Need help in debugging llma-index mistral 7b document chatbot

Question

Till last week the code given below was working fine. Im running this code on google colab using T4 gpu runtime. But starting today the response to any question I ask is just '##########'. I need some help identifying the problem.

This is the code for the chatbot:

!pip install -q pypdf
!pip install -q python-dotenv
!pip install -q transformers
!CMAKE_ARGS="-DLLAMA_CUBLAS=on" FORCE_CMAKE=1 pip install  llama-cpp-python --no-cache-dir
!pip install -q llama-index
!pip -q install sentence-transformers
!pip install langchain
import logging
import sys
logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))
from llama_index import VectorStoreIndex, SimpleDirectoryReader, ServiceContext
documents = SimpleDirectoryReader("/content/Data/").load_data()
import torch
from llama_index.llms import LlamaCPP
from llama_index.llms.llama_utils import messages_to_prompt, completion_to_prompt
llm = LlamaCPP(
    # You can pass in the URL to a GGML model to download it automatically
    model_url='https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf',
    # optionally, you can set the path to a pre-downloaded model instead of model_url
    model_path=None,
    temperature=0.1,
    max_new_tokens=256,
    # llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
    context_window=3900,
    # kwargs to pass to __call__()
    generate_kwargs={},
    # kwargs to pass to __init__()
    # set to at least 1 to use GPU
    model_kwargs={"n_gpu_layers": -1},
    # transform inputs into Llama2 format
    messages_to_prompt=messages_to_prompt,
    completion_to_prompt=completion_to_prompt,
    verbose=True,
)
from langchain.embeddings.huggingface import HuggingFaceEmbeddings
from llama_index.embeddings import LangchainEmbedding
from llama_index import ServiceContext
embed_model = LangchainEmbedding(
  HuggingFaceEmbeddings(model_name="thenlper/gte-large")
)
service_context = ServiceContext.from_defaults(
    chunk_size=256,
    llm=llm,
    embed_model=embed_model
)
index = VectorStoreIndex.from_documents(documents, service_context=service_context)
query_engine = index.as_query_engine()
response = query_engine.query("Enter your query here")
print(response)

Tried everything and not getting the response other than a huge string of '#'.