[graph_memory]: The current tools does not support non-structured models.

[spike-spiegel-21]

🐛 Describe the bug

When I try to use these configurations:

from mem0 import Memory

config = {
    "llm": {
        "provider": "azure_openai",
        "config": {
            "model": "gpt4Omni",
            "temperature": 0.1,
            "max_tokens": 2000,
             "azure_kwargs" : {
                "azure_deployment" : "",
                "api_version" : "",
                "azure_endpoint" : "",
                "api_key" : ""
              }
        }
    },
    "embedder": {
        "provider": "azure_openai",
        "config": {
            "model": "",
            "azure_kwargs" : {
                  "api_version" : "",
                  "azure_deployment" : "",
                  "azure_endpoint" : "",
                  "azure_endpoint": "",
                  "api_key": ""
              }
        }
    },
    "graph_store": {
        "provider": "",
        "config": {
            "url": "",
            "username": "neo4j",
            "password": ""
        }
    },
    "version": "v1.1"
}
m = Memory.from_config(config)
m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})

I get an error

openai.BadRequestError: Error code: 400 - {'error': {'message': "Invalid function definition for 'search': unexpected parameter 'strict' parameter supplied.", 'type': 'invalid_request_error', 'param': None, 'code': None}}
    raise self._make_status_error_from_response(err.response) from None

[prateekchhikara]

Hi @spike-spiegel-21 let me check and get back to you on this.

[spike-spiegel-21]

Hi @prateekchhikara raising a PR quickly.

[prateekchhikara]

@spike-spiegel-21 the PR has been merged, so closing the issue