Pipelines
Pipelines transform your unstructured data to a searchable vector collection, chaining up the embedding, ingestion, search, and deletion of your data.
Zilliz Cloud Pipelines will be discontinued by the end of Q2 2025 and replaced by a new feature, “Data In, Data Out,” to streamline embedding generation in both Milvus and Zilliz Cloud. As of December 24, 2024, new user registrations are no longer accepted. Current users can continue using the service within the $20 monthly free allowance until the sunset date; however, no SLA is provided. Please consider using embedding APIs from model providers or open-source models to generate vector embeddings.
Pipelines Quickstart [READ MORE]
Zilliz Cloud Pipelines is a robust solution for transforming unstructured data such as documents, text pieces and images into a searchable vector collection. This guide provides a detailed description of the three main Pipelines types and provides and example of building a RAG application with Pipelines.
Ingest, Search, Delete [READ MORE]
Learn how to ingest, search, and delete various formats of unstructured data (eg. Images, texts, docs, etc.) with Zilliz Cloud Pipelines. Currently, three data formats are supported.
Connect to Your Data [READ MORE]
The connector is an in-built free tool that makes it easy to connect various data sources to a vector database. This guide will explain the concept of a connector and provide instructions on how to create and manage connectors in Zilliz Cloud Pipelines.
Pricing [READ MORE]
Understand the pricing of Zilliz Cloud Pipelines and learn how to estimate your pipeline usage.
Concepts [READ MORE]
Explanations about the relevant concepts we use when discussing how to use Zilliz Cloud Pipelines.
Pipeline Integrations [READ MORE]
Still do not know how to integrate great open-source and third-party services with Zilliz Cloud Pipelines? Use these guides to start with.