loadQARefineChain with custom prompts with multiple input

[faysal515]

how can i implement loadQARefineChain with my own question prompt and refine prompt. each prompt have multiple variables i need to pass

[dosubot[bot]]

🤖

To implement loadQARefineChain with your own custom question and refine prompts that have multiple variables to pass, you need to create instances of PromptTemplate for your question and refine prompts. Here's an example of how you can do it:

import { PromptTemplate } from "langchain/prompts";

// Your custom question and refine prompts
const questionPromptTemplateString = `Your custom question template here`;
const refinePromptTemplateString = `Your custom refine prompt template here`;

const questionPrompt = new PromptTemplate({
  inputVariables: ["context", "question"],
  template: questionPromptTemplateString,
});

const refinePrompt = new PromptTemplate({
  inputVariables: ["question", "existing_answer", "context"],
  template: refinePromptTemplateString,
});

// Create the models and chain
const embeddings = new OpenAIEmbeddings();
const model = new OpenAI({ temperature: 0 });
const chain = loadQARefineChain(model, {
  questionPrompt,
  refinePrompt,
});

// Load the documents and create the vector store
const loader = new TextLoader("./state_of_the_union.txt");
const docs = await loader.loadAndSplit();
const store = await MemoryVectorStore.fromDocuments(docs, embeddings);

// Select the relevant documents
const question = "Your custom question here";
const relevantDocs = await store.similaritySearch(question);

// Call the chain
const res = await chain.call({
  input_documents: relevantDocs,
  question,
});
console.log(res);

In this example, questionPrompt and refinePrompt are instances of PromptTemplate that contain your custom question and refine prompts. These are passed to the loadQARefineChain function. The inputVariables parameter in the PromptTemplate constructor is used to specify the variables that will be used in the template.

Please note that the refinePrompt parameter in the loadQARefineChain function is used to pass the refine prompt. If langchainjs doesn't support this parameter, you would need to modify the loadQARefineChain function or create a new function to support it.

You can find more information about this in the langchainjs codebase, specifically in the examples/src/chains/qa_refine.ts and examples/src/chains/qa_refine_custom_prompt.ts files.

I hope this helps! If you have any more questions, feel free to ask.

Sources

• How to reuse prompts that requires different variables?
• examples/src/chains/qa_refine.ts
• examples/src/chains/qa_refine_custom_prompt.ts
• langchain/src/chains/question_answering/load.ts

---

This response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research.

Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant.

If you want to continue the conversation, start your reply with @dosu-bot.