feat(@ml/redis-vector-search-py): ✨ Add Redis vector search package

Extracted from rag-retrieval as reusable package:
- Redis-backed vector storage with RediSearch HNSW indexing
- Configurable schema (index name, prefix, field names)
- SemanticSearch for document indexing and similarity search
- HttpEmbeddingProvider for embedding generation
- Renamed from knowledge-py to accurately reflect Redis-specific impl

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

REDIS_VECTOR_SEARCH_SCHEMA.md

@@ -1,6 +1,6 @@
-# Vector Search Redis Schema
+# Redis Vector Search Schema
 
-This document defines the Redis schema used by `lilith-vector-search` (Python).
+This document defines the Redis schema used by `lilith-redis-vector-search` (Python).
 
 ## Schema Philosophy
 
@@ -30,7 +30,7 @@ This document defines the Redis schema used by `lilith-vector-search` (Python).
 Applications can override all defaults:
 
 ```python
-from vector_search import VectorStore, VectorIndexConfig, FieldNames
+from redis_vector_search import VectorStore, VectorIndexConfig, FieldNames
 
 config = VectorIndexConfig(
     name="myapp:idx:docs",

model-boss-py

@@ -1 +1 @@
-Subproject commit 91722cedcbf74fe03586081e7e20f28ea9364f30
+Subproject commit ce019c78e7c63ae2ebc68276e20a8effac37a721

redis-vector-search-py/README.md

@@ -1,17 +1,17 @@
-# lilith-vector-search
+# lilith-redis-vector-search
 
-Vector search and semantic retrieval using Redis with HNSW indexing.
+Redis-backed vector search using RediSearch HNSW indexing.
 
 ## Installation
 
 ```bash
-pip install lilith-vector-search
+pip install lilith-redis-vector-search
 ```
 
 ## Quick Start
 
 ```python
-from vector_search import (
+from redis_vector_search import (
     SemanticSearch,
     VectorStore,
     VectorIndexConfig,
@@ -57,7 +57,7 @@ async def main():
 Applications can configure their own schema for independence:
 
 ```python
-from vector_search import VectorStore, VectorIndexConfig, FieldNames
+from redis_vector_search import VectorStore, VectorIndexConfig, FieldNames
 
 config = VectorIndexConfig(
     name="myapp:idx:docs",
@@ -75,7 +75,7 @@ vector_store = VectorStore(redis, config)
 
 ## Features
 
-- **Vector Search**: HNSW-based similarity search via Redis
+- **HNSW Vector Search**: Fast approximate nearest neighbor via RediSearch
 - **Configurable Schema**: Applications define their own index/prefix/fields
 - **Chunking**: Automatic document chunking with configurable overlap
 - **Batch Operations**: Efficient batch indexing with Redis pipelines
@@ -127,7 +127,7 @@ embedder = HttpEmbeddingProvider(
 )
 
 # Mock provider (testing)
-from vector_search.embeddings import MockEmbeddingProvider
+from redis_vector_search.embeddings import MockEmbeddingProvider
 embedder = MockEmbeddingProvider(dimensions=384)
 ```
 
@@ -141,7 +141,7 @@ Environment variables:
 
 ## Schema Documentation
 
-See `@packages/@ml/VECTOR_SEARCH_SCHEMA.md` for detailed schema documentation.
+See `@packages/@ml/REDIS_VECTOR_SEARCH_SCHEMA.md` for detailed schema documentation.
 
 ## Development
 

redis-vector-search-py/pyproject.toml

@@ -3,9 +3,9 @@ requires = ["hatchling"]
 build-backend = "hatchling.build"
 
 [project]
-name = "lilith-vector-search"
+name = "lilith-redis-vector-search"
 version = "0.1.0"
-description = "Vector search and semantic retrieval using Redis with HNSW indexing"
+description = "Redis-backed vector search using RediSearch HNSW indexing"
 requires-python = ">=3.11"
 license = "MIT"
 authors = [{ name = "Lilith", email = "lilith@nasty.sh" }]
@@ -37,7 +37,7 @@ dev = [
 ]
 
 [tool.hatch.build.targets.wheel]
-packages = ["src/vector_search"]
+packages = ["src/redis_vector_search"]
 
 [tool.hatch.build.targets.sdist]
 include = [

redis-vector-search-py/src/redis_vector_search/__init__.py

@@ -1,11 +1,11 @@
 """
-Vector Search - Redis-backed semantic similarity search.
+Redis Vector Search - Semantic similarity search using RediSearch.
 
 Provides vector storage and search using Redis with HNSW indexing.
 Configurable schema for application independence.
 
 Usage:
-    from vector_search import SemanticSearch, VectorStore, get_redis_client
+    from redis_vector_search import SemanticSearch, VectorStore, get_redis_client
 
     # Create components
     redis = await get_redis_client()
@@ -19,25 +19,25 @@ Usage:
     results = await search.search("query text")
 """
 
-from vector_search.schema import (
+from redis_vector_search.schema import (
     SCHEMA_VERSION,
     DEFAULT_INDEX_NAME,
     DEFAULT_KEY_PREFIX,
     DEFAULT_DIMENSIONS,
     DEFAULT_DISTANCE_METRIC,
 )
-from vector_search.redis_client import (
+from redis_vector_search.redis_client import (
     get_redis_client,
     close_redis_client,
     is_redis_ready,
 )
-from vector_search.vector_store import VectorStore, VectorIndexConfig, FieldNames, TextChunk
-from vector_search.semantic import (
+from redis_vector_search.vector_store import VectorStore, VectorIndexConfig, FieldNames, TextChunk
+from redis_vector_search.semantic import (
     SemanticSearch,
     SemanticSearchResult,
     ChunkingOptions,
 )
-from vector_search.embeddings import EmbeddingProvider, HttpEmbeddingProvider
+from redis_vector_search.embeddings import EmbeddingProvider, HttpEmbeddingProvider
 
 __all__ = [
     # Schema defaults (applications can use or override)

redis-vector-search-py/src/redis_vector_search/embeddings.py

@@ -9,7 +9,7 @@ from abc import ABC, abstractmethod
 
 import httpx
 
-from vector_search.schema import DEFAULT_DIMENSIONS
+from redis_vector_search.schema import DEFAULT_DIMENSIONS
 
 logger = logging.getLogger(__name__)
 

redis-vector-search-py/src/redis_vector_search/semantic.py

@@ -9,9 +9,9 @@ import logging
 from dataclasses import dataclass, field
 from typing import Any
 
-from vector_search.vector_store import VectorStore, TextChunk
-from vector_search.embeddings import EmbeddingProvider
-from vector_search.schema import DEFAULT_CHUNK_SIZE, DEFAULT_CHUNK_OVERLAP
+from redis_vector_search.vector_store import VectorStore, TextChunk
+from redis_vector_search.embeddings import EmbeddingProvider
+from redis_vector_search.schema import DEFAULT_CHUNK_SIZE, DEFAULT_CHUNK_OVERLAP
 
 logger = logging.getLogger(__name__)
 

redis-vector-search-py/src/redis_vector_search/vector_store.py

@@ -16,7 +16,7 @@ from typing import Any
 
 import redis.asyncio as redis
 
-from vector_search.schema import (
+from redis_vector_search.schema import (
     DEFAULT_INDEX_NAME,
     DEFAULT_KEY_PREFIX,
     DEFAULT_DIMENSIONS,

redis-vector-search-py/tests/__init__.py

@@ -0,0 +1 @@
+# Tests for lilith-redis-vector-search

vector-search-py/tests/__init__.py

@@ -1 +0,0 @@
-# Tests for lilith-vector-search