Retrieval of response from open-ai llm based on language of question.

[rupeshKumarAmt]

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 os
import json
from dotenv import load_dotenv
from chromadb import HttpClient
from chromadb.config import Settings
from langchain.prompts import PromptTemplate
from langchain.chat_models import ChatOpenAI
from langchain.vectorstores.chroma import Chroma
from langchain.embeddings import OpenAIEmbeddings
import config
from openai._exceptions import RateLimitError
from langchain.schema.messages import HumanMessage, SystemMessage
import re

prompt = PromptTemplate(template=template, input_variables=["question", "context"]).format(question=question, context=vector_similarity_search)

message = [
	SystemMessage(content=prompt),
	HumanMessage(content=question),
]

res = llm(message)

Description

We are trying to do a RAG on a trained data which consist of Arabic and English contents.
We require the resposne from the llm based on the language the user has asked the question but the response is comming as English.

How to tackle the same.
used model is gpt3.5-turbo

System Info

langchain==0.0.346
langchain-core==0.0.10
langchainhub==0.1.14
langsmith==0.0.69

[feijoes]

@rupeshKumarAmt try adding the instruction in the prompt. I had a similar issue it worked fine after modify the prompt