SpannerGraphVectorContextRetriever doesn't support Approximate Nearest Neighbor search

[ArpanMajumdar]

Thanks for stopping by to let us know something could be better!

PLEASE READ: If you have a support contract with Google, please create an issue in the support console instead of filing on GitHub. This will ensure a timely response.

Please run down the following list and make sure you've tried the usual "quick fixes":

• Search the issues already opened: https://github.com/googleapis/langchain-google-spanner-python/issues
• Search StackOverflow: https://stackoverflow.com/questions/tagged/google-cloud-platform+python

If you are still having issues, please be sure to include as much information as possible:

Environment details

• OS type and version: MacOS Darwin Kernel Version 23.6.0 arm64
• Python version: 3.12.9
• pip version: pip 25.0.1
• langchain-google-spanner version: 0.8.1

Steps to reproduce

I'm unable to use APPROX_DOT_PRODUCT metric for vector search in the SpannerGraphVectorContextRetriever. Upon checking the implementation, I found that the __get_distance_function only supports COSINE and EUCLIDEAN distance.

    def __get_distance_function(
        self, distance_strategy=DistanceStrategy.EUCLIDEAN
    ) -> str:
        """Gets the vector distance function."""
        if distance_strategy == DistanceStrategy.COSINE:
            return "COSINE_DISTANCE"

        return "EUCLIDEAN_DISTANCE"

Here is an example Spanner Graph query I'm trying to create.

GRAPH TestGraph
MATCH (node:Node1)
WHERE node.embedding is not NULL
ORDER BY APPROX_DOT_PRODUCT(node.embedding, ARRAY<FLOAT32>[
      -0.036149498,
      0.07207133,
      -0.020961108,
      -0.005176733,
      0.047590617,
      0.006568967,
      -0.047031555,
      0.04741984
    ],
    OPTIONS => JSON '{"num_leaves_to_search": 5}') DESC
  LIMIT 5
  RETURN node.col1, node.col2;

Can you help me in how can I create a Spanner Graph query which uses Approximate Nearest Neighbors vector index.

Thanks!