gllm-datastore-binary 0.0.15__cp312-cp312-win_amd64.whl → 0.0.16__cp312-cp312-win_amd64.whl

gllm_datastore/vector_data_store/chroma_vector_data_store.pyi

@@ -5,8 +5,9 @@ from gllm_core.schema.chunk import Chunk
 from gllm_datastore.constants import DEFAULT_TOP_K as DEFAULT_TOP_K
 from gllm_datastore.utils.converter import from_langchain as from_langchain, to_langchain as to_langchain
 from gllm_datastore.vector_data_store.vector_data_store import BaseVectorDataStore as BaseVectorDataStore
+from gllm_inference.em_invoker.em_invoker import BaseEMInvoker
 from langchain_core.documents import Document as Document
-from langchain_core.embeddings import Embeddings as Embeddings
+from langchain_core.embeddings import Embeddings
 from typing import Any
 
 DEFAULT_NUM_CANDIDATES: int
@@ -30,25 +31,20 @@ class ChromaVectorDataStore(BaseVectorDataStore):
     using the langchain-chroma integration.
 
     Attributes:
+        store (Chroma): The langchain Chroma vector store instance.
         collection_name (str): The name of the ChromaDB collection to use.
-        embedding: The model used to generate embeddings.
-        client: The ChromaDB client instance.
-            1. MEMORY: In-memory client (chromadb.Client)
-            2. PERSISTENT: Persistent client (chromadb.PersistentClient)
-            3. HTTP: HTTP client for client-server architecture (chromadb.HttpClient)
-        vector_store (Chroma): The langchain Chroma vector store instance.
         num_candidates (int): The maximum number of candidates to consider during search.
     """
+    store: Incomplete
     collection_name: Incomplete
-    embedding: Incomplete
-    vector_store: Incomplete
     num_candidates: Incomplete
-    def __init__(self, collection_name: str, embedding: Embeddings | None = None, client_type: ChromaClientType = ..., persist_directory: str | None = None, host: str | None = None, port: int | None = None, num_candidates: int = ..., **kwargs: Any) -> None:
+    def __init__(self, collection_name: str, embedding: BaseEMInvoker | Embeddings | None = None, client_type: ChromaClientType = ..., persist_directory: str | None = None, host: str | None = None, port: int | None = None, num_candidates: int = ..., **kwargs: Any) -> None:
         """Initialize the ChromaDB vector data store with langchain-chroma.
 
         Args:
             collection_name (str): Name of the collection to use in ChromaDB.
-            embedding (Embeddings | None): Function to generate embeddings.
+            embedding (BaseEMInvoker | Embeddings | None, optional): The embedding model to perform vectorization.
+                Defaults to None.
             client_type (ChromaClientType, optional): Type of ChromaDB client to use.
                 Defaults to ChromaClientType.MEMORY.
             persist_directory (str | None, optional): Directory to persist vector store data.

gllm_datastore/vector_data_store/elasticsearch_vector_data_store.pyi

@@ -3,7 +3,8 @@ from gllm_core.schema import Chunk
 from gllm_datastore.constants import DEFAULT_REQUEST_TIMEOUT as DEFAULT_REQUEST_TIMEOUT, DEFAULT_TOP_K as DEFAULT_TOP_K
 from gllm_datastore.utils.converter import from_langchain as from_langchain, to_langchain as to_langchain
 from gllm_datastore.vector_data_store.vector_data_store import BaseVectorDataStore as BaseVectorDataStore
-from langchain_core.embeddings import Embeddings as Embeddings
+from gllm_inference.em_invoker.em_invoker import BaseEMInvoker
+from langchain_core.embeddings import Embeddings
 from typing import Any
 
 class ElasticsearchVectorDataStore(BaseVectorDataStore):
@@ -21,12 +22,12 @@ class ElasticsearchVectorDataStore(BaseVectorDataStore):
     index_name: Incomplete
     store: Incomplete
     logger: Incomplete
-    def __init__(self, index_name: str, embedding: Embeddings | None = None, connection: Any | None = None, url: str | None = None, cloud_id: str | None = None, user: str | None = None, api_key: str | None = None, password: str | None = None, vector_query_field: str = 'vector', query_field: str = 'text', distance_strategy: str | None = None, strategy: Any | None = None, request_timeout: int = ...) -> None:
+    def __init__(self, index_name: str, embedding: BaseEMInvoker | Embeddings, connection: Any | None = None, url: str | None = None, cloud_id: str | None = None, user: str | None = None, api_key: str | None = None, password: str | None = None, vector_query_field: str = 'vector', query_field: str = 'text', distance_strategy: str | None = None, strategy: Any | None = None, request_timeout: int = ...) -> None:
         '''Initializes an instance of the ElasticsearchVectorDataStore class.
 
         Args:
             index_name (str): The name of the Elasticsearch index.
-            embedding (Embeddings | None, optional): The Embeddings object for vector operations. Defaults to None.
+            embedding (BaseEMInvoker | Embeddings): The embedding model to perform vectorization.
             connection (Any | None, optional): The Elasticsearch connection object. Defaults to None.
             url (str | None, optional): The URL of the Elasticsearch server. Defaults to None.
             cloud_id (str | None, optional): The cloud ID of the Elasticsearch cluster. Defaults to None.
@@ -39,6 +40,9 @@ class ElasticsearchVectorDataStore(BaseVectorDataStore):
             strategy (Any | None, optional): The retrieval strategy for retrieval. Defaults to None, in which case
                 DenseVectorStrategy() is used.
             request_timeout (int, optional): The request timeout. Defaults to DEFAULT_REQUEST_TIMEOUT.
+
+        Raises:
+            TypeError: If `embedding` is not an instance of `BaseEMInvoker` or `Embeddings`.
         '''
     async def query(self, query: str, top_k: int = ..., retrieval_params: dict[str, Any] | None = None) -> list[Chunk]:
         """Queries the Elasticsearch data store.

gllm_datastore.pyi

@@ -53,6 +53,9 @@ import langchain_core
 import langchain_core.documents
 import sys
 import gllm_core.schema.chunk
+import gllm_inference
+import gllm_inference.em_invoker
+import gllm_inference.em_invoker.em_invoker
 import langchain_core.embeddings
 import chromadb
 import chromadb.types

{gllm_datastore_binary-0.0.15.dist-info → gllm_datastore_binary-0.0.16.dist-info}/METADATA

@@ -1,10 +1,10 @@
 Metadata-Version: 2.1
 Name: gllm-datastore-binary
-Version: 0.0.15
+Version: 0.0.16
 Summary: A library containing data store components for Gen AI applications.
 Author: Berty C L Tobing
 Author-email: berty.c.l.tobing@gdplabs.id
-Requires-Python: >=3.11,<4.0
+Requires-Python: >=3.11,<3.13
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
@@ -16,6 +16,7 @@ Provides-Extra: redis
 Requires-Dist: Jinja2 (>=3.1.4,<4.0.0) ; extra == "kg"
 Requires-Dist: chromadb (>=0.6.3,<0.7.0) ; extra == "chroma"
 Requires-Dist: gllm-core-binary
+Requires-Dist: gllm-inference-binary
 Requires-Dist: langchain-chroma (>=0.2.2,<0.3.0) ; extra == "chroma"
 Requires-Dist: langchain-elasticsearch (==0.3.0) ; extra == "elasticsearch"
 Requires-Dist: llama-index-core (>=0.12.0,<0.13.0) ; extra == "kg"

{gllm_datastore_binary-0.0.15.dist-info → gllm_datastore_binary-0.0.16.dist-info}/RECORD

@@ -26,13 +26,13 @@ gllm_datastore/utils/__init__.pyi,sha256=YE0R6kzfJGi0LVj12JDTYJBTXr2sFdDnPUKw1k6
 gllm_datastore/utils/converter.pyi,sha256=H4_O-diiWw33TDEqHWB24SR25tpbuSE6Lu6-G7o_X28,610
 gllm_datastore/utils/ttl.pyi,sha256=CPGdxD3HpWABw149t-kS_usPReNMj-jRaVRnrd8TDWk,778
 gllm_datastore/vector_data_store/__init__.pyi,sha256=U1x8eo3OJ5jTjoC4fz2zgyapxZmn-e3ZtI8D32PQ_-g,331
-gllm_datastore/vector_data_store/chroma_vector_data_store.pyi,sha256=NQNTcOztwiHhzApsweT_5xotEk_CUTZHYuP7kl8WEjA,6529
+gllm_datastore/vector_data_store/chroma_vector_data_store.pyi,sha256=RCevJFssGYEoxFiirO2XbHNWWstJCYoQLeXse_WXgOY,6302
 gllm_datastore/vector_data_store/elasticsearch_data_store.pyi,sha256=1-lXVSacRhm0FIwykJwUI9lOwRQmrYCVF5cYOx7qjaw,450
-gllm_datastore/vector_data_store/elasticsearch_vector_data_store.pyi,sha256=Bja4Woio3cAw5SY1FPQRRYAjbPzenb02iYDxePw6i7o,8086
+gllm_datastore/vector_data_store/elasticsearch_vector_data_store.pyi,sha256=_AiU29bZeb4NxD32KdUVNk-2g0m9CUclvxlSdbYjGFI,8233
 gllm_datastore/vector_data_store/vector_data_store.pyi,sha256=GoeW_BxpZywJ11oEWHEXw7P0kap7LWxE-3p3KpaHhk4,2695
 gllm_datastore.build/.gitignore,sha256=aEiIwOuxfzdCmLZe4oB1JsBmCUxwG8x-u-HBCV9JT8E,1
-gllm_datastore.cp312-win_amd64.pyd,sha256=sqZcOVWLjNuK3c_ff56tOrV8pAa-F_4NuKPyUop-Kas,1125888
-gllm_datastore.pyi,sha256=gSGm1EVJP80w3dv9DffuYdvDilHCT67qkJc8dPtJpFA,1299
-gllm_datastore_binary-0.0.15.dist-info/METADATA,sha256=7rSZVe65XYS1QNvliXvw0gnZDHpcrIPtnZACyeMIxis,3900
-gllm_datastore_binary-0.0.15.dist-info/WHEEL,sha256=4N0hGcnWMI_Ty6ATf4qJqqSl-UNI-Ln828iTWGIywmU,98
-gllm_datastore_binary-0.0.15.dist-info/RECORD,,
+gllm_datastore.cp312-win_amd64.pyd,sha256=we3zTwcMdDPDvz7_wjO6y-ejgOhS_uove_mUzVTeEJU,1129472
+gllm_datastore.pyi,sha256=RtR6Nw07RMT9x5dPNhbP7XCDdEvjHZIamBLh2cNYAjU,1398
+gllm_datastore_binary-0.0.16.dist-info/METADATA,sha256=vyWCLl0OOuAZDCYxYSNhzjwoi3GEIOP2ujXNqtCyDPY,3938
+gllm_datastore_binary-0.0.16.dist-info/WHEEL,sha256=4N0hGcnWMI_Ty6ATf4qJqqSl-UNI-Ln828iTWGIywmU,98
+gllm_datastore_binary-0.0.16.dist-info/RECORD,,