How to add prompt here

[lakshya29154]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

import * as fs from "fs";
import { JsonSpec } from "langchain/tools";
import { createOpenApiAgent, OpenApiToolkit } from "langchain/agents";
import { OpenAI } from "@langchain/openai";
import { config } from "dotenv";
import { getPromptTemplateFromKey } from "langchain/retrievers/hyde";

config();
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const prompt = PromptTemplate.fromTemplate("I am given you the documentation, find the relevant API URLs there can be multiple url so give all the url step by step give the response and call you also give method with it.You should build the API URLs in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.");
async function generateAPIEndpoints(specFilePath) {
  let data;
  try {
    const jsonFile = fs.readFileSync(specFilePath, "utf8");
    data = JSON.parse(jsonFile);
    if (!data) {
      throw new Error("Failed to load OpenAPI spec");
    }
  } catch (e) {
    console.error(e);
    return;
  }

  const headers = {
    "Content-Type": "application/json",
    Authorization: `Bearer ${process.env.OPENAI_API_KEY}`,
  };
  const model = new OpenAI({ temperature: 0, apiKey: OPENAI_API_KEY });
  const toolkit = new OpenApiToolkit(new JsonSpec(data), model, headers,prompt);
  const executor = createOpenApiAgent(model, toolkit);

  const input = `Generate a list of API endpoints in the correct order to first add a new pet, then find the pet by ID, and finally delete the pet.`;
  console.log(`Executing with input "${input}"...`);

  const result = await executor.invoke({ input });
  console.log(`Got output ${result.output}`);

  console.log(
    `Got intermediate steps ${JSON.stringify(
      result.intermediateSteps,
      null,
      2
    )}`
  );
}

const specFilePath = './swagger.json';
generateAPIEndpoints(specFilePath);






------------------------------------------------------------error----------------------------------

file:///C:/Users/LakshyaTambi/Desktop/try/test23.js:10
const prompt = PromptTemplate.fromTemplate("I am given you the documentation, find the relevant API URLs there can be multiple url so give all the url step by step give the response and call you also give method with it.You should build the API URLs in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.");
               ^

ReferenceError: PromptTemplate is not defined
    at file:///C:/Users/LakshyaTambi/Desktop/try/test23.js:10:16
    at ModuleJob.run (node:internal/modules/esm/module_job:218:25)
    at async ModuleLoader.import (node:internal/modules/esm/loader:329:24)
    at async loadESM (node:internal/process/esm_loader:34:7)
    at async handleMainPromise (node:internal/modules/run_main:113:12)

Description

I want to pass the prompt here to find the list of api but facing the problem for the prompt Can you help once

System Info

all good

[dosubot[bot]]

To resolve the ReferenceError: PromptTemplate is not defined error, you need to import PromptTemplate from the @langchain/core/prompts module. Here is how you can do it:

Add the following import statement at the beginning of your script:

import { PromptTemplate } from "@langchain/core/prompts";

Here is your updated code with the necessary import:

import * as fs from "fs";
import { JsonSpec } from "langchain/tools";
import { createOpenApiAgent, OpenApiToolkit } from "langchain/agents";
import { OpenAI } from "@langchain/openai";
import { config } from "dotenv";
import { getPromptTemplateFromKey } from "langchain/retrievers/hyde";
import { PromptTemplate } from "@langchain/core/prompts"; // Add this import

config();
const OPENAI_API_KEY = process.env.OPENAI_API_KEY;
const prompt = PromptTemplate.fromTemplate("I am given you the documentation, find the relevant API URLs there can be multiple url so give all the url step by step give the response and call you also give method with it.You should build the API URLs in order to get a response that is as short as possible, while still getting the necessary information to answer the question. Pay attention to deliberately exclude any unnecessary pieces of data in the API call.");

async function generateAPIEndpoints(specFilePath) {
  let data;
  try {
    const jsonFile = fs.readFileSync(specFilePath, "utf8");
    data = JSON.parse(jsonFile);
    if (!data) {
      throw new Error("Failed to load OpenAPI spec");
    }
  } catch (e) {
    console.error(e);
    return;
  }

  const headers = {
    "Content-Type": "application/json",
    Authorization: `Bearer ${process.env.OPENAI_API_KEY}`,
  };
  const model = new OpenAI({ temperature: 0, apiKey: OPENAI_API_KEY });
  const toolkit = new OpenApiToolkit(new JsonSpec(data), model, headers, prompt);
  const executor = createOpenApiAgent(model, toolkit);

  const input = `Generate a list of API endpoints in the correct order to first add a new pet, then find the pet by ID, and finally delete the pet.`;
  console.log(`Executing with input "${input}"...`);

  const result = await executor.invoke({ input });
  console.log(`Got output ${result.output}`);

  console.log(
    `Got intermediate steps ${JSON.stringify(
      result.intermediateSteps,
      null,
      2
    )}`
  );
}

const specFilePath = './swagger.json';
generateAPIEndpoints(specFilePath);

This should resolve the ReferenceError and allow you to use the PromptTemplate in your script ^[1].

To continue talking to Dosu, mention @dosu.