Langchain and streamlit chatbot

Hello, I am having some problems on generating answers based on the csv that I got. I started by creating a vector database to store the embeddings of the csv data, in order to use it in the chatbot. This is in a file called embeddings.py.

from langchain.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.document_loaders.csv_loader import CSVLoader

DB_FAISS_PATH = "vectorstore/db_faiss"
loader = CSVLoader(file_path="./data/cleanTripLisbon.csv", encoding="utf-8", csv_args={'delimiter': ','})
data = loader.load()
text_splitter = CharacterTextSplitter(separator='\n')
text_chunks = text_splitter.split_documents(data)
embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
docsearch = FAISS.from_documents(text_chunks, embeddings)
docsearch.save_local(DB_FAISS_PATH)

I have tried multiple ways to put my chatbot to give answers based on the content inside of the csv and unfortunately, never worked. The csv is about attractions to visit and columns such as name, about, address, ratings… And below is the chatbot, that is in the file chatbot.py

from langchain.vectorstores import FAISS
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.document_loaders.csv_loader import CSVLoader
from util import local_settings
# from langchain.llms import OpenAI
from openai import OpenAI
from embeddings import embeddings

vectorstore = FAISS.load_local("vectorstore/db_faiss", embeddings)

# [i]                                                                                            #
# [i] OpenAI API                                                                                 #
# [i]                                                                                            #

class GPT_Helper:
    def __init__(self,
        OPENAI_API_KEY: str,
        system_behavior: str="",
        model="gpt-3.5-turbo",
    ):
        self.client = OpenAI(api_key=OPENAI_API_KEY)
        self.messages = []
        self.model = model

        if system_behavior:
            self.messages.append({
                "role": "system",
                "content": system_behavior
            })

    # [i] get completion from the model 
    def get_completion(self, prompt, temperature=0):
        self.messages = []  # Clear messages list before each interaction
        self.messages.append({"role": "user", "content": prompt})
        
        completion = self.client.chat.completions.create(
            model=self.model,
            messages=self.messages,
            temperature=temperature,
        )
        
        self.messages.append(
            {
                "role": "assistant",
                "content": completion.choices[0].message.content
            }
        )
        return completion.choices[0].message.content

# [i]                                                                                            #
# [i] AttractionBot                                                                               #
# [i]                                                                                            #

class AttractionBot:
    """
    Generate a response by using LLMs.
    """

    def __init__(self, system_behavior: str):
        self._system_behavior = system_behavior
        self._username = None  # Add a private attribute to store the username

        self.engine = GPT_Helper(
            OPENAI_API_KEY=local_settings.OPENAI_API_KEY,
            system_behavior=system_behavior
        )

    def set_username(self, username):
        self._username = username

    def generate_response(self, message: str):
        # Include the username in the message if available
        user_message = f"{self._username}: {message}" if self._username else message

        query_embeddings = embeddings.embed_query(user_message)
        matching_documents = vectorstore.similarity_search_by_vector(query_embeddings)
        retrieved_information = self.retrieve_information(matching_documents)
        response = self.engine.get_completion(retrieved_information)
    
        return response
    
    @staticmethod
    def retrieve_information(matching_documents):
        # Extract the relevant information from the matching documents
        information = []
        for doc in matching_documents:
            # Assuming that the CSV file has columns "attraction_name" and "description"
            attraction_name = doc.page_content
            information.append(attraction_name)
        return information
        
    def __str__(self):
        shift = "   "
        class_name = str(type(self)).split('.')[-1].replace("'>", "")

        return f"🤖 {class_name}."

    def reset(self):
        ...
    
    @property
    def memory(self):
        return self.engine.messages

    @property
    def system_behavior(self):
        return self._system_behavior

    @system_behavior.setter
    def system_behavior(self, system_config: str):
        self._system_behavior = system_config

Could someone helping me understand where is the problem? I am new on working with Langchain. Thanks in advance.