Fireworks LLM
Fireworks.ai focus on production use cases for open source LLMs, offering speed and quality.
Usage
import { FireworksLLM, serviceContextFromDefaults } from "llamaindex";
const fireworksLLM = new FireworksLLM({
apiKey: "<YOUR_API_KEY>",
});
const serviceContext = serviceContextFromDefaults({ llm: fireworksLLM });
Load and index documents
For this example, we will load the Berkshire Hathaway 2022 annual report pdf
const reader = new PDFReader();
const documents = await reader.loadData("../data/brk-2022.pdf");
// Split text and create embeddings. Store them in a VectorStoreIndex
const index = await VectorStoreIndex.fromDocuments(documents, {
serviceContext,
});
Query
const queryEngine = index.asQueryEngine();
const response = await queryEngine.query({
query: "What mistakes did Warren E. Buffett make?",
});