add documentation and vector quantization option

docs/components/vectordbs/dbs/azure_ai_search.mdx

@@ -0,0 +1,38 @@
+[Azure AI Search](https://learn.microsoft.com/en-us/azure/search/search-what-is-azure-search/) (formerly known as "Azure Cognitive Search") provides secure information retrieval at scale over user-owned content in traditional and generative AI search applications.
+
+### Usage
+
+```python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "sk-xx"
+
+config = {
+    "vector_store": {
+        "provider": "azure_ai_search",
+        "config": {
+            "service_name": "ai-search-test",
+            "api_key": "*****",
+            "collection_name": "mem0", 
+            "embedding_model_dims": 1536 ,
+            "use_compression": False
+        }
+    }
+}
+
+m = Memory.from_config(config)
+m.add("Likes to play cricket on weekends", user_id="alice", metadata={"category": "hobbies"})
+```
+
+### Config
+
+Let's see the available parameters for the `qdrant` config:
+service_name (str): Azure Cognitive Search service name.  
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `service_name` | Azure AI Search service name | `None` |
+| `api_key` | API key of the Azure AI Search service | `None` |
+| `collection_name` | The name of the collection/index to store the vectors, it will be created automatically if not exist | `mem0` |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
+| `use_compression` | Use scalar quantization vector compression | False |

mem0/configs/vector_stores/azure_ai_search.py

@@ -8,6 +8,7 @@ class AzureAISearchConfig(BaseModel):
     service_name: str = Field(None, description="Azure Cognitive Search service name")
     api_key: str = Field(None, description="API key for the Azure Cognitive Search service")
     embedding_model_dims: int = Field(None, description="Dimension of the embedding vector")
+    use_compression: bool = Field(False, description="Use compression or not")
 
     @model_validator(mode="before")
     @classmethod

mem0/vector_stores/azure_ai_search.py

@@ -13,6 +13,7 @@
     from azure.search.documents.indexes import SearchIndexClient
     from azure.search.documents.indexes.models import (
         HnswAlgorithmConfiguration,
+        ScalarQuantizationCompression,
         SearchField,
         SearchFieldDataType,
         SearchIndex,
@@ -36,7 +37,7 @@ class OutputData(BaseModel):
     payload: Optional[dict]  
 
 class AzureAISearch(VectorStoreBase):  
-    def __init__(self, service_name, collection_name, api_key, embedding_model_dims):  
+    def __init__(self, service_name, collection_name, api_key, embedding_model_dims, use_compression):  
         """Initialize the Azure Cognitive Search vector store.  
   
         Args:  
@@ -48,6 +49,7 @@ def __init__(self, service_name, collection_name, api_key, embedding_model_dims)
         self.index_name = collection_name  
         self.collection_name = collection_name
         self.embedding_model_dims = embedding_model_dims  
+        self.use_compression = use_compression
         self.search_client = SearchClient(endpoint=f"https://{service_name}.search.windows.net",  
                                           index_name=self.index_name,  
                                           credential=AzureKeyCredential(api_key))  
@@ -57,16 +59,35 @@ def __init__(self, service_name, collection_name, api_key, embedding_model_dims)
 
     def create_col(self):  
         """Create a new index in Azure Cognitive Search."""  
-        vector_dimensions = self.embedding_model_dims  # Set this to the number of dimensions in your vector  
+        vector_dimensions = self.embedding_model_dims  # Set this to the number of dimensions in your vector 
+
+
+        if self.use_compression:
+            vector_type = "Collection(Edm.Half)"
+        else:
+            vector_type = "Collection(Edm.Single)"
+
         fields = [  
             SimpleField(name="id", type=SearchFieldDataType.String, key=True),  
-            SearchField(name="vector", type=SearchFieldDataType.Collection(SearchFieldDataType.Single),
+            SearchField(name="vector", type=vector_type,
                 searchable=True, vector_search_dimensions=vector_dimensions, vector_search_profile_name="my-vector-config"),
             SimpleField(name="payload", type=SearchFieldDataType.String, searchable=True)  
         ]  
+
+
+        if self.use_compression:
+            compression_name = "myCompression"
+            compression_configurations = [
+                ScalarQuantizationCompression(compression_name=compression_name)
+            ]
+        else:
+            compression_name = None
+            compression_configurations = []
+
         vector_search = VectorSearch(
         profiles=[VectorSearchProfile(name="my-vector-config", algorithm_configuration_name="my-algorithms-config")],
         algorithms=[HnswAlgorithmConfiguration(name="my-algorithms-config")],
+        compressions=compression_configurations
         )
         index = SearchIndex(name=self.index_name, fields=fields, vector_search=vector_search)  
         self.index_client.create_or_update_index(index)