Skip to main content

llama-index vector_stores nile integration

Project description

Nile Vector Store (PostgreSQL)

This integration makes it possible to use Nile - Postgres re-engineered for multi-tenant applications as a vector store in LlamaIndex.

What is Nile?

Nile is a Postgres database that enables all database operations per tenant including auto-scaling, branching, and backups, with full customer isolation.

Multi-tenant RAG applications are increasingly popular, since they provide security and privacy while using large language models.

However, managing the underlying Postgres database is not straightforward. DB-per-tenant is expensive and complex to manage, while shared-DB has security and privacy concerns, and also limits the scalability and performance of the RAG application. Nile re-engineered Postgres to deliver the best of all worlds - the isolation of DB-per-tenant, at the cost, efficiency and developer experience of a shared-DB.

Storing millions of vectors in a shared-DB can be slow and require significant resources to index and query. But if you store 1000 tenants in Nile's virtual tenant databases, each with 1000 vectors, this can be quite manageable. Especially since you can place larger tenants on their own compute, while smaller tenants can efficiently share compute resources and auto-scale as needed.

Getting Started with Nile

Start by signing up for Nile. Once you've signed up for Nile, you'll be promoted to create your first database. Go ahead and do so. You'll be redirected to the "Query Editor" page of your new database.

From there, click on "Home" (top icon on the left menu), click on "generate credentials" and copy the resulting connection string. You will need it in a sec.

Quickstart

Install the integration with:

pip install llama-index-vector-stores-nile

Use the connection string you generated earlier (at the "Getting started" step) to create a tenant-aware vector store.

:fire: NileVectorStore supports both tenant-aware vector stores, that isolates the documents for each tenant and a regular store which is typically used for shared data that all tenants can access. Below, we'll demonstrate the tenant-aware vector store.

# Replace with your connection string.
NILE_SERVICE_URL = "postgresql://nile:password@db.thenile.dev:5432/nile"

vector_store = NileVectorStore(
    service_url=NILEDB_SERVICE_URL,
    table_name="documents",
    tenant_aware=True,
    num_dimensions=1536,
)

Create an index from documents:

storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents_nexiv + documents_modamart,
    storage_context=storage_context,
    show_progress=True,
)

Or from existing embeddings:

index = VectorStoreIndex.from_vector_store(vector_store=vector_store)

and query each tenant's data with guaranteed isolation:

query_engine = index.as_query_engine(
    vector_store_kwargs={
        "tenant_id": str(tenant_id_modamart),
    },
)
response = query_engine.query("What action items do we need to follow up on?")

print(response)

See resources below for more information and examples.

Additional Resources

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

llama_index_vector_stores_nile-0.2.2.tar.gz (9.7 kB view details)

Uploaded Source

Built Distribution

File details

Details for the file llama_index_vector_stores_nile-0.2.2.tar.gz.

File metadata

File hashes

Hashes for llama_index_vector_stores_nile-0.2.2.tar.gz
Algorithm Hash digest
SHA256 6fcf034c8c8ac0f4354d48532f6720ee65215909696898484d64642591b4a6ad
MD5 ed8adc6a8f2a79a9ac9a27f680b51e6b
BLAKE2b-256 e7f048e0f0d1ad765a777b6ed268b1998d6243b61a7c9f5e2468761f4ac8f1d2

See more details on using hashes here.

File details

Details for the file llama_index_vector_stores_nile-0.2.2-py3-none-any.whl.

File metadata

File hashes

Hashes for llama_index_vector_stores_nile-0.2.2-py3-none-any.whl
Algorithm Hash digest
SHA256 bfa3bde19565d98e5b9f583de9ba9ef31db1bb9f37b92f2596bb6952154b1beb
MD5 a96d5ec7972a570dc54a4d51d9b28793
BLAKE2b-256 0382fb21aa06d1b0a258409f1d986c9cebed574d541aab96d610f5f7eb80a092

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page