.id;

// Turn 1
const response1 = await graphlit.promptConversation({
  prompt: "What are the main features of Graphlit?",
  id: conversationId
});
console.log('Q1:', response1.message.message);

// Turn 2 - context maintained
const response2 = await graphlit.promptConversation({
  prompt: "How does it compare to competitors?",  // "it" refers to Graphlit
  id: conversationId
});
console.log('Q2:', response2.message.message);

// Turn 3 - further refinement
const response3 = await graphlit.promptConversation({
  prompt: "What pricing options are available?",
  id: conversationId
});
console.log('Q3:', response3.message.message);

---

Key Features

Context Preservation: Conversation history maintained Pronoun Resolution: "it", "they" understood Follow-up Questions: Natural conversation flow Memory: Previous answers inform new responses

---