forked from sheetjs/docs.sheetjs.com
45 lines
1.5 KiB
JavaScript
45 lines
1.5 KiB
JavaScript
import { ChatOllama, OllamaEmbeddings } from "@langchain/ollama";
|
|
import { MemoryVectorStore } from "langchain/vectorstores/memory";
|
|
import { SelfQueryRetriever } from "langchain/retrievers/self_query";
|
|
import { FunctionalTranslator } from "@langchain/core/structured_query";
|
|
|
|
import LoadOfSheet from "./loadofsheet.mjs";
|
|
|
|
let s = 0, spin = ['\\', '|', '/', '-'];
|
|
setInterval(() => { process.stderr.write(spin[s = ++s % spin.length] + '\u001b[0G'); }, 100).unref();
|
|
process.on('exit', function() { process.stderr.write('\u001b[2K'); });
|
|
|
|
// const model = "llama3-chatqa:8b-v1.5-q8_0";
|
|
const model = "phi4:14b";
|
|
|
|
console.log(`Using model ${model}`);
|
|
|
|
const llm = new ChatOllama({ baseUrl: "http://127.0.0.1:11434", model });
|
|
const embeddings = new OllamaEmbeddings({model});
|
|
|
|
console.time("load of sheet");
|
|
const loader = new LoadOfSheet("./cd.xls");
|
|
const docs = await loader.load();
|
|
console.timeEnd("load of sheet");
|
|
|
|
console.time("vector store");
|
|
const vectorStore = await MemoryVectorStore.fromDocuments(docs, embeddings);
|
|
console.timeEnd("vector store");
|
|
|
|
console.time("query");
|
|
const selfQueryRetriever = SelfQueryRetriever.fromLLM({
|
|
llm,
|
|
vectorStore,
|
|
documentContents: "Data rows from a worksheet",
|
|
attributeInfo: loader.attributes,
|
|
structuredQueryTranslator: new FunctionalTranslator(),
|
|
searchParams: { k: 1024 } // default is 4
|
|
});
|
|
|
|
const res = await selfQueryRetriever.invoke(
|
|
"Which rows have over 40 miles per gallon?"
|
|
);
|
|
console.timeEnd("query");
|
|
|
|
res.forEach(({metadata}) => { console.log({ Name: metadata.Name, MPG: metadata.Miles_per_Gallon }); });
|