I am following this tutorial to get started with Azure AI Studio. The create_search_index.py script ran successfully and created an index. But the get_product_documents.py and chat_with_products.py scripts do not produce any error or output when running, they just keep running indefinitely.

Any idea what might be going on? And what could I try out to fix the issue?

Here are the scripts from the link:

### config.py

# ruff: noqa: ANN201, ANN001

import os
import sys
import pathlib
import logging
from azure.identity import DefaultAzureCredential
from azure.ai.projects import AIProjectClient
from azure.ai.inference.tracing import AIInferenceInstrumentor

# load environment variables from the .env file
from dotenv import load_dotenv

load_dotenv()

# Set "./assets" as the path where assets are stored, resolving the absolute path:
ASSET_PATH = pathlib.Path(__file__).parent.resolve() / "assets"

# Configure an root app logger that prints info level logs to stdout
logger = logging.getLogger("app")
logger.setLevel(logging.INFO)
logger.addHandler(logging.StreamHandler(stream=sys.stdout))


# Returns a module-specific logger, inheriting from the root app logger
def get_logger(module_name):
    return logging.getLogger(f"app.{module_name}")


# Enable instrumentation and logging of telemetry to the project
def enable_telemetry(log_to_project: bool = False):
    AIInferenceInstrumentor().instrument()

    # enable logging message contents
    os.environ["AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED"] = "true"

    if log_to_project:
        from azure.monitor.opentelemetry import configure_azure_monitor

        project = AIProjectClient.from_connection_string(
            conn_str=os.environ["AIPROJECT_CONNECTION_STRING"], credential=DefaultAzureCredential()
        )
        tracing_link = f"=/subscriptions/{project.scope['subscription_id']}/resourceGroups/{project.scope['resource_group_name']}/providers/Microsoft.MachineLearningServices/workspaces/{project.scope['project_name']}"
        application_insights_connection_string = project.telemetry.get_connection_string()
        if not application_insights_connection_string:
            logger.warning(
                "No application insights configured, telemetry will not be logged to project. Add application insights at:"
            )
            logger.warning(tracing_link)

            return

        configure_azure_monitor(connection_string=application_insights_connection_string)
        logger.info("Enabled telemetry logging to project, view traces at:")
        logger.info(tracing_link)

### create_search_index.py

import os
from azure.ai.projects import AIProjectClient
from azure.ai.projects.models import ConnectionType
from azure.identity import DefaultAzureCredential
from azure.core.credentials import AzureKeyCredential
from azure.search.documents import SearchClient
from azure.search.documents.indexes import SearchIndexClient
from config import get_logger

# initialize logging object
logger = get_logger(__name__)

# create a project client using environment variables loaded from the .env file
# project = AIProjectClient.from_connection_string(
#     conn_str=os.environ["AIPROJECT_CONNECTION_STRING"], credential=DefaultAzureCredential()
# )

API_ENDPOINT = os.environ["API_ENDPOINT"]
API_KEY = os.environ["API_KEY"]
SUBSCRIPTION_ID = os.environ["SUBSCRIPTION_ID"]
RESOURCE_GROUP_NAME = os.environ["RESOURCE_GROUP_NAME"]
PROJECT_NAME = os.environ["PROJECT_NAME"]

# Initialize the AIProjectClient
project = AIProjectClient(
    endpoint=API_ENDPOINT,
    credential=DefaultAzureCredential(),
    subscription_id=SUBSCRIPTION_ID,
    resource_group_name=RESOURCE_GROUP_NAME,
    project_name=PROJECT_NAME
)

# create a vector embeddings client that will be used to generate vector embeddings
embeddings = project.inference.get_embeddings_client()

# use the project client to get the default search connection
search_connection = project.connections.get_default(
    connection_type=ConnectionType.AZURE_AI_SEARCH, include_credentials=True
)

# Create a search index client using the search connection
# This client will be used to create and delete search indexes
index_client = SearchIndexClient(
    endpoint=search_connection.endpoint_url, credential=AzureKeyCredential(key=search_connection.key)
)


### Define a search index
import pandas as pd
from azure.search.documents.indexes.models import (
    SemanticSearch,
    SearchField,
    SimpleField,
    SearchableField,
    SearchFieldDataType,
    SemanticConfiguration,
    SemanticPrioritizedFields,
    SemanticField,
    VectorSearch,
    HnswAlgorithmConfiguration,
    VectorSearchAlgorithmKind,
    HnswParameters,
    VectorSearchAlgorithmMetric,
    ExhaustiveKnnAlgorithmConfiguration,
    ExhaustiveKnnParameters,
    VectorSearchProfile,
    SearchIndex,
)


def create_index_definition(index_name: str, model: str) -> SearchIndex:
    dimensions = 1536  # text-embedding-ada-002
    if model == "text-embedding-3-large":
        dimensions = 3072

    # The fields we want to index. The "embedding" field is a vector field that will
    # be used for vector search.
    fields = [
        SimpleField(name="id", type=SearchFieldDataType.String, key=True),
        SearchableField(name="content", type=SearchFieldDataType.String),
        SimpleField(name="filepath", type=SearchFieldDataType.String),
        SearchableField(name="title", type=SearchFieldDataType.String),
        SimpleField(name="url", type=SearchFieldDataType.String),
        SearchField(
            name="contentVector",
            type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
            searchable=True,
            # Size of the vector created by the text-embedding-ada-002 model.
            vector_search_dimensions=dimensions,
            vector_search_profile_name="myHnswProfile",
        ),
    ]

    # The "content" field should be prioritized for semantic ranking.
    semantic_config = SemanticConfiguration(
        name="default",
        prioritized_fields=SemanticPrioritizedFields(
            title_field=SemanticField(field_name="title"),
            keywords_fields=[],
            content_fields=[SemanticField(field_name="content")],
        ),
    )

    # For vector search, we want to use the HNSW (Hierarchical Navigable Small World)
    # algorithm (a type of approximate nearest neighbor search algorithm) with cosine
    # distance.
    vector_search = VectorSearch(
        algorithms=[
            HnswAlgorithmConfiguration(
                name="myHnsw",
                kind=VectorSearchAlgorithmKind.HNSW,
                parameters=HnswParameters(
                    m=4,
                    ef_construction=1000,
                    ef_search=1000,
                    metric=VectorSearchAlgorithmMetric.COSINE,
                ),
            ),
            ExhaustiveKnnAlgorithmConfiguration(
                name="myExhaustiveKnn",
                kind=VectorSearchAlgorithmKind.EXHAUSTIVE_KNN,
                parameters=ExhaustiveKnnParameters(metric=VectorSearchAlgorithmMetric.COSINE),
            ),
        ],
        profiles=[
            VectorSearchProfile(
                name="myHnswProfile",
                algorithm_configuration_name="myHnsw",
            ),
            VectorSearchProfile(
                name="myExhaustiveKnnProfile",
                algorithm_configuration_name="myExhaustiveKnn",
            ),
        ],
    )

    # Create the semantic settings with the configuration
    semantic_search = SemanticSearch(configurations=[semantic_config])

    # Create the search index definition
    return SearchIndex(
        name=index_name,
        fields=fields,
        semantic_search=semantic_search,
        vector_search=vector_search,
    )

### add a csv file to the index
# define a function for indexing a csv file, that adds each row as a document
# and generates vector embeddings for the specified content_column
def create_docs_from_csv(path: str, content_column: str, model: str) -> list[dict[str, any]]:
    products = pd.read_csv(path)
    items = []
    for product in products.to_dict("records"):
        content = product[content_column]
        id = str(product["id"])
        title = product["name"]
        url = f"/products/{title.lower().replace(' ', '-')}"
        emb = embeddings.embed(input=content, model=model)
        rec = {
            "id": id,
            "content": content,
            "filepath": f"{title.lower().replace(' ', '-')}",
            "title": title,
            "url": url,
            "contentVector": emb.data[0].embedding,
        }
        items.append(rec)

    return items


def create_index_from_csv(index_name, csv_file):
    # If a search index already exists, delete it:
    try:
        index_definition = index_client.get_index(index_name)
        index_client.delete_index(index_name)
        logger.info(f"