AzureCosmosDBNoSqlVectorSearch(
self,
*,
cosmos_client: CosmosClient,
embedding: Embeddings,
vector_embedding_policy: | Name | Type | Description |
|---|---|---|
cosmos_client* | CosmosClient | Client used to connect to azure cosmosdb no sql account. |
database_name | str | Default: 'vectorSearchDB'Name of the database to be created. |
container_name | str | Default: 'vectorSearchContainer'Name of the container to be created. |
embedding* | Embeddings | |
vector_embedding_policy* | Dict[str, Any] | |
full_text_policy | Optional[Dict[str, Any]] | Default: None |
indexing_policy* | Dict[str, Any] | |
cosmos_container_properties* | Dict[str, Any] | |
cosmos_database_properties* | Dict[str, Any] | |
text_key | str | Default: 'text' |
embedding_key | str | Default: 'embedding' |
metadata_key | str | Default: 'metadata' |
create_container | bool | Default: True |
full_text_search_enabled | bool | Default: False |
| Name | Type |
|---|---|
| cosmos_client | CosmosClient |
| embedding | Embeddings |
| 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]] |
| database_name | str |
| container_name | str |
| text_key | str |
| embedding_key | str |
| metadata_key | str |
| create_container | bool |
| full_text_search_enabled | bool |
Azure Cosmos DB for NoSQL 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
Text embedding model to use.
Vector Embedding Policy for the container.
Full Text Policy for the container.
Indexing Policy for the container.
Container Properties for the container.
Database Properties for the container.
Text key to use for text property which will be embedded in the data schema.
Embedding key to use for vector embedding.
Metadata key to use for data schema.
Set to true if the container does not exist.
Set to true if the full text search is enabled.