DataStax announced new features and updates to its AI
PaaS, which minimizes hallucinations with up to 20% higher relevance,
74x faster response time, and 9x higher throughput. DataStax
will demonstrate all of the new updates tonight, alongside industry
experts from Glean, Unstructured.io, and more at its
RAG++ NYC event, to be held at Pier Sixty at Chelsea Pier.
With DataStax, developers can focus on application
development, rather than infrastructure management, powered by multiple,
new updates to the DataStax AI PaaS.
Simplifying Data Ingestion to Improve Relevancy with Unstructured.io
Data preparation and ingestion is one of the biggest
challenges when building a GenAI application. Developers are faced with
converting massive amounts of existing data, in different formats, into a
format suitable for use in retrieval-augmented generation (RAG). Often these documents are too large for embedding models to ingest and must be broken up into smaller segments or chunked.
To solve this problem Unstructured is now natively integrated with Langflow and Astra DB,
simplifying complex configuration options and bringing the power of
Unstructured's ingestion pipelines to DataStax users. Developers can
easily import multiple PDF files of any size, chunk those files, and
using DataStax Vectorize, they can generate the vector embeddings for
improved query relevancy.
This update adds support for more file types and
streamlines data processing by bringing data preparation directly into
the data loading process. Users can control chunk sizes to optimize
semantic relevance and improve RAG performance. This leads to more
relevant query results and better application resource utilization.
Read more about the native integration with Unstructured.
Enabling Seamless Access to Data with New Glean Integrations
DataStax will introduce a new integration that allows users
to seamlessly connect their data stored in Astra DB with Glean. With
this integration, Glean will be able to directly access and analyze data
stored in Astra DB, enabling the platform to answer complex questions
and provide relevant, accurate query responses.
Additionally, users will be able to leverage a new Glean
Component for DataStax Langflow which enables developers to easily
create Glean queries within a Langflow flow. Users can tap into Glean's
indexing capabilities to enrich the context of their operations and make
more informed decisions based on real-time data insights.
The Glean integration is another example of the robust
GenAI ecosystem being built into DataStax Langflow, which will provide
developers the most diverse ecosystem of integration partners via its AI
PaaS.
Driving Agility in GenAI Application Development with the Langflow API
DataStax has further enhanced its AI PaaS with the free
public preview of the DataStax Langflow API. The Langflow API lets
developers build and host their GenAI application anywhere with a simple
HTTP call to an API endpoint hosted by DataStax, providing a fast and
easy path to production.
This simplifies and speeds up deployment by removing the
overhead of self-hosting an application, and integrates with external
applications to easily embed GenAI into existing projects. The API is
accessible over HTTP, and Langflow includes JavaScript and Python code
snippets that can be dropped into a developer's application.
Read more about the public preview of the DataStax Langflow API.