fix(weaviate): handle case where distance is 0 by setting score to infinity (#2415)

# What does this PR do?
Fixes provider weaviate `query_vector` function for when the distance
between the query embedding and an embedding within the vector db is 0
(identical vectors). Catches `ZeroDivisionError` and then sets `score`
to infinity, which represent maximum similarity.

<!-- If resolving an issue, uncomment and update the line below -->
Closes [#2381]

## Test Plan
Checkout this PR

Execute this code and there will no longer be a `ZeroDivisionError`
exception
```
from llama_stack_client import LlamaStackClient

base_url = "http://localhost:8321"
client = LlamaStackClient(base_url=base_url)

models = client.models.list()
embedding_model = (
    em := next(m for m in models if m.model_type == "embedding")
).identifier
embedding_dimension = 384

_ = client.vector_dbs.register(
    vector_db_id="foo_db",
    embedding_model=embedding_model,
    embedding_dimension=embedding_dimension,
    provider_id="weaviate",
)

chunk = {
    "content": "foo",
    "mime_type": "text/plain",
    "metadata": {
        "document_id": "foo-id"
    }
}

client.vector_io.insert(vector_db_id="foo_db", chunks=[chunk])
client.vector_io.query(vector_db_id="foo_db", query="foo")
```

llama_stack/providers/remote/vector_io/weaviate/weaviate.py

@@ -76,7 +76,7 @@ class WeaviateIndex(EmbeddingIndex):
                 continue
 
             chunks.append(chunk)
-            scores.append(1.0 / doc.metadata.distance)
+            scores.append(1.0 / doc.metadata.distance if doc.metadata.distance != 0 else float("inf"))
 
         return QueryChunksResponse(chunks=chunks, scores=scores)
 

tests/integration/vector_io/test_vector_io.py

@@ -154,3 +154,36 @@ def test_insert_chunks_with_precomputed_embeddings(client_with_empty_registry, e
     assert len(response.chunks) > 0
     assert response.chunks[0].metadata["document_id"] == "doc1"
     assert response.chunks[0].metadata["source"] == "precomputed"
+
+
+def test_query_returns_valid_object_when_identical_to_embedding_in_vdb(client_with_empty_registry, embedding_model_id):
+    vector_db_id = "test_precomputed_embeddings_db"
+    client_with_empty_registry.vector_dbs.register(
+        vector_db_id=vector_db_id,
+        embedding_model=embedding_model_id,
+        embedding_dimension=384,
+    )
+
+    chunks_with_embeddings = [
+        Chunk(
+            content="duplicate",
+            metadata={"document_id": "doc1", "source": "precomputed"},
+            embedding=[0.1] * 384,
+        ),
+    ]
+
+    client_with_empty_registry.vector_io.insert(
+        vector_db_id=vector_db_id,
+        chunks=chunks_with_embeddings,
+    )
+
+    response = client_with_empty_registry.vector_io.query(
+        vector_db_id=vector_db_id,
+        query="duplicate",
+    )
+
+    # Verify the top result is the expected document
+    assert response is not None
+    assert len(response.chunks) > 0
+    assert response.chunks[0].metadata["document_id"] == "doc1"
+    assert response.chunks[0].metadata["source"] == "precomputed"