zeusdb-vector-database 0.0.9__cp311-cp311-musllinux_1_2_armv7l.whl → 0.1.0__cp311-cp311-musllinux_1_2_armv7l.whl

zeusdb_vector_database/__init__.py

@@ -1,7 +1,7 @@
 """
 ZeusDB Vector Database Module
 """
-__version__ = "0.0.9"
+__version__ = "0.1.0"
 
 from .vector_database import VectorDatabase # imports the VectorDatabase class from the vector_database.py file
 

zeusdb_vector_database/vector_database.py

@@ -1,50 +1,86 @@
 """
 vector_database.py
 
-Pure factory for creating vector indexes using Rust backend.
-Currently supports HNSW (Hierarchical Navigable Small World).
+Factory for creating vector indexes with support for multiple types.
+Currently supports HNSW (Hierarchical Navigable Small World) with extensible design.
 """
+from typing import Callable, Dict, Any
 from .zeusdb_vector_database import HNSWIndex
+# from .zeusdb_vector_database import HNSWIndex, IVFIndex, LSHIndex, AnnoyIndex, FlatIndex # Future support planned
 
 class VectorDatabase:
     """
-    Pure factory for creating vector indexes.
-    No state management - just creates and returns indexes.
+    Factory for creating various types of vector indexes.
+    Each index type is registered via _index_constructors.
     """
+
+    _index_constructors: Dict[str, Callable[..., Any]] = {
+        "hnsw": HNSWIndex,
+        # "ivf": IVFIndex,      # Future support planned
+        # "lsh": LSHIndex,      # Future support planned
+        # "annoy": AnnoyIndex,  # Future support planned
+        # "flat": FlatIndex,    # Future support planned
+    }
     
     def __init__(self):
-        """Initialize VectorDatabase factory."""
+        """Initialize the vector database factory."""
         pass
 
-    def create_index_hnsw(
-        self,
-        dim: int = 1536,
-        space: str = "cosine",
-        M: int = 16,
-        ef_construction: int = 200,
-        expected_size: int = 10000
-    ) -> HNSWIndex:
+    def create(self, index_type: str = "hnsw", **kwargs) -> Any:
         """
-        Creates a new HNSW (Hierarchical Navigable Small World) index.
+        Create a vector index of the specified type.
 
         Args:
-            dim: Vector dimension (default: 1536)
-            space: Distance metric, only 'cosine' supported (default: 'cosine')
-            M: Bidirectional links per node (default: 16, max: 256)
-            ef_construction: Construction candidate list size (default: 200)
-            expected_size: Expected number of vectors (default: 10000)
+            index_type: The type of index to create (case-insensitive: "hnsw", "ivf", etc.)
+            **kwargs: Parameters specific to the chosen index type (validated by Rust backend)
+
+            For "hnsw", supported parameters are:
+                - dim (int): Vector dimension (default: 1536)
+                - space (str): Distance metric — supports 'cosine', 'l2', or 'l1' (default: 'cosine')
+                - m (int): Bidirectional links per node (default: 16, max: 256)
+                - ef_construction (int): Construction candidate list size (default: 200)
+                - expected_size (int): Expected number of vectors (default: 10000)
 
         Returns:
-            HNSWIndex: Use this index directly for all operations
+            An instance of the created vector index.
 
-        Example:
+        Examples:
+            # HNSW index with defaults
             vdb = VectorDatabase()
-            index = vdb.create_index_hnsw(dim=1536, expected_size=10000)
-            index.add_point("doc1", vector, metadata)
-            results = index.search(query_vector, top_k=10)
+            index = vdb.create("hnsw", dim=1536)
+            
+            # HNSW index with custom parameters
+            index = vdb.create("hnsw", dim=768, m=16, ef_construction=200, space="cosine", expected_size=10000)
+            
+            # Future IVF index
+            # index = vdb.create("ivf", dim=1536, nlist=100, nprobe=10)
+
+        Raises:
+            ValueError: If index_type is not supported.
+            RuntimeError: If index creation fails due to backend validation.
         """
+        index_type = (index_type or "").strip().lower()
+
+        if index_type not in self._index_constructors:
+            available = ', '.join(sorted(self._index_constructors.keys()))
+            raise ValueError(f"Unknown index type '{index_type}'. Available: {available}")
+        
+        # Apply index-specific defaults
+        if index_type == "hnsw":
+            kwargs.setdefault("dim", 1536)
+            kwargs.setdefault("space", "cosine")
+            kwargs.setdefault("m", 16)
+            kwargs.setdefault("ef_construction", 200)
+            kwargs.setdefault("expected_size", 10000)
+        
+        constructor = self._index_constructors[index_type]
+        
         try:
-            return HNSWIndex(dim, space, M, ef_construction, expected_size)
+            return constructor(**kwargs)
         except Exception as e:
-            raise RuntimeError(f"Failed to create HNSW index: {e}") from e
-    
+            raise RuntimeError(f"Failed to create {index_type.upper()} index: {e}") from e
+            
+    @classmethod
+    def available_index_types(cls) -> list[str]:
+        """Return list of all supported index types."""
+        return sorted(cls._index_constructors.keys())

{zeusdb_vector_database-0.0.9.dist-info → zeusdb_vector_database-0.1.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: zeusdb-vector-database
-Version: 0.0.9
+Version: 0.1.0
 Classifier: Programming Language :: Rust
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Requires-Dist: numpy>=2.2.6,<3.0.0
@@ -124,7 +124,7 @@ from zeusdb_vector_database import VectorDatabase
 vdb = VectorDatabase()
 
 # Initialize and set up the database resources
-index = vdb.create_index_hnsw(dim = 8)
+index = vdb.create(index_type="hnsw", dim=8)
 
 # Vector embeddings with accompanying ID's and Metadata
 records = [
@@ -175,11 +175,11 @@ ZeusDB Vector Database makes it easy to work with high-dimensional vector data u
 
 **Three simple steps**
 
-1. **Create an index**  
-2. **Add data to the index**  
-3. **Conduct a similarity search**
+1. **Create an index** using `.create()`
+2. **Add data** using `.add(...)`
+3. **Conduct a similarity search** using `.search(...)`
 
-Each step is covered below.
+Each step is covered below. 
 
 <br/>
 
@@ -195,22 +195,24 @@ from zeusdb_vector_database import VectorDatabase
 vdb = VectorDatabase()
 
 # Initialize and set up the database resources
-index = vdb.create_index_hnsw(
+index = vdb.create(
+  index_type = "hnsw",
   dim = 8, 
   space = "cosine", 
-  M = 16, 
+  m = 16, 
   ef_construction = 200, 
-  expected_size=5
+  expected_size = 5
   )
 ```
 
-#### 📘 `create_index_hnsw()` Parameters
+#### 📘 `create()` Parameters
 
 | Parameter        | Type   | Default   | Description                                                                 |
 |------------------|--------|-----------|-----------------------------------------------------------------------------|
+| `index_type`     | `str`  | `"hnsw"`  | The type of vector index to create. Currently supports `"hnsw"`. Future options include `"ivf"`, `"flat"`, etc. Case-insensitive. |
 | `dim`            | `int`  | `1536`    | Dimensionality of the vectors to be indexed. Each vector must have this length. The default dim=1536 is chosen to match the output dimensionality of OpenAI’s text-embedding-ada-002 model. |
 | `space`          | `str`  | `"cosine"`| Distance metric used for similarity search. Options include `"cosine"`. Additional metrics such as `"l2"`, and `"dot"` will be added in future versions. |
-| `M`              | `int`  | `16`      | Number of bi-directional connections created for each new node. Higher `M` improves recall but increases index size and build time. |
+| `m`              | `int`  | `16`      | Number of bi-directional connections created for each new node. Higher `m` improves recall but increases index size and build time. |
 | `ef_construction`| `int`  | `200`     | Size of the dynamic list used during index construction. Larger values increase indexing time and memory, but improve quality. |
 | `expected_size`  | `int`  | `10000`   | Estimated number of elements to be inserted. Used for preallocating internal data structures. Not a hard limit. |
 
@@ -393,7 +395,7 @@ print(index.info())
 ```
 *Output*
 ```
-HNSWIndex(dim=8, space=cosine, M=16, ef_construction=200, expected_size=5, vectors=5)
+HNSWIndex(dim=8, space=cosine, m=16, ef_construction=200, expected_size=5, vectors=5)
 ```
 
 <br/>

zeusdb_vector_database-0.1.0.dist-info/RECORD

@@ -0,0 +1,10 @@
+zeusdb_vector_database-0.1.0.dist-info/METADATA,sha256=TpOxVHETFf2PMjZVWwjxyV43ZJPIsuIqTmBmwCXfJGI,22218
+zeusdb_vector_database-0.1.0.dist-info/WHEEL,sha256=A0NA77PxChGQFi1IYP9OCFEqCQA-RdpKrrZdN1LBaAI,107
+zeusdb_vector_database-0.1.0.dist-info/licenses/LICENSE,sha256=82Hi3E_KqpDOBk00HrY6fGiErqL3QJquGQ6dUu9wJzE,11336
+zeusdb_vector_database-0.1.0.dist-info/licenses/NOTICE,sha256=GDGZ9V3p4Uvaj-1RT9Pbeczps-rSeZz8q8wSxb_Q13o,971
+zeusdb_vector_database.libs/libgcc_s-5b5488a6.so.1,sha256=HGKUsVmTeNAxEdSy7Ua5Vh_I9FN3RCbPWzvZ7H_TrwE,2749061
+zeusdb_vector_database/__init__.py,sha256=WANw_gobvA72v6z1tydjyWwRUvx01mnCjMX55LXbeic,202
+zeusdb_vector_database/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+zeusdb_vector_database/vector_database.py,sha256=7Gs9FiasO5suqc3E8mxxtW1ORIXBh-8AXvp0pQo1VYc,3463
+zeusdb_vector_database/zeusdb_vector_database.cpython-311-arm-linux-musleabihf.so,sha256=9ZVe65qhPj3r-ln_sBTaA-N1zYquzT5mN4ZQuHFt4Z0,4231365
+zeusdb_vector_database-0.1.0.dist-info/RECORD,,

zeusdb_vector_database-0.0.9.dist-info/RECORD

@@ -1,10 +0,0 @@
-zeusdb_vector_database-0.0.9.dist-info/METADATA,sha256=M8_KsB8EW0BjPjwilv8mSoXa0NCNbkTHvV7VPovx5U4,21994
-zeusdb_vector_database-0.0.9.dist-info/WHEEL,sha256=A0NA77PxChGQFi1IYP9OCFEqCQA-RdpKrrZdN1LBaAI,107
-zeusdb_vector_database-0.0.9.dist-info/licenses/LICENSE,sha256=82Hi3E_KqpDOBk00HrY6fGiErqL3QJquGQ6dUu9wJzE,11336
-zeusdb_vector_database-0.0.9.dist-info/licenses/NOTICE,sha256=GDGZ9V3p4Uvaj-1RT9Pbeczps-rSeZz8q8wSxb_Q13o,971
-zeusdb_vector_database.libs/libgcc_s-5b5488a6.so.1,sha256=HGKUsVmTeNAxEdSy7Ua5Vh_I9FN3RCbPWzvZ7H_TrwE,2749061
-zeusdb_vector_database/__init__.py,sha256=8nQKR99xrTRvMgH_Z2nNI4XtwkTAi5DmkjBxUxxeJho,202
-zeusdb_vector_database/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-zeusdb_vector_database/vector_database.py,sha256=HmOjY7qOWfh0We-85qmfVmwoVSlM9zD-Hj1SvplMtF0,1621
-zeusdb_vector_database/zeusdb_vector_database.cpython-311-arm-linux-musleabihf.so,sha256=ll_m1lIi0RDIgaoGTTAwNWDFn2Wg7LGXkRvfZxIcSzk,4231365
-zeusdb_vector_database-0.0.9.dist-info/RECORD,,