LLM cannot be configured using langchain.Databricks.v1

[jstammers]

It is not possible to configure spacy_llm to instantiate an LLM agent using langchain.Databricks.

For example, here is my initial config

[components.llm.model]
@llm_models = "langchain.Databricks.v1"
name = "databricks-meta-llama-3-70b-instruct"
query = {"@llm_queries": "spacy.CallLangChain.v1"}

This gives me the following error indicating that the endpoint_name must be set in the config

File ~/****/.venv/lib/python3.11/site-packages/pydantic/main.py:214, in BaseModel.__init__(self, **data)
    212 # `__tracebackhide__` tells pytest and some other tools to omit this function from tracebacks
    213 __tracebackhide__ = True
--> 214 validated_self = self.__pydantic_validator__.validate_python(data, self_instance=self)
    215 if self is not validated_self:
    216     warnings.warn(
    217         'A custom validator is returning a value other than `self`.\n'
    218         "Returning anything other than `self` from a top level model validator isn't supported when validating via `__init__`.\n"
    219         'See the `model_validator` docs (https://docs.pydantic.dev/latest/concepts/validators/#model-validators) for more details.',
    220         stacklevel=2,
    221     )

ValidationError: 1 validation error for Databricks
  Value error, Neither endpoint_name nor cluster_id was set. And the cluster_id cannot be automatically determined. Received error: Cannot access dbruntime, not running inside a Databricks notebook. [type=value_error, input_value={'model': 'databricks-meta-llama-3-70b-instruct'}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/value_error

Modifying the config to include an endpoint name then raises a different validation error because lanchain_community.llm.databricks.Databricks does not accept a name argument

[components.llm.model]
@llm_models = "langchain.Databricks.v1"
name = "databricks-meta-llama-3-70b-instruct"
query = {"@llm_queries": "spacy.CallLangChain.v1"}
config = {"endpoint_name": "databricks-meta-llama-3-70b-instruct"}

raises

ValidationError: 1 validation error for Databricks
model
  Extra inputs are not permitted [type=extra_forbidden, input_value='databricks-meta-llama-3-70b-instruct', input_type=str]
    For further information visit https://errors.pydantic.dev/2.10/v/extra_forbidden

This API has been deprecated in favour of langchain_databricks.ChatDatabricks, so is there a recommended way to interface with LLMs using spacy_llm and the Databricks platform?

For reference, these are the packages I am using:

spacy-llm==0.7.3
langchain==0.3.14
langchain-community==0.3.14
langchain-databricks==0.1.2
databricks-connect==15.4.3
databricks-langchain==0.1.1