AsyncAzureCosmosDBNoSqlVectorSearch(
self,
*,
cosmos_client: CosmosClient,
embedding: Embeddings,
database: DatabaseProxy,| Name | Type | Description |
|---|---|---|
cosmos_client* | CosmosClient | Async client used to connect to azure cosmosdb. |
embedding* | Embeddings | Text embedding model to use. |
database* | DatabaseProxy | Already-initialised async |
container* | ContainerProxy | Already-initialised async |
vector_embedding_policy* | Dict[str, Any] | |
indexing_policy* | Dict[str, Any] | |
cosmos_container_properties* | Dict[str, Any] | |
cosmos_database_properties* | Dict[str, Any] | |
full_text_policy | Optional[Dict[str, Any]] | Default: None |
vector_search_fields* | Dict[str, Any] | |
database_name | str | Default: 'vectorSearchDB' |
container_name | str | Default: 'vectorSearchContainer' |
search_type | str | Default: 'vector' |
metadata_key | str | Default: 'metadata' |
create_container | bool | Default: True |
full_text_search_enabled | bool | Default: False |
table_alias | str | Default: 'c' |
| Name | Type |
|---|---|
| cosmos_client | CosmosClient |
| embedding | Embeddings |
| database | DatabaseProxy |
| container | ContainerProxy |
| vector_embedding_policy | Dict[str, Any] |
| indexing_policy | Dict[str, Any] |
| cosmos_container_properties | Dict[str, Any] |
| cosmos_database_properties | Dict[str, Any] |
| full_text_policy | Optional[Dict[str, Any]] |
| vector_search_fields | Dict[str, Any] |
| database_name | str |
| container_name | str |
| search_type | str |
| metadata_key | str |
| create_container | bool |
| full_text_search_enabled | bool |
| table_alias | str |
Azure Cosmos DB for NoSQL async vector store.
To use, you should have both:
- the azure-cosmos python package installed
You can read more about vector search, full text search and hybrid search using AzureCosmosDBNoSQL here: https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/vector-search https://learn.microsoft.com/en-us/azure/cosmos-db/gen-ai/full-text-search https://learn.microsoft.com/en-us/azure/cosmos-db/gen-ai/hybrid-search
Vector Embedding Policy for the container.
Indexing Policy for the container.
Container Properties for the container.
Database Properties for the container.
Full Text Policy for the container.
Vector Search and Text Search Fields for the container.
Name of the database.
Name of the container.
CosmosDB Search Type to be performed.
Metadata key to use for data schema.
Whether the container was created.
Whether full text search is enabled.
Alias for the table in SQL queries.