Fix LangChain compatibility with SQLDatabase

[dbczumar]

Related Issues/PRs

Fixes #9188

What changes are proposed in this pull request?

Fix LangChain compatibility with SQLDatabase

How is this patch tested?

• Existing unit/integration tests
• New unit/integration tests
• Manual tests (describe details, including test results, below)

Does this PR change the documentation?

• No. You can skip the rest of this section.
• Yes. Make sure the changed pages / sections render correctly in the documentation preview.

Release Notes

Is this a user-facing change?

• No. You can skip the rest of this section.
• Yes. Give a description of this change to be included in the release notes for MLflow users.

(Details in 1-2 sentences. You can just refer to another PR with a description if this PR is part of a larger change.)

What component(s), interfaces, languages, and integrations does this PR affect?

Components

• area/artifacts: Artifact stores and artifact logging
• area/build: Build and test infrastructure for MLflow
• area/docs: MLflow documentation pages
• area/examples: Example code
• area/gateway: AI Gateway service, Gateway client APIs, third-party Gateway integrations
• area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
• area/models: MLmodel format, model serialization/deserialization, flavors
• area/recipes: Recipes, Recipe APIs, Recipe configs, Recipe Templates
• area/projects: MLproject format, project running backends
• area/scoring: MLflow Model server, model deployment tools, Spark UDFs
• area/server-infra: MLflow Tracking server backend
• area/tracking: Tracking Service, tracking client APIs, autologging

Interface

• area/uiux: Front-end, user experience, plotting, JavaScript, JavaScript dev server
• area/docker: Docker use across MLflow's components, such as MLflow Projects and MLflow Models
• area/sqlalchemy: Use of SQLAlchemy in the Tracking Service or Model Registry
• area/windows: Windows support

Language

• language/r: R APIs and clients
• language/java: Java APIs and clients
• language/new: Proposals for new client languages

Integrations

• integrations/azure: Azure and Azure ML integrations
• integrations/sagemaker: SageMaker integrations
• integrations/databricks: Databricks integrations

How should the PR be classified in the release notes? Choose one:

• rn/breaking-change - The PR will be mentioned in the "Breaking Changes" section
• rn/none - No description will be included. The PR will be mentioned only by the PR number in the "Small Bugfixes and Documentation Updates" section
• rn/feature - A new user-facing feature worth mentioning in the release notes
• rn/bug-fix - A user-facing bug fix worth mentioning in the release notes
• rn/documentation - A user-facing documentation change worth mentioning in the release notes

[mlflow-automation]

Documentation preview for 2da6697 will be available here when this CircleCI job completes successfully.

More info

• Ignore this comment if this PR does not change the documentation.
• It takes a few minutes for the preview to be available.
• The preview is updated when a new commit is pushed to this PR.
• This comment was created by https://github.com/mlflow/mlflow/actions/runs/5733550032.

[dbczumar]

This is quite brittle, since it doesn't support subclasses. Changed to isinstance().

[dbczumar]

This is quite brittle, since it doesn't support subclasses. Changed to isinstance() in _get_special_chain_info_or_none

[dbczumar]

This breaks for subclasses of special chains. It also breaks if the chain class name changes in a future version of langchain. Accordingly, rather than relying on the class name, we store the name of the loader argument for dependent objects (e.g. embeddings, database, ...) as part of the MLModel flavor config for improved compatibility across versions.

[dbczumar]

See https://github.com/mlflow/mlflow/pull/9192/files#r1281259226

[dbczumar]

This fails on master with:

   def _load_api_chain(config: dict, **kwargs: Any) -> APIChain:
        if "api_request_chain" in config:
            api_request_chain_config = config.pop("api_request_chain")
            api_request_chain = load_chain_from_config(api_request_chain_config)
        elif "api_request_chain_path" in config:
            api_request_chain = load_chain(config.pop("api_request_chain_path"))
        else:
            raise ValueError(
                "One of `api_request_chain` or `api_request_chain_path` must be present."
            )
        if "api_answer_chain" in config:
            api_answer_chain_config = config.pop("api_answer_chain")
            api_answer_chain = load_chain_from_config(api_answer_chain_config)
        elif "api_answer_chain_path" in config:
            api_answer_chain = load_chain(config.pop("api_answer_chain_path"))
        else:
            raise ValueError(
                "One of `api_answer_chain` or `api_answer_chain_path` must be present."
            )
        if "requests_wrapper" in kwargs:
            requests_wrapper = kwargs.pop("requests_wrapper")
        else:
>           raise ValueError("`requests_wrapper` must be present.")
E           ValueError: `requests_wrapper` must be present.

But it passes on the PR branch :)

[serena-ruan]

LGTM!