Fireworks AI

npm install @llamaindex/fireworks

import { FireworksLLM } from "@llamaindex/fireworks";

const llm = new FireworksLLM({
  model: "accounts/fireworks/models/llama-v3p1-70b-instruct",
  apiKey: process.env.FIREWORKS_API_KEY
});

const response = await llm.chat({
  messages: [
    { role: "user", content: "Explain quantum computing" }
  ]
});

console.log(response.message.content);

import { FireworksEmbedding } from "@llamaindex/fireworks";

const embedModel = new FireworksEmbedding({
  model: "nomic-ai/nomic-embed-text-v1.5",
  apiKey: process.env.FIREWORKS_API_KEY
});

const embedding = await embedModel.getTextEmbedding(
  "LlamaIndex is a data framework for LLM applications"
);

const stream = await llm.chat({
  messages: [{ role: "user", content: "Write a story about AI" }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.delta);
}

import { tool } from "@llamaindex/core/tools";
import { z } from "zod";

const weatherTool = tool({
  name: "get_weather",
  description: "Get current weather",
  parameters: z.object({
    location: z.string(),
    units: z.enum(["celsius", "fahrenheit"]).optional()
  }),
  execute: async ({ location, units = "celsius" }) => {
    return `Weather in ${location}: 22°${units === "celsius" ? "C" : "F"}`;
  }
});

const llm = new FireworksLLM({
  model: "accounts/fireworks/models/llama-v3p1-70b-instruct"
});

const response = await llm.chat({
  messages: [{ role: "user", content: "What's the weather in Tokyo?" }],
  tools: [weatherTool]
});

import { z } from "zod";

const schema = z.object({
  name: z.string(),
  age: z.number(),
  interests: z.array(z.string())
});

const result = await llm.exec({
  messages: [{ role: "user", content: "Extract info: John is 30 and likes coding, hiking" }],
  responseFormat: schema
});

import { Settings, VectorStoreIndex } from "llamaindex";
import { FireworksLLM, FireworksEmbedding } from "@llamaindex/fireworks";

Settings.llm = new FireworksLLM({
  model: "accounts/fireworks/models/llama-v3p1-70b-instruct"
});

Settings.embedModel = new FireworksEmbedding({
  model: "nomic-ai/nomic-embed-text-v1.5"
});

const index = await VectorStoreIndex.fromDocuments(documents);
const queryEngine = index.asQueryEngine();

const response = await queryEngine.query({
  query: "What are the main features?"
});

import { fireworks } from "@llamaindex/fireworks";

const llm = fireworks({
  model: "accounts/fireworks/models/llama-v3p1-8b-instruct"
});

FIREWORKS_API_KEY=fw_...

const llm = new FireworksLLM({
  additionalSessionOptions: {
    baseURL: "https://custom-fireworks-endpoint.com/inference/v1"
  }
});

import { Settings } from "llamaindex";
import { FireworksLLM } from "@llamaindex/fireworks";

Settings.llm = new FireworksLLM({
  model: "accounts/fireworks/models/llama-v3p1-70b-instruct"
});

const startTime = Date.now();

const response = await llm.chat({
  messages: [{ role: "user", content: "Explain AI" }]
});

const duration = Date.now() - startTime;
console.log(`Response time: ${duration}ms`);

try {
  const response = await llm.chat({ messages });
} catch (error) {
  if (error.message.includes("FIREWORKS_API_KEY")) {
    console.error("API key not set or invalid");
  } else if (error.status === 429) {
    console.error("Rate limit exceeded");
  } else {
    console.error("API error:", error.message);
  }
}

try {
  const response = await llm.chat({ messages });
} catch (error) {
  if (error.status === 429) {
    console.log("Rate limit hit, waiting...");
    await new Promise(resolve => setTimeout(resolve, 1000));
    // Retry logic
  }
}

import { VectorStoreIndex, Settings } from "llamaindex";
import { FireworksLLM, FireworksEmbedding } from "@llamaindex/fireworks";

// Configure both LLM and embeddings
Settings.llm = new FireworksLLM({
  model: "accounts/fireworks/models/llama-v3p1-70b-instruct",
  temperature: 0.1
});

Settings.embedModel = new FireworksEmbedding({
  model: "nomic-ai/nomic-embed-text-v1.5"
});

// Build index
const index = await VectorStoreIndex.fromDocuments(documents);

// Query
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({
  query: "What are the key insights?"
});