Model API guide

Model Guide for you to implement FLock model

Pre-requirement

Manual creation via website

• Generate API Key via Acquiring the API Key

• Create Model via Model Customisation

Technology Stack

• TypeScript

• JavaScript

API Call example

Conversational Rag Chat

RAG chat with a conversation history.

POST/chat/conversational_rag_chat

Authorization

APIKeyHeader

Body

application/json

question*Question

chat_historyChat History

array of array of stringarray of any

knowledge_source_id*Knowledge Source Id

Response

200422

Successful Response

Body

application/json

answer*Answer

source_docs*Source Docs

generated_question*Generated Question

Request

JavaScriptCurlPythonHTTP

const response = await fetch('/chat/conversational_rag_chat', {
    method: 'POST',
    headers: {
      "Content-Type": "application/json"
    },
    body: JSON.stringify({
      "question": "text",
      "knowledge_source_id": "text"
    }),
});
const data = await response.json();

Response

200422

{
  "answer": "text",
  "source_docs": [
    []
  ],
  "generated_question": "text"
}

How it Works

Setup

Package installation

npm install --save axios dotenv
# or
yarn add axios dotenv
# or 
pnpm add axios dotenv

.env

• Create an .env file in the root directory or in your existing env file, add the followings:

// Some code
FLOCK_BOT_API_KEY= "<your_wallet_address_from_api_generation>"
FLOCK_BOT_ENDPOINT="https://rag-chat-ml-backend-prod.flock.io"

Step by Step guide

• Create a flockModel.ts

• Create a async/await function flockModel wrapping the API call

  • use axios.post method for request

  • We will pass two parameters

    • question

    • knowledge_source_id

  • get the response of the call

  • We chose to use try/catch to handle any error during the call to debug the process.

import axios from "axios";
import * as dotenv from "dotenv";

// Load environment variables from .env file
dotenv.config({ path: "./.env" }); // Make sure the path is correct

async function main(prompt: string) {
  console.log("Prompt:", prompt);

  try {
    // Construct the request payload
    const payload = {
      question: prompt,
      chat_history: [],
      knowledge_source_id: "<model_id>", // replace with your model id
    };

    // Set the headers
    const headers = {
      "x-api-key": process.env.FLOCK_BOT_API_KEY, // Ensure API key is set in .env
    };

    // Send POST request using axios
    const response = await axios.post(
      `${endpoint}/chat/conversational_rag_chat`,
      payload,
      {
        headers,
      }
    );


    // Output the response data
    console.log(response.data);
  } catch (error) {
    console.error("Error:", error);
  }
}

// Example call to the main function
main("Can you figure out how to make a chatbot?");