Integrations overview

Integrations connect third-party tools to Astra DB Serverless for data management, machine learning, analytics, and more.

Add an integration

You can add an integration with the Astra Portal.

  1. Open the Astra Portal, and then switch to the organization that you want to use with this integration.

  2. Go to Settings > Integrations.

  3. In the All Integrations section, select the integration you want to add, and then complete the configuration.

    If you don’t see your integration, check the list of other integrations.
  4. Refresh the page. If the installation succeeded, your integration will appear in the Active section.

Remove an active integration

You can permanently remove an active integration with the Astra Portal.

  1. Open the Astra Portal, and then switch to the organization with the integration that you want to remove.

  2. Go to Settings > Integrations.

  3. In the Active section, select an integration to remove.

    If you don’t see your integration, check the list of other integrations.
  4. Click Remove, and then click Remove again to confirm.

If the removal succeeded, your integration will no longer appear in the Active section.

Other integrations

Build your generative AI application with these integrations connected to your Serverless (Vector) database:

Airbyte

Airbyte can use Astra DB Serverless as a destination for streams and embeddings.

Azure OpenAI

Integrate Azure OpenAI as an external embedding provider for Astra DB vectorize to leverage Azure OpenAI’s embeddings API within Astra DB Serverless.

Cohere

After embedding text with Cohere’s embedding models, Astra DB Serverless indexes the text to perform similarity searches. Using a portion of the Stanford Question Answering Dataset (SQuAD), set up a Retrieval-Augmented Generation (RAG) pipeline and perform similarity searches.

Grafana Cloud

Grafana Cloud can consume and visualize Astra DB Serverless health metrics.

Haystack

Haystack can use Astra DB Serverless to store and retrieve vectors for ML applications.

Hugging Face - Dedicated

Integrate Hugging Face - Dedicated as an external embedding provider for Astra DB vectorize to leverage Hugging Face’s embeddings API within Astra DB Serverless.

Hugging Face - Serverless

Integrate Hugging Face - Serverless as an external embedding provider for Astra DB vectorize to leverage Hugging Face’s embeddings API within Astra DB Serverless.

Jina AI

Integrate Jina AI as an external embedding provider for Astra DB vectorize to leverage Jina AI’s embeddings API within Astra DB Serverless.

LangChain and LangChain.js

LangChain and LangChain.js can use Astra DB Serverless to store and retrieve vectors for ML applications.

LlamaIndex and LlamaIndex.TS

LlamaIndex and LlamaIndex.TS can use Astra DB Serverless to store and retrieve vectors for ML applications.

Mistral AI

Integrate Mistral AI as an external embedding provider for Astra DB vectorize to leverage Mistral AI’s embeddings API within Astra DB Serverless.

MongooseJS

MongooseJS is a popular framework for Object Data Modeling (ODM) on top of document databases. This integration lets you connect MongooseJS apps to an Astra DB Serverless database and use the Data API.

NVIDIA

Integrate NVIDIA as a native embedding provider for Astra DB vectorize.

OpenAI

Integrate OpenAI as an external embedding provider for Astra DB vectorize to leverage OpenAI’s embeddings API within Astra DB Serverless.

Semantic Kernel

The Semantic Kernel integration simplifies the creation of AI agents and uses Astra DB Serverless to store and retrieve vector data.

Superagent

Superagent allows you to build, manage, and deploy unique AI Assistants with Astra DB Serverless as your backend vector store.

Upstage

Integrate Upstage AI as an external embedding provider for Astra DB vectorize to leverage Upstage AI’s embeddings API within Astra DB Serverless.

Unstructured.io

The Unstructured.io integration with Astra DB Serverless makes your data LLM-ready for use in RAG pipelines and applications. Unstructured.io provides a no-code platform and cloud service that handles any complex enterprise document type. Unstructured.io then transforms, cleans, and generates embeddings with Astra DB Serverless serving as the vector data store destination.

Vercel

Vercel can use Astra DB Serverless to store and retrieve vectors for your front-end applications.

Vertex AI

Vertex AI can integrate LLMs such as Google Gemini with your Serverless (Vector) databases, allowing Gemini to directly retrieve and manipulate data stored within Astra DB.

Vertex AI search and conversation

Vertex AI search and conversation apps can use Astra DB Serverless to store and retrieve vectors for ML applications.

Voyage AI

Integrate Voyage AI as an external embedding provider for Astra DB vectorize to leverage Voyage AI’s embeddings API within Astra DB Serverless.

In-product integration guides

In the Astra Portal, select Integrations in the left navigation to see and use the available integrations. Each integration offers an overview, prerequisites, a quickstart procedure, installation, and other recommended integrations.

700

Explore integrations for a variety of use cases. For users just getting started, explore integrated development environments (IDE), frameworks, and Platform-as-a-Service integrations. For users with a production database in their app stack, consider monitoring, observability, data exploration, analytics tools, and security integrations.

See the following list of integrations organized by category:

Integration Tags

Amazon Bedrock

generative AI | embeddings | LLM | Vector

AWS GameSparks

AWS | FaaS | Java | Python | serverless

AWS Glue

data management | ide | jdbc

AWS Lambda Functions

AWS | FaaS | Java | Python | serverless

Apache Airflow

ETL | machine learning | Python | third-party tools | workflow

Apache Nifi

ETL | Java | third-party tools | workflow

Apache Spark

machine learning | middleware | Java | Python

Authorizer

ETL | machine learning | Python | third-party tools | workflow

Azure Functions

Azure | FaaS | Java | serverless | Python

Cadence

CQL | Go | third-party tools | workflow

CircleCI

devops | third-party tools

Data Grip

data management | ide | jdbc

DBeaver

ETL | machine learning | Python | third-party tools | workflow

DataStation

ide

DataStax Studio

notebook

DbSchema

Data management | ide | jdbc

Feast

machine learning | Python | third-party tools

Flink

Java | middleware | third-party tools

GCP Dataflow

data management ETL | Java | third-party tools | workflow

Google Cloud Functions

FaaS | GCP | Java | Python | serverless

Grafana

CQL | data management | data visualization | devops | go | Java

IntelliJ

IDE plugins | Java |

JanusGraph

database | graph | jdbc | Java | third-party tools

Lagom

framework | Java | Scala

LangChain

generative AI | GPT | LLM | prompt | Python | third-party tools | vector

Liquibase

devops | jdbc | third-party tools

LlamaIndex

generative AI | GPT | LLM | prompt | Python | third-party tools | vector

Micronaut

CQL | framework | Java |

Microsoft Power Query

ETL | Microsoft | powerbi | third-party tools | workflow

MindsDB

data management | machine learning | Python

Netflix Data Explorer

CQL | data management | IDE

NoSQLBench

CQL | data management | Java |

Pentaho

ETL | jdbc | third-party tools

Quine

ETL | graph | Java | Scala | streaming | third-party tools

Spring

framework | Java

StepZen

GraphQL | Javascript | third-party tools

Strapi

Doc API | Javascript | Node.js | third-party tools

TablePlus

IDE | data management | jdbc

Tableau

analytics | business intelligence | data visualization | SQL | visual querying

Temporal

CQL | framework | Go | third-party tools

Trino

analytics | query engine | SQL

Vault

devops | third-party tools

Vercel

framework | Javascript | third-party tools

To explore integrations by tags, see the integrations directly in the Astra Portal.

Was this helpful?

Give Feedback

How can we improve the documentation?

© 2024 DataStax | Privacy policy | Terms of use

Apache, Apache Cassandra, Cassandra, Apache Tomcat, Tomcat, Apache Lucene, Apache Solr, Apache Hadoop, Hadoop, Apache Pulsar, Pulsar, Apache Spark, Spark, Apache TinkerPop, TinkerPop, Apache Kafka and Kafka are either registered trademarks or trademarks of the Apache Software Foundation or its subsidiaries in Canada, the United States and/or other countries. Kubernetes is the registered trademark of the Linux Foundation.

General Inquiries: +1 (650) 389-6000, info@datastax.com