Is anyone here using pinecone I m a

def get_recent_files(dir_path, after_date):
    # Convert the input string to a datetime object
    after_date = datetime.strptime(after_date, '%Y-%m-%d')
    # List all files in the directory
    for root, dirs, files in os.walk(dir_path):
        for file in files:
            file_path = os.path.join(root, file)
            # Get the modification time of the file
            mod_time = datetime.fromtimestamp(os.path.getmtime(file_path))
            # Check if the file was modified after the given date
            if ".md" in file.lower():
                if mod_time > after_date:
                    f = open(file_path, encoding="utf8")
                    text = f.read()
                    text = re.sub(regex, '', text, 0, re.DOTALL)
                    text = os.linesep.join([s for s in text.splitlines() if s])
                    print("\n");
                    print("Processing " + file + " ...")
                    print("\n")
                    text_chunks = text.splitlines()
                    for chunk in text_chunks:
                        if chunk != "":
                            meta = [{'text': chunk, 'filename': file}]
                            if (len(chunk) > 20):
                                vector_id = uuid.uuid4()
                                vector_id = str(vector_id)
                                print("Creating and indexing embed with id " + str(vector_id))
                                res = openai.Embedding.create(input=chunk, engine=cs.embedding_model)
                                embeds = [record['embedding'] for record in res['data']]
                                to_upsert = zip([vector_id], embeds, meta)
                                #print(meta)
                                index.upsert(vectors=list(to_upsert))

get_recent_files(cs.directory, cs.date_modified)

def my_function():

    directory = 'Test MD Files'

    # Retrieve settings from user input
    question = q_entry.get()
    number_of_nodes = n_entry.get()
    run_embedding = run_embed.get()

    # Load directory of files
    documents = SimpleDirectoryReader(directory, recursive=True, required_exts=[".md"]).load_data(concatenate=False)

    # Ask if user wants to embed or not
    if run_embedding == 1:
        index = GPTSimpleVectorIndex(documents)
        index.save_to_disk('index_test.json')

    index = GPTSimpleVectorIndex.load_from_disk('index_test.json')

    response = index.query(question, response_mode="compact", similarity_top_k=int(number_of_nodes))

    print(response)
    # print(response.get_formatted_sources())