Coveo's new API allows companies to accelerate their GenAI success by seamlessly integrating their own LLMs with Coveo's advanced retrieval technology.
With this new API, designed to improve precision, minimize hallucinations and protect data, GenAI applications will become instantly smarter and more secure.
Coveo to offer select companies' early access to the API, launching mid-September, with a full release slated for early 2025.
SAN FRANCISCO and MONTREAL, Sept. 10, 2024 /CNW/ - Coveo (TSX: CVO), the leading enterprise AI platform that brings AI Search and Generative AI (GenAI) to every point-of-experience, today announced the launch of its new Relevance-Augmented Passage Retrieval API. The new API empowers organizations to connect their own Large Language Models (LLM) with Coveo's relevant and robust AI retrieval infrastructure to seamlessly and securely ground their GenAI experiences in the entirety of their enterprise content. Leveraging the full power of the Coveo Platform™, it retrieves the most relevant passages from multiple sources of content, securely, and delivers them in the optimal format for LLMs, ensuring the outputs are accurate, secure and firmly anchored in the most current, reliable and relevant knowledge available. As a leader in AI innovation for more than a dozen years, Coveo is now democratizing access to its industry-leading unified index, AI search and relevance capabilities, making it easier for enterprises to build their own GenAI applications with robust, industry-leading retrieval functionality.
Coveo Logo (CNW Group/Coveo Solutions Inc.)
The retrieval challenge in RAG Systems
In Retrieval-Augmented Generation (RAG) systems, enterprises can ground LLMs in their proprietary data and knowledge sources. However, the retrieval process — the "R" in RAG — is notoriously the most challenging aspect. It involves extracting the most relevant and accurate information from vast, fragmented data and content sources across the entire enterprise. This process is vital, as it directly influences the accuracy and security of AI-generated responses across all digital experiences, from websites to commerce, customer service and the workplace.
Strengthen your GenAI applications with Coveo's Leading Retrieval
Coveo's new API is a powerful technology that enables enterprises to elevate their own LLM-powered applications, including, for example, making their various Copilots or other GenAI initiatives more knowledgeable, precise and relevant. It allows developers to seamlessly integrate precise, context-aware answers into their applications without the need to build a full AI search retrieval and relevance system, or the need to migrate data from multiple, siloed applications. By leveraging Coveo's leading unified index and AI Search Relevance technology with this new API, enterprises will be able to overcome common development challenges, including generating relevant answers, ensuring accurate information across all GenAI experiences, minimizing hallucinations, maintaining secure access, respecting content permissions, and accelerating time-to-value.
"Coveo's Relevance-Augmented Passage Retrieval API will play a crucial role in an enterprise's AI and Generative AI architecture, enhancing all digital experiences. It's a game-changer for organizations building intelligent and high-performing large language model (LLM) applications," said Laurent Simoneau, Co-Founder, President, and CTO at Coveo. "Enterprises using this API will benefit from our rapid AI innovation, backed by hundreds of developers and data scientists, and driven by our collaboration with some of the world's largest enterprises in the AI search and generative experiences industry. By using our API for passage retrieval in their RAG systems, companies will be able to save time and resources, reduce risks, and ultimately achieve and surpass their business objectives faster with generative AI."
Over 30 enterprises to date have chosen Coveo's out-of-the-box full Coveo Relevance Generative Answering solution to solve their GenAI needs, and Coveo anticipates that a substantial portion of the market will continue to prefer to buy out-of-the-box. However, for companies that have chosen to invest in their own LLMs, they can now leverage Coveo's Passage Retrieval API to accelerate their GenAI projects. Early adopters of Coveo's out-of-the-box solution such as Xero, F5, SAP Concur, Forcepoint, United Airlines and many others are already reaping the benefits of Coveo's leading GenAI technology.
Join our Passage Retrieval API Early Access Program now
Coveo is offering select enterprises with early access to the Relevance-Augmented Passage Retrieval API, launching mid-September. Participants will collaborate with Coveo's development team, providing feedback to refine the API before its full release in early 2025. Visit Coveo's Early Access Program page to join this exclusive opportunity.
To learn more about these groundbreaking advancements and see them in action, we invite you to join us at our virtual Relevance 360 event on October 3, 2024, or our exclusive in-person Relevance 360 Breakfast during Dreamforce on September 18, 2024, at 7:30am PDT. These events offer a unique opportunity to delve deeper into how Coveo's innovations are shaping the future of AI-driven experiences. Register here to secure your spot.
You can also dive deeper into the new Coveo Relevance-Augmented Passage Retrieval API with Coveo's VP of ML, Sebastien Paquet, over on the Coveo blog.
About Coveo
We strongly believe that the future is business-to-person, that experiences are today's competitive front line, a make or break for every business. We also believe that remarkable experiences not only enhance user satisfaction but also yield significant gains for enterprises. That is what we call the AI-experience advantage – the degree to which the content, products, recommendations, and advice presented to a person online aligns easily with their needs, intent, preferences, context, and behavior, resulting in superior business outcomes.
To realize this AI-experience advantage at scale, enterprises require a robust, spinal and composable infrastructure capable of unifying content securely and delivering AI search, AI recommendations, true personalization, and a trusted generative experience at every touchpoint with each individual customer, partner and employee.
Coveo is dedicated to bringing this advantage to every point-of-experience, using powerful data and AI models to transform the enterprise in commerce, customer service, website and workplace.
The Coveo platform is ISO 27001 and ISO 27018 certified, SOC2 compliant, HIPAA compatible, with a 99.999% SLA available. We are a Salesforce ISV Partner, an SAP® Endorsed App, an Adobe Gold Partner, MACH Alliance member and a Genesys AppFoundry ISV Partner.
Coveo is a trademark of Coveo Solutions Inc.
Forward-Looking Information
This press release contains "forward-looking information" and "forward-looking statements" within the meaning of applicable securities laws (collectively, "forward-looking information"). This forward-looking information is identified by the use of terms and phrases such as "may", "would", "should", "could", "might", "will", "achieve", "occur", "expect", "intend", "estimate", "anticipate", "plan", "foresee", "believe", "continue", "target", "opportunity", "strategy", "scheduled", "outlook", "forecast", "projection", or "prospect", the negative of these terms and similar terminology, including references to assumptions, although not all forward-looking information contains these terms and phrases. In addition, any statements that refer to expectations, intentions, projections, or other characterizations of future events or circumstances contain forward-looking information. Statements containing forward-looking information are not historical facts but instead represent management's expectations, estimates, and projections regarding future events or circumstances.
Forward-looking information is necessarily based on a number of opinions, estimates, and assumptions that we considered appropriate and reasonable as of the date such statements are made. Although the forward-looking information contained herein is based upon what we believe are reasonable assumptions, actual results may vary from the forward-looking information contained herein. Forward-looking information is subject to known and unknown risks, uncertainties, and there are factors, many of which are beyond our control, that may cause the actual results, level of activity, performance, or achievements to be materially different from those expressed or implied by such forward-looking information, including but not limited to macro-economic uncertainties and the risk factors described under "Risk Factors" in the Company's most recently filed Annual Information Form available under our profile on SEDAR at www.sedar.com. There can be no assurance that such forward-looking information will prove to be accurate, as actual results and future events could differ materially from those anticipated in such information. Accordingly, prospective investors should not place undue reliance on forward-looking information, which speaks only as of the date made.
Although we have attempted to identify important risk factors that could cause actual results to differ materially from those contained in forward-looking information, there may be other risk factors not presently known to us or that we presently believe are not material that could also cause actual results or future events to differ materially from those expressed in such forward-looking information. Additional information will be set forth in public filings that we make available under our profile on SEDAR+ at plus.ca from time to time.
The forward-looking information provided in this press release is expressly qualified in their entirety by this cautionary statement.
