Updates
Last updated
Was this helpful?
Last updated
Was this helpful?
Pipeline Editing Improvements
We've enhanced our pipeline editing capabilities, allowing you to modify existing pipelines without having to recreate them. You can now edit pipeline names directly from the pipeline view, add new data sources, change extraction techniques, and make other modifications to your RAG pipelines, making it simpler to organize and manage your data processing workflows.
Deep Research
We've added the ability to do deep research on your private data. Using the data in your pipeline, our deep research feature will generate a report on any topic. You can combine your private data with internet data using the web search and you can save the report as a PDF when it is done. You can specify exactly how you want the report to be structured, or you can let deep research figure it out.
Built-in Vectorize Database & Embedder
We've added a built-in vector database and embedder, allowing you to get your RAG pipeline up and running without needing to set up a separate vector database. You can still use your own database if preferred.
Interactive Pipeline Tour
The pipeline tour now not only walks you through the steps of creating a pipeline and retrieving data, but also creates a pipeline for you in real-time using the built-in vector database and embedder.
Visual RAG Pipeline Editor
We've released a completely new version of the pipeline editor. The new Visual RAG Pipeline Editor provides a cleaner, more intuitive experience, allowing you to build and deploy pipelines more efficiently. Check out our walkthrough.
Vectorize API Beta Enhancements
The API Beta continues to expand, adding more functionality for managing integrations and RAG pipelines. View the API docs.
Retrieval Performance
A new Retrieval Performance dashboard provides real-time monitoring and analysis of retrieval effectiveness. Learn more.
Support for Groq in our Chatbot Starter
Support for Groq has been added to the ready-to-use Next.js chatbot. The chatbot is pre-configured with your pipeline’s retrieval endpoint and can be downloaded from the Connect tab.
The Extraction Tester lets you test how different extraction methods process your documents before creating a RAG pipeline. This helps you choose the best extraction method for your specific documents and use case.
Documentation
Vectorize Iris is a model-based extraction solution that combines extraction and chunking into one streamlined process, making it easier than ever to get clean, usable text from complex documents.
Documentation
Manage your connectors, AI platforms, vector databases, and pipelines using the Vectorize API. The API is Beta and may change.
Documentation
Query rewriting uses conversation history to improve retrieval relevance. Before retrieving relevant documents, the system reformulates the user query based on the context of the conversation. This can help you provide more accurate answers to user queries.
Documentation
Performance metrics for RAG pipelines are now available in the Vectorize UI users on the Pro plan. The dashboard displays key metrics to help you evaluate retrieval performance, including:
Non-Rewritten Relevance
Rewritten Question Relevance
Overall Retrieval Health
If a pipeline has been inactive for 14 days (no data processed, no use of the retrieval endpoint), it will hibernate. In order to use the pipeline it must be manually restarted.
If the pipeline remains inactive after restart, after 14 days it will hibernate again.
To prevent a pipeline from hibernating:
Perform a single retrieval on the pipeline's endpoint.
A new document being written/updated will also prevent hibernation.
Documentation
Documentation
New Vector Databases
Qdrant
New Vector Databases
PostgreSQL
Added a context recall metric to RAG evaluations, which measures whether the retrieved context contains the necessary information to answer the provided question. The higher the value, the better the system is at retrieving relevant context.
New Vector Databases
Milvus / Zilliz Cloud
Added the ability to select multiple Dropbox folders to read data from.
Connectors
SharePoint
New AI Platforms
Vertex AI
Added support for Firecrawl's /scrape endpoint.
Integrations not in use by a RAG pipeline can now be edited.
Connectors
Firecrawl
Google Drive
Dropbox
OneDrive
New Vector Databases
SingleStore
New AI Platforms
Amazon Bedrock
Connectors and AI Platforms not being used by a pipeline can now be edited.
Added a tab which displays configuration for the source connector(s), AI platform, and vector database for the selected RAG pipeline.
Added an AI Assistant which will answer context-specific questions as you use Vectorize. You can optionally give the answer a thumbs-up or thumbs-down.
voyage-3
voyage-3-lite
voyage-finance-2
voyage-multilingual-2
voyage-law-2
voyage-code-2
