Add RedisVL integration for advanced vector search

[abrookins]

Summary

Adds RedisVL integration, providing an escape hatch for advanced vector search operations.

Changes

• Add redisvl as a dependency
• Add aredis_om/redisvl.py module with:
  • to_redisvl_schema(model_cls) - Convert OM model to RedisVL IndexSchema
  • get_redisvl_index(model_cls) - Get ready-to-use RedisVL SearchIndex
• Supports all OM field types: text, tag, numeric, vector
• Supports FLAT and HNSW vector algorithms with all parameters

Usage

from aredis_om import JsonModel, Field, VectorFieldOptions
from aredis_om.redisvl import to_redisvl_schema, get_redisvl_index
from redisvl.query import VectorQuery

class Document(JsonModel, index=True):
    title: str = Field(index=True)
    embedding: list[float] = Field(
        vector_options=VectorFieldOptions.hnsw(
            type=VectorFieldOptions.TYPE.FLOAT32,
            dimension=768,
            distance_metric=VectorFieldOptions.DISTANCE_METRIC.COSINE,
        )
    )

# Get RedisVL index for advanced operations
index = get_redisvl_index(Document)

# Use RedisVL's advanced query features
results = await index.query(VectorQuery(
    vector=query_embedding,
    vector_field_name="embedding",
    num_results=10,
))

Why

This is the first step toward integrating RedisVL as the underlying query engine for Redis OM (see #790). It provides users immediate access to RedisVL's advanced features without changing OM internals:

• VectorQuery with hybrid policies (BATCHES, ADHOC_BF)
• VectorRangeQuery for epsilon-based searches
• Advanced filter expressions
• EF_RUNTIME tuning for HNSW indexes

Refs #790