# Azure Cosmos DB for NoSQL Vector Store
This integration makes possible to use [Azure Cosmos DB for NoSQL](https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/)
as a vector store in LlamaIndex.
## Quick start
Install the integration with:
```sh
pip install llama-index-vector-stores-azurecosmosnosql
```
Create the CosmosDB client:
```python
URI = "AZURE_COSMOSDB_URI"
KEY = "AZURE_COSMOSDB_KEY"
client = CosmosClient(URI, credential=KEY)
```
Specify the vector store properties:
```python
indexing_policy = {
"indexingMode": "consistent",
"includedPaths": [{"path": "/*"}],
"excludedPaths": [{"path": '/"_etag"/?'}],
"vectorIndexes": [{"path": "/embedding", "type": "quantizedFlat"}],
}
vector_embedding_policy = {
"vectorEmbeddings": [
{
"path": "/embedding",
"dataType": "float32",
"distanceFunction": "cosine",
"dimensions": 3072,
}
]
}
```
Create the vector store:
```python
store = AzureCosmosDBNoSqlVectorSearch(
cosmos_client=client,
vector_embedding_policy=vector_embedding_policy,
indexing_policy=indexing_policy,
cosmos_container_properties={"partition_key": PartitionKey(path="/id")},
cosmos_database_properties={},
create_container=True,
)
```
Finally, create the index from a list containing documents:
```python
storage_context = StorageContext.from_defaults(vector_store=store)
index = VectorStoreIndex.from_documents(
documents, storage_context=storage_context
)
```
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-vector-stores-azurecosmosnosql",
"maintainer": null,
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": null,
"author": "Aayush Kataria",
"author_email": "aayushkataria3011@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/7f/58/cfa8f21edc596cf9a7834f092e3eace5b1b9cecf450a96c7f4ddff5d616d/llama_index_vector_stores_azurecosmosnosql-1.3.1.tar.gz",
"platform": null,
"description": "# Azure Cosmos DB for NoSQL Vector Store\n\nThis integration makes possible to use [Azure Cosmos DB for NoSQL](https://learn.microsoft.com/en-us/azure/cosmos-db/nosql/)\nas a vector store in LlamaIndex.\n\n## Quick start\n\nInstall the integration with:\n\n```sh\npip install llama-index-vector-stores-azurecosmosnosql\n```\n\nCreate the CosmosDB client:\n\n```python\nURI = \"AZURE_COSMOSDB_URI\"\nKEY = \"AZURE_COSMOSDB_KEY\"\nclient = CosmosClient(URI, credential=KEY)\n```\n\nSpecify the vector store properties:\n\n```python\nindexing_policy = {\n \"indexingMode\": \"consistent\",\n \"includedPaths\": [{\"path\": \"/*\"}],\n \"excludedPaths\": [{\"path\": '/\"_etag\"/?'}],\n \"vectorIndexes\": [{\"path\": \"/embedding\", \"type\": \"quantizedFlat\"}],\n}\n\nvector_embedding_policy = {\n \"vectorEmbeddings\": [\n {\n \"path\": \"/embedding\",\n \"dataType\": \"float32\",\n \"distanceFunction\": \"cosine\",\n \"dimensions\": 3072,\n }\n ]\n}\n```\n\nCreate the vector store:\n\n```python\nstore = AzureCosmosDBNoSqlVectorSearch(\n cosmos_client=client,\n vector_embedding_policy=vector_embedding_policy,\n indexing_policy=indexing_policy,\n cosmos_container_properties={\"partition_key\": PartitionKey(path=\"/id\")},\n cosmos_database_properties={},\n create_container=True,\n)\n```\n\nFinally, create the index from a list containing documents:\n\n```python\nstorage_context = StorageContext.from_defaults(vector_store=store)\n\nindex = VectorStoreIndex.from_documents(\n documents, storage_context=storage_context\n)\n```\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index vector_stores azurecosmosnosql integration",
"version": "1.3.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "92787b542149215a452d05210a20bb01aba93dbe6ecd985490b22e055728f514",
"md5": "b4b4cf805ec6ad34c7896931208b9163",
"sha256": "8bb682f1196ca48ac85181cba71f7a764e3210a4f32d1be3d6e33d4d4a1d9c15"
},
"downloads": -1,
"filename": "llama_index_vector_stores_azurecosmosnosql-1.3.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b4b4cf805ec6ad34c7896931208b9163",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 5237,
"upload_time": "2024-12-30T17:24:28",
"upload_time_iso_8601": "2024-12-30T17:24:28.457836Z",
"url": "https://files.pythonhosted.org/packages/92/78/7b542149215a452d05210a20bb01aba93dbe6ecd985490b22e055728f514/llama_index_vector_stores_azurecosmosnosql-1.3.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "7f58cfa8f21edc596cf9a7834f092e3eace5b1b9cecf450a96c7f4ddff5d616d",
"md5": "0194d4665f890a261727c9cb96d005ee",
"sha256": "25519fc245db66ce888dbc4536d51b2cef65b3879d1982ae9f632d8de3753ddb"
},
"downloads": -1,
"filename": "llama_index_vector_stores_azurecosmosnosql-1.3.1.tar.gz",
"has_sig": false,
"md5_digest": "0194d4665f890a261727c9cb96d005ee",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 4758,
"upload_time": "2024-12-30T17:24:30",
"upload_time_iso_8601": "2024-12-30T17:24:30.500500Z",
"url": "https://files.pythonhosted.org/packages/7f/58/cfa8f21edc596cf9a7834f092e3eace5b1b9cecf450a96c7f4ddff5d616d/llama_index_vector_stores_azurecosmosnosql-1.3.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-30 17:24:30",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-vector-stores-azurecosmosnosql"
}
JSON