Issue with model for 01_08_rag.py

[snehamysynaptica]

Hello! I am getting this error when I run the code.

weaviate.exceptions.WeaviateQueryError: Query call with protocol GRPC search failed with message connection to: OpenAI API failed with status: 404 request-id: req_f65ea1bfd1c8490097f59f7d535d4ad2 error: The model gpt-4-1106-preview does not exist or you do not have access to it..

It looks like openai retired the model : To improve reliability and make it easier for developers to choose the right models, we are deprecating a set of older OpenAI models with declining usage over the next six to twelve months. Access to these models will be shut down on the dates below.

Shutdown date / Model / systemRecommended replacement: 2026‑03‑26 / gpt-4-1106-preview / gpt-5 or gpt-4.1*

Would you be able to fix this so I can run the code for the demo db for rag? Thank you!

[snehamysynaptica]

Okay, no worries, managed to find a fix. Here it is:

import utils
import weaviate.classes as wvc


client = utils.connect_to_demo_db()  # Connect to the demo database

try:
    movies = client.collections.get("Movie")

    # Use the 'overrgenerative_provider' parameter to specify a model you have access to
    response = movies.generate.near_text(
        query="romantic love",
        limit=3,
        single_prompt="Summarize the description: {description} for this movie {title}.",
        generative_provider=wvc.query.GenerativeConfig.openai(model="gpt-5-nano")  # Override the retired gpt-4-1106-preview
        )

    for o in response.objects:
        print(f"Title: {o.properties['title']}") # Show which titles were found
        print(f"Summary: {o.generated}\n") # RAG output
        print()

    response = movies.generate.near_text(
        query="romantic love",
        limit=10,
        grouped_task="""
        Are there any common themes in these movies?
        Explain 2 in very short points,  and list the relevant movies:
        """,
        generative_provider=wvc.query.GenerativeConfig.openai(model="gpt-5-nano")  # Override the retired gpt-4-1106-preview
        )
    
    print(response.generated)  # Print the generated text

finally:
    client.close()