DataStax announced the launch of RAGStack, an out-of-the-box RAG solution designed to simplify implementation of retrieval augmented generation (RAG) applications built with LangChain. RAGStack reduces the complexity and overwhelming choices that developers face when implementing RAG for their generative AI applications with a streamlined, tested, and efficient set of tools and techniques for building with LLMs.
With RAGStack, companies benefit from a preselected set of open-source software for implementing generative AI applications, providing developers with a ready-made solution for RAG that leverages the LangChain ecosystem including LangServe, LangChain Templates and LangSmith, along with Apache Cassandra and the DataStax Astra DB vector database. This removes the hassle of having to assemble a bespoke solution and provides developers with a simplified, comprehensive generative AI stack.
RAG combines the strengths of both retrieval-based and generative AI methods for natural language understanding and generation, enabling real-time, contextually relevant responses that underpin much of the innovation happening with this technology.
With specifically curated software components, abstractions to improve developer productivity and system performance, enhancements that improve existing vector search techniques, and compatibility with most generative AI data components, RAGStack provides overall improvements to the performance, scalability, and cost of implementing RAG in generative AI applications.
Fivetran announced the launch of two new software developer kits (SDKs) for data source connectors and target destinations. These new SDKs enable third-party vendors to develop new connectors and destinations on Fivetran’s platform – unlocking compatibility with their product and Fivetran’s network of 400+ connectors, 14 destinations and 45,000+ users.
More complex databases and API-enabled software vendors can become Fivetran source partners by writing their own integration on the Connector SDK. Fivetran connectors add value by providing customers with an easy, automated and reliable way to move their data to their destination of choice, efficiently and in an analytic-ready format, for analysis and enrichment with other data.
Data warehouse, data lake and storage vendors can leverage the destination SDK for Fivetran to allow joint customers to load their critical business data from any of Fivetran’s 400+ connectors to their destination platform. Centralizing data into a single destination empowers customers to access analytical and transactional data for reporting, efficiencies and predictive analytics. The gRPC-based SDK allows connectors and destinations to be written in any supported programming language.
SnapLogic announced it has entered a multifaceted partnership with Acolad, a provider of content and language solutions. Together they will develop and deliver generative AI translation services from Acolad based on the generative integration solutions from SnapLogic.
The collaboration is meant to go beyond a conventional business alliance to deliver new solutions that benefit both language and integration professionals with accelerated productivity, increase revenue streams, and to introduce new services to technical and non-technical users. Acolad will create pre-built integration connectors for instant document translation, allowing any SnapLogic user to immediately add Acolad’s multi-level AI-powered translation service to new and existing integration pipelines without any coding knowledge.
The solution will employ Acolad’s proprietary two-stage AI-process to provide accuracy for both language translation and intent, in near real-time. This allows any enterprise to immediately leverage the global language translation services, eliminating language barriers with customers, partners, and employees. Acolad will leverage SnapLogic’s generative integration interface, SnapGPT, to automate integration processes to create new translation services more quickly, create new revenue streams and service packages, and increase customer satisfaction among Acolad’s customer base.
https://www.snaplogic.com ■ https://www.acolad.com
Cloudera, Inc., a data company for enterprise artificial intelligence (AI), and Pinecone, a vector database company providing long-term memory for AI, announced a strategic partnership that integrates Pinecone’s AI vector database expertise into Cloudera’s open data platform, aimed to help organizations use AI to streamline operations and improve customer experiences.
Pinecone is optimized to store AI representations of data (vector embeddings) and search through them by semantic similarity. This capability is necessary for adding context to queries against applications that use Large Language Models (LLMs) to reduce erroneous outputs and helps search and Generative AI applications deliver more accurate and relevant responses.
Pinecone’s vector database will also be integrated into Cloudera Data Platform (CDP), and includes the release of a new Applied ML Prototype (AMP) that will allow developers to more quickly create and augment new knowledge bases from data on their own website, as well as pre-built connectors that will enable customers to quickly set up ingest pipelines in AI applications.
Customers can use this same architecture to set up or improve support chatbots or internal support search systems to reduce operational costs and improve customer experience by decreasing human case-handling efforts and faster resolution times.
https://www.cloudera.com ■ https://www.pinecone.io