How to fix Unknown Model error?

I am following Build a Custom Knowledge Retrieval (RAG) chatbot using Azure AI Foundry. I have setted up the AI search and also deployed two models gpt-4o-mini and text-embedding-ada-002, but I can't seem to access them in my computer using azure sdk. I have copied the code from tutorial and try to run it but It gives error

azure.core.exceptions.HttpResponseError: (unavailable_model) Unavailable model: gpt-4o-mini

Code: unavailable_model

Message: Unavailable model: gpt-4o-mini.
in when running code for intent_mapping_response. Additionally the same thing happens when I try to run embedding code.

I am trying to run following code:

import os
from pathlib import Path
from opentelemetry import trace
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 config import ASSET_PATH, get_logger
from azure.ai.inference.prompts import PromptTemplate

from azure.search.documents.models import VectorizedQuery
from dotenv import load_dotenv

from azure.identity import DefaultAzureCredential
import os



load_dotenv()

# initialize logging and tracing objects
logger = get_logger(__name__)
tracer = trace.get_tracer(__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()
)
print(dir(project.inference))

# create a vector embeddings client that will be used to generate vector embeddings
chat = project.inference.get_chat_completions_client()
print("chat completion client created :", chat)
model_info = chat.get_model_info('gpt-4o-mini')  # Replace with your model name
print("Model Info:", model_info)

# Print available attributes and methods

embeddings = project.inference.get_embeddings_client()
print("embedding client created :", embeddings)

# 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
search_client = SearchClient(
    index_name=os.environ["AISEARCH_INDEX_NAME"],
    endpoint=search_connection.endpoint_url,
    credential=AzureKeyCredential(key=search_connection.key),
)

@tracer.start_as_current_span(name="get_relevant_documents")
def get_relevant_documents(messages: list, context: dict = None) -> dict:
    if context is None:
        context = {}

    overrides = context.get("overrides", {})
    top = overrides.get("top", 5)


    # # generate a search query from the chat messages
    intent_prompty = PromptTemplate.from_prompty("intent_mapping.prompty")

    intent_mapping_response = chat.complete(
        model=os.environ["INTENT_MAPPING_MODEL"],
        messages=intent_prompty.create_messages(conversation=messages),
        **intent_prompty.parameters,
    )

    search_query = intent_mapping_response.choices[0].message.content
    logger.debug(f"🧠 Intent mapping: {search_query}")

    # generate a vector representation of the search query
    embedding = embeddings.embed(model=os.environ["EMBEDDINGS_MODEL"], input=search_query)
    search_vector = embedding.data[0].embedding

    # search the index for products matching the search query
    vector_query = VectorizedQuery(vector=search_vector, k_nearest_neighbors=top, fields="contentVector")

    search_results = search_client.search(
        search_text=search_query, vector_queries=[vector_query], select=["id", "content", "filepath", "title", "url"]
    )

    documents = [
        {
            "id": result["id"],
            "content": result["content"],
            "filepath": result["filepath"],
            "title": result["title"],
            "url": result["url"],
        }
        for result in search_results
    ]

    # add results to the provided context
    if "thoughts" not in context:
        context["thoughts"] = []

    # add thoughts and documents to the context object so it can be returned to the caller
    context["thoughts"].append(
        {
            "title": "Generated search query",
            "description": search_query,
        }
    )

    if "grounding_data" not in context:
        context["grounding_data"] = []
    context["grounding_data"].append(documents)

    logger.debug(f"📄 {len(documents)} documents retrieved: {documents}")
    return documents

if __name__ == "__main__":
    import logging
    import argparse

    # set logging level to debug when running this module directly
    logger.setLevel(logging.DEBUG)

    # load command line arguments
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--query",
        type=str,
        help="Query to use to search product",
        default="I need a new tent for 4 people, what would you recommend?",
    )

    args = parser.parse_args()
    query = args.query

    result = get_relevant_documents(messages=[{"role": "user", "content": query}])