DeepSeek vs Qwen: local model showdown featuring LaunchDarkly AgentControl

import ollama from "ollama";
import "dotenv/config";
import launchDarkly from "@launchdarkly/node-server-sdk";
import launchDarklyAI from "@launchdarkly/server-sdk-ai";


const LD_CONFIG_KEY = "model-showdown";
const DEFAULT_CONFIG = {
 enabled: true,
 model: { name: "deepseek-r1:1.5b" },
 // double ??s so you know it fell back to the default value
 messages: [{ role: "user", content: "Why is the sky blue??" }],
};


// In a real app you'd fill in this example data
const userContext = {
 kind: "user",
 name: "Mark",
 email: "mark.s@lumonindustries.work",
 key: "example-user-key",
};


const ldClient = launchDarkly.init(process.env.LAUNCHDARKLY_SDK_KEY);
const ldAiClient = launchDarklyAI.initAi(ldClient);


// Wait for LaunchDarkly client to initialize
async function waitForLDClient() {
 return new Promise((resolve) => {
   ldClient.once("ready", () => {
     resolve();
   });
 });
}


function trackMetrics(tracker, response) {
 if (!response) return;


 tracker.trackSuccess();


 // ollama provides duration in nanoseconds but LaunchDarkly wants milliseconds
 const durationInMilliseconds = response.total_duration / 1_000_000;
 tracker.trackDuration(durationInMilliseconds);


 // Track token usage
 const tokens = {
   input: response.prompt_eval_count,
   output: response.eval_count,
   total: response.prompt_eval_count + response.eval_count,
 };
 tracker.trackTokens(tokens);
}


async function generate(options = {}) {
 /**
  * Generates text using a large language model.
  * @param {Object} options - Configuration options for the generation
  * @returns {Promise<string|null>} The generated text or null if an error occurs
  */
    await waitForLDClient();


 console.log("User context being evaluated:", userContext);


 const configValue = await ldAiClient.completionConfig(
   LD_CONFIG_KEY,
   userContext,
   DEFAULT_CONFIG,
   options
 );
 console.log("configValue: ", configValue);
 const { model, tracker, messages = [] } = configValue;


 try {
   const response = await ollama.chat({
     model: model.name,
     messages,
   });
   console.log(response);
   trackMetrics(tracker, response);
   return response;
 } catch (error) {
   tracker.trackError(error);
   console.error("Error generating AI response:", error);
   return null;
 }
}
generate();