{"id":16590,"date":"2024-12-02T05:45:09","date_gmt":"2024-12-02T13:45:09","guid":{"rendered":"https:\/\/www.couchbase.com\/blog\/?p=16590"},"modified":"2025-06-13T16:39:42","modified_gmt":"2025-06-13T23:39:42","slug":"ai-services-expedite-agent-development","status":"publish","type":"post","link":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/","title":{"rendered":"Couchbase Introduces Capella AI Services to Expedite Agent Development"},"content":{"rendered":"<p><span style=\"font-weight: 400;\">TLDR: Couchbase announces new AI Services in the Capella developer data platform to efficiently and effectively create and operate <\/span><b>GenAI-powered agents<\/b><span style=\"font-weight: 400;\">. These services include the <\/span><b>Model Service<\/b><span style=\"font-weight: 400;\"> for private and secure hosting of open source LLMs, the <\/span><b>Unstructured Data Service<\/b><span style=\"font-weight: 400;\"> for processing PDFs and images for ingestion, the <\/span><b>Vectorization Service<\/b><span style=\"font-weight: 400;\"> for real-time streaming, storage and indexing of vector embeddings, an <\/span><b>Agent Catalog<\/b><span style=\"font-weight: 400;\"> providing an extensible framework to help developers add new capabilities to the agent stack, and <\/span><b>AI Functions<\/b><span style=\"font-weight: 400;\"> to\u00a0 enrich data using the power of LLMs, collect key data artifacts generated by agents, and establish guardrails for evolving operations as LLMs and agents develop.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">Introducing Capella AI Services<\/span><\/h2>\n<p><a href=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image-2.png\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-large wp-image-16623\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image-2-1024x534.png\" alt=\"\" width=\"900\" height=\"469\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image-2-1024x534.png 1024w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image-2-300x157.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image-2-768x401.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image-2.png 1267w\" sizes=\"auto, (max-width: 900px) 100vw, 900px\" \/><\/a><\/p>\n<p><span style=\"font-weight: 400;\">Couchbase is excited to announce a series of new AI Services that will enhance the <\/span><a href=\"https:\/\/cloud.couchbase.com\/?ref=blog\"><span style=\"font-weight: 400;\">Capella platform<\/span><\/a><span style=\"font-weight: 400;\"> to assist developers in creating and deploying <\/span><a href=\"https:\/\/www.couchbase.com\/blog\/supercharge-genai-apps-with-couchbase\/\"><span style=\"font-weight: 400;\">GenAI-powered<\/span><\/a><span style=\"font-weight: 400;\"> agents and <strong>agentic applications<\/strong>. Agents are autonomous programs designed to use natural language interactions to perform tasks or solve problems by making decisions based on data, conversational exchanges with large language models, and environmental context\u2014all without human involvement.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Agents will not only process textual inputs but also incorporate visual and audio information in executing their tasks. Capella&#8217;s AI Services will help developers with many of the data processing steps required when using retrieval-augmented generation (RAG) techniques, and leverage the myriad tools and frameworks within the RAG ecosystem to interact effectively with large language models. Additionally, these services will support architects and DevOps teams in managing the operation of agents over time.<\/span><\/p>\n<p><a href=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3.png\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-large wp-image-16624\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3-1024x505.png\" alt=\"\" width=\"900\" height=\"444\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3-1024x505.png 1024w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3-300x148.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3-768x379.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3-1536x758.png 1536w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3-1320x651.png 1320w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/image1-3.png 1603w\" sizes=\"auto, (max-width: 900px) 100vw, 900px\" \/><\/a><\/p>\n<h2><span style=\"font-weight: 400;\">Capella&#8217;s new AI Services<\/span><\/h2>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Model Service<\/b><span style=\"font-weight: 400;\">: External, local, and embedded language model hosting to minimize processing latencies by moving models closer to the data and their consumption. This approach helps address data privacy, consistency, and sharing risks by ensuring data never leaves the customer&#8217;s VPC. Capella will host models from Mistral and Llama3.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Vectorization Service:<\/b><span style=\"font-weight: 400;\"> For creating, streaming, storing, and searching vector embeddings to enhance conversation quality and accuracy, and facilitate ongoing interaction contexts as LLMs evolve and may lose context.\u00a0\u00a0<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Unstructured Data Service:<\/b><span style=\"font-weight: 400;\"> Transforms unstructured data such as text documents, PDFs, and media types like images and recordings into \u201cchunks\u201d of readable semantic information (e.g., sentences and paragraphs) for generating usable vectors. This pre-processing step broadens the range of use cases agents can support.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>Agent Catalog:<\/b><span style=\"font-weight: 400;\"> Accelerates agentic application development with a centralized repository for tools, metadata, prompts, and audit information to manage LLM flow, traceability, and governance. It also automates discovery of relevant agent tools to answer user questions and enforces guardrails for consistent agent exchanges over time.<\/span><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><b>AI Functions: <\/b><span style=\"font-weight: 400;\">Boost developer productivity by integrating AI-driven data analysis directly into application workflows using familiar SQL++ syntax. This accelerates developer productivity by eliminating the need for external tooling, custom coding, and model management. Capella AI Functions include summarization, classification, sentiment analysis, and data masking.\u00a0<\/span><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><span style=\"font-weight: 400;\">Through its unified developer data platform, Couchbase empowers customers to deliver their most critical applications in this new AI-driven landscape, offering a persistent, stateful data supply for AI interactions, agent application functionality, and the ongoing development and maintenance of these systems.<\/span><\/p>\n<h2><span style=\"font-weight: 400;\">Why do we need AI Services?<\/span><\/h2>\n<p><span style=\"font-weight: 400;\">Agentic application development and operation will introduce many new data-centric challenges. These include:<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Working with GenAI fundamentally changes developers&#8217; everyday workflows<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">While the <\/span><a href=\"https:\/\/www.couchbase.com\/blog\/what-is-an-ai-agent\/\"><span style=\"font-weight: 400;\">concept of Agents<\/span><\/a><span style=\"font-weight: 400;\"> is straightforward\u2013creating task-based programs that independently figure things out, such as making reservations on your behalf\u2013developing Agents requires new techniques beyond RAG to ensure reliable, trustworthy behavior. This involves maintaining consistent behavior within each Agent and every LLM exchange for ongoing Agent invocations over time. Instead of simply designing database-powered applications, developers will need to incorporate agentic interactions between both databases and application functionality. Our new AI Services will help developers take advantage of these new workflows and become proficient in using LLMs in their development.<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Everyone must learn new technologies and operational techniques<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Building AI-powered functionality introduces new development workflows, integrations, and processes into today\u2019s software development lifecycle. AI interactions will become programmatic, and new types of data, such as vectors, will be both generated and consumed during these exchanges. The new AI Services introduced in Couchbase Capella will help developers and architects address these new processes, including automating <\/span><a href=\"https:\/\/www.couchbase.com\/blog\/an-overview-of-retrieval-augmented-generation\/\"><span style=\"font-weight: 400;\">RAG (Retrieval Augmented Generation)<\/span><\/a><span style=\"font-weight: 400;\">, prompt construction, guardrails for prompts and responses, and response tracking, agent observability, and validation for LLM accuracy.\u00a0 Capella&#8217;s AI services will help DevOps make sure that agents are doing what we expected and not creating surprises.<\/span><\/p>\n<div id=\"attachment_16622\" style=\"width: 910px\" class=\"wp-caption aligncenter\"><a href=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard.png\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-16622\" class=\"wp-image-16622 size-large\" style=\"border: 1px solid black;\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard-1024x576.png\" alt=\"\" width=\"900\" height=\"506\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard-1024x576.png 1024w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard-300x169.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard-768x432.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard-1536x864.png 1536w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard-1320x743.png 1320w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Capella-AI-Services-Dashboard.png 1920w\" sizes=\"auto, (max-width: 900px) 100vw, 900px\" \/><\/a><p id=\"caption-attachment-16622\" class=\"wp-caption-text\">Capella AI Services web-based management interface<\/p><\/div>\n<h3><span style=\"font-weight: 400;\">Offering proprietary data to private models<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">According to our conversations with customers, the scariest thing about GenAI is sharing data that shouldn&#8217;t be shared publicly. But in many cases proprietary company data is required to make sure the LLM\u2019s knowledge is as accurate and contextual as possible. This may require teaching the model with proprietary and sensitive business data that cannot be divulged publicly. To meet this requirement, LLMs must be privatized or hosted privately and not exposed to the public. To address this need, Capella will host language models privately on behalf of customers.<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Intensive conversations with LLMs<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Vector Search and chatbot assistants are just the early applications of GenAI. They represent single interactions with one language model. What we will see in the near future is the evolution of RAG to encompass an explosion of multiple exchanges with LLMs, similar to a crowd of back and forth conversations. We will also see Agents working in concert as an ensemble, conversing with multiple models across multiple, ongoing conversations to complete larger, more complex tasks. When we first learned about RAG, it was presented as a single-path workflow with many steps. In reality, agent workflows will be recursive and much more complex.<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Reducing latency to improve user experiences<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Latency is the enemy of AI. It is especially intolerable when real people are involved. As we mentioned earlier, we expect to reduce latency by hosting models alongside their data supply. Similar to Netflix, we believe that content should be processed close to where it is consumed\u2013on mobile devices for users. A major advantage of Capella is that it offers a local data store, Couchbase Lite, to process LLM exchanges directly on devices. This will help keep users happy because they won&#8217;t have to exclusively wait for cloud-hosted LLMs to respond.<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Preprocessing unstructured data prior to vectorization<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Incorporating both structured and unstructured data within the RAG process is essential.\u00a0 Unstructured data, such as PDF files, is not immediately ready for consumption by an LLM.\u00a0 This data must be parsed, broken into logical chunks, and transformed into simple text or JSON before it can be fed into an embedding model or an LLM\u2019s knowledge base. This is often referred to as \u201cPreprocessing and Chunking,\u201d or preparing unstructured data for inclusion in the RAG processes of an Agent. Capella will offer an unstructured data service for preparing objects like PDFs to be used as sources for vector embeddings and their indexing. During this process, we extract important metadata, chunk and vectorize the data based on its semantic content, and generate high-quality vector embeddings for AI insights.<\/span><\/p>\n<div id=\"attachment_16621\" style=\"width: 910px\" class=\"wp-caption aligncenter\"><a href=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service.png\"><img loading=\"lazy\" decoding=\"async\" aria-describedby=\"caption-attachment-16621\" class=\"wp-image-16621 size-large\" style=\"border: 1px solid black;\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service-1024x576.png\" alt=\"\" width=\"900\" height=\"506\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service-1024x576.png 1024w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service-300x169.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service-768x432.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service-1536x864.png 1536w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service-1320x743.png 1320w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Unstuctured-Data-Service.png 1920w\" sizes=\"auto, (max-width: 900px) 100vw, 900px\" \/><\/a><p id=\"caption-attachment-16621\" class=\"wp-caption-text\">Web-based workflow for managing unstructured data via AI Services<\/p><\/div>\n<h3><span style=\"font-weight: 400;\">Vectorization: creation and streaming of vectors in real-time<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Once processed, this unstructured data, plus regular operational and semi-structured data, can be fed into an embedding model for creating vector indices (vectors) that serve as contextual guideposts within a prompt to an LLM. The process of creating vectors as a streamed service enables real-time context setting and vector creation as the agent runs. The quantity of vector dimensions and embeddings could be immense, potentially reaching the billions. This volume will pose challenges for existing data platforms that are unprepared or under-designed to handle such scale.\u00a0\u00a0<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Specialization will drive the need for many models and many agents<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Developers will need to track the programs that interact with AI models, because models will evolve over time. To keep their knowledge up to date, language models will need to become smaller so they can shrink their learning cycles. As models specialize, they will also become more focused on specific topics or contexts, such as a model that predicts weather patterns, evaluates medical test results, or understands specific laws of physics. Similarly, agents will also become specialized in their functionality. This will create the need for a catalog index that maintains different agents and their interactions with specialized models.\u00a0\u00a0<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Maintaining persistent context over time<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Long-running agents will need data persistence to ensure the outcomes or outputs from the agent remain consistent and as expected over time. This is challenging because large language models do not maintain context from one conversation to the next. They need to be re-informed of their context from session to session, which requires conversations to be preserved.<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">LLM knowledge changes over time, and agents need guardrails<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Further complicating the data preservation problem is the fact that the knowledge in an LLM is dynamic and growing, which means that the model may not provide the same answer to a prompt from one moment to the next. Therefore, developers must incorporate reliability verification routines to check the expected outcomes and consistency of LLM exchanges over time. This means that yesterday\u2019s LLM conversation must be preserved and persisted so that it can be used as validation data for today\u2019s LLM interaction. What this means is that Agent interactions with LLMs\u2014along with their inputs, response outputs, and contextual metadata\u2014 must be preserved for each conversion to further accuracy validation. This will generate a lot of data that needs to be stored in an <\/span><a href=\"https:\/\/www.couchbase.com\/products\/vector-search\/\"><span style=\"font-weight: 400;\">AI-ready database like Couchbase<\/span><\/a><span style=\"font-weight: 400;\">.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Building an agent involves selecting an LLM for reasoning and function calling, managing tools and data, maintaining prompts, optimizing with caching, and iterating for quality. The <\/span><b>Couchbase Agent Catalog<\/b><span style=\"font-weight: 400;\"> seamlessly integrates with the Capella Developer Platform to streamline this process, reducing cognitive load for developers. Our multi-agent catalog helps developers manage tools, datasets, templates, ground truth, and prompts across agents. It supports semantic tool selection for queries, provides prebuilt tools, and offers best-in-class model-serving infrastructure for hosting LLMs. Additional features include guardrail enforcement, hallucination detection, query lineage auditing, forecasting, and RAG-as-a-Service (RAGaaS) integration for agent quality assessment.<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Minimizing the costs of LLM conversations\u00a0<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Conversations with LLMs will be expensive and slow. Agents will engage in multitudes of conversations with LLMs, which make this a significant challenge. This is why each CSP is excited about the models they support (Bedrock\/Claude, Gemini, ChatGPT) as future revenue generators. With Agent performance, milliseconds cost money. Couchbase will leverage multiple performance advantages already built into Capella to make LLM interactions faster and more cost effective. These include the ability to cache common queries for prompts, minimizing redundant hits to an LLM, and offering semantic and conversational caching of LLM results for common answers. Capella also provides performance-tuning features such as multidimensional scaling and cross-datacenter replication. We expect that Capella will offer a compelling price\/performance advantage to customers.<\/span><\/p>\n<p><span style=\"font-weight: 400;\">Diving further into the challenges and opportunities, Stephen O\u2019Grady, principal analyst at RedMonk, said: \u201cAs AI continues to transform the enterprise, it\u2019s posing significant new challenges for infrastructure. In order to apply AI to their existing businesses, enterprises have been required to integrate large and disparate data sources and an array of rapidly evolving AI models using complicated workflows. This has created demand for an alternative, multi-modal data platform with access to not just the necessary training data but the models to apply to it. This is the opportunity Couchbase\u2019s new Capella AI Services were built for.\u201d<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">Conclusion: Welcome to our AI world!<\/span><\/h3>\n<p><span style=\"font-weight: 400;\">Couchbase is expanding its developer data platform to include an array of AI services to support both the creation and operation of <\/span><a href=\"https:\/\/www.couchbase.com\/blog\/agentic-ai\/\"><b>agentic applications<\/b><\/a><span style=\"font-weight: 400;\">. These services address multiple pressing needs for data persistence and organization when agents are running, and simplify many of the early-stage headaches developers face when creating them. These services will be offered to customers and qualified prospects as a private preview. We are extremely excited about what we are introducing to support critical applications in this new AI world. Come join the ride!<\/span><\/p>\n<h3><span style=\"font-weight: 400;\">For more information<\/span><\/h3>\n<ul>\n<li style=\"list-style-type: none;\">\n<ul>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><a href=\"https:\/\/www.couchbase.com\/press-releases\/couchbase-introduces-capella-ai-services-to-streamline-development-of-agentic-ai-applications\/\"><span style=\"font-weight: 400;\">Read the Press Release<\/span><\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Check out <\/span><a href=\"https:\/\/www.couchbase.com\/products\/ai-services\/\"><span style=\"font-weight: 400;\">Capella AI Services<\/span><\/a><span style=\"font-weight: 400;\"> or Sign up for the <\/span><a href=\"https:\/\/info.couchbase.com\/capella-ai-services-signup\"><span style=\"font-weight: 400;\">Private Preview<\/span><\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Blog: <\/span><a href=\"https:\/\/www.couchbase.com\/blog\/an-overview-of-retrieval-augmented-generation\/\"><span style=\"font-weight: 400;\">What is RAG?<\/span><\/a><\/li>\n<li style=\"font-weight: 400;\" aria-level=\"1\"><span style=\"font-weight: 400;\">Blog: <\/span><a href=\"https:\/\/www.couchbase.com\/blog\/what-is-an-ai-agent\/\"><span style=\"font-weight: 400;\">What is an AI Agents?<\/span><\/a><\/li>\n<li><span style=\"font-weight: 400;\">Register for the webcast: <\/span><a href=\"https:\/\/info.couchbase.com\/a-roadmap-for-the-new-age-of-ai-agents-2025january\"><span style=\"font-weight: 400;\">A Roadmap for the New Age of AI Agents \u2013 Challenges and Opportunities<\/span><\/a><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p><a href=\"https:\/\/info.couchbase.com\/capella-ai-services-signup\"><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter wp-image-16625\" style=\"border: 1px solid black;\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Screenshot-2024-11-28-at-12.36.24\u202fAM-1024x828.png\" alt=\"\" width=\"450\" height=\"364\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Screenshot-2024-11-28-at-12.36.24\u202fAM-1024x828.png 1024w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Screenshot-2024-11-28-at-12.36.24\u202fAM-300x243.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Screenshot-2024-11-28-at-12.36.24\u202fAM-768x621.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Screenshot-2024-11-28-at-12.36.24\u202fAM-1536x1242.png 1536w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Screenshot-2024-11-28-at-12.36.24\u202fAM-2048x1657.png 2048w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/11\/Screenshot-2024-11-28-at-12.36.24\u202fAM-1320x1068.png 1320w\" sizes=\"auto, (max-width: 450px) 100vw, 450px\" \/><\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>TLDR: Couchbase announces new AI Services in the Capella developer data platform to efficiently and effectively create and operate GenAI-powered agents. These services include the Model Service for private and secure hosting of open source LLMs, the Unstructured Data Service [&hellip;]<\/p>\n","protected":false},"author":62223,"featured_media":16629,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[10123,10122,3917,2225,1816,9973,9937],"tags":[9974,9870],"ppma_author":[8966],"class_list":["post-16590","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-agentic-ai-apps","category-artificial-intelligence-ai","category-company","category-cloud","category-couchbase-server","category-generative-ai-genai","category-vector-search","tag-genai","tag-llms"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v25.7.1 (Yoast SEO v25.7) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Couchbase Introduces Capella AI Services to Expedite Agent Development - The Couchbase Blog<\/title>\n<meta name=\"description\" content=\"Couchbase unveils AI Services in Capella to streamline GenAI agent development with model hosting, data processing, and real-time vectorization.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Couchbase Introduces Capella AI Services to Expedite Agent Development\" \/>\n<meta property=\"og:description\" content=\"Couchbase unveils AI Services in Capella to streamline GenAI agent development with model hosting, data processing, and real-time vectorization.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/\" \/>\n<meta property=\"og:site_name\" content=\"The Couchbase Blog\" \/>\n<meta property=\"article:published_time\" content=\"2024-12-02T13:45:09+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-06-13T23:39:42+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services-1024x536.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"536\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Jeff Morris, VP Product Marketing\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@JeffMMorris\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Jeff Morris, VP Product Marketing\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"11 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/\"},\"author\":{\"name\":\"Jeff Morris, VP Product Marketing\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/d64e614a24acc9ed36e77607fc2fb647\"},\"headline\":\"Couchbase Introduces Capella AI Services to Expedite Agent Development\",\"datePublished\":\"2024-12-02T13:45:09+00:00\",\"dateModified\":\"2025-06-13T23:39:42+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/\"},\"wordCount\":2074,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png\",\"keywords\":[\"GenAI\",\"LLMs\"],\"articleSection\":[\"Agentic AI Applications\",\"Artificial Intelligence (AI)\",\"Company\",\"Couchbase Capella\",\"Couchbase Server\",\"Generative AI (GenAI)\",\"Vector Search\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/\",\"url\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/\",\"name\":\"Couchbase Introduces Capella AI Services to Expedite Agent Development - The Couchbase Blog\",\"isPartOf\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png\",\"datePublished\":\"2024-12-02T13:45:09+00:00\",\"dateModified\":\"2025-06-13T23:39:42+00:00\",\"description\":\"Couchbase unveils AI Services in Capella to streamline GenAI agent development with model hosting, data processing, and real-time vectorization.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage\",\"url\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png\",\"contentUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png\",\"width\":2400,\"height\":1256},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.couchbase.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Couchbase Introduces Capella AI Services to Expedite Agent Development\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#website\",\"url\":\"https:\/\/www.couchbase.com\/blog\/\",\"name\":\"The Couchbase Blog\",\"description\":\"Couchbase, the NoSQL Database\",\"publisher\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.couchbase.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#organization\",\"name\":\"The Couchbase Blog\",\"url\":\"https:\/\/www.couchbase.com\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/logo\/image\/\",\"url\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/2023\/04\/admin-logo.png\",\"contentUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/2023\/04\/admin-logo.png\",\"width\":218,\"height\":34,\"caption\":\"The Couchbase Blog\"},\"image\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/logo\/image\/\"}},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/d64e614a24acc9ed36e77607fc2fb647\",\"name\":\"Jeff Morris, VP Product Marketing\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/image\/d30352f9b7e0c9862c1707074f15bcd0\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/8c718e94092d1dde50a7ed8a265dcb948a7d005dd850bfd0daefe013cbe388a6?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/8c718e94092d1dde50a7ed8a265dcb948a7d005dd850bfd0daefe013cbe388a6?s=96&d=mm&r=g\",\"caption\":\"Jeff Morris, VP Product Marketing\"},\"description\":\"Jeff Morris is VP of Product, Solutions and Customer Marketing at Couchbase. He's spent over three decades marketing software development tools, databases, analytic tools and other open source products. Needless to say, he's a big believer in Couchbase Capella because it is as easy as SQL, versatile for many use cases and blazingly fast, which delivers exceptionally low TCO.\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/jeffmorris3\/\",\"https:\/\/x.com\/JeffMMorris\"],\"url\":\"https:\/\/www.couchbase.com\/blog\/author\/jmorris\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Couchbase Introduces Capella AI Services to Expedite Agent Development - The Couchbase Blog","description":"Couchbase unveils AI Services in Capella to streamline GenAI agent development with model hosting, data processing, and real-time vectorization.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/","og_locale":"en_US","og_type":"article","og_title":"Couchbase Introduces Capella AI Services to Expedite Agent Development","og_description":"Couchbase unveils AI Services in Capella to streamline GenAI agent development with model hosting, data processing, and real-time vectorization.","og_url":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/","og_site_name":"The Couchbase Blog","article_published_time":"2024-12-02T13:45:09+00:00","article_modified_time":"2025-06-13T23:39:42+00:00","og_image":[{"width":1024,"height":536,"url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services-1024x536.png","type":"image\/png"}],"author":"Jeff Morris, VP Product Marketing","twitter_card":"summary_large_image","twitter_creator":"@JeffMMorris","twitter_misc":{"Written by":"Jeff Morris, VP Product Marketing","Est. reading time":"11 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#article","isPartOf":{"@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/"},"author":{"name":"Jeff Morris, VP Product Marketing","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/d64e614a24acc9ed36e77607fc2fb647"},"headline":"Couchbase Introduces Capella AI Services to Expedite Agent Development","datePublished":"2024-12-02T13:45:09+00:00","dateModified":"2025-06-13T23:39:42+00:00","mainEntityOfPage":{"@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/"},"wordCount":2074,"commentCount":0,"publisher":{"@id":"https:\/\/www.couchbase.com\/blog\/#organization"},"image":{"@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage"},"thumbnailUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png","keywords":["GenAI","LLMs"],"articleSection":["Agentic AI Applications","Artificial Intelligence (AI)","Company","Couchbase Capella","Couchbase Server","Generative AI (GenAI)","Vector Search"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/","url":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/","name":"Couchbase Introduces Capella AI Services to Expedite Agent Development - The Couchbase Blog","isPartOf":{"@id":"https:\/\/www.couchbase.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage"},"image":{"@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage"},"thumbnailUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png","datePublished":"2024-12-02T13:45:09+00:00","dateModified":"2025-06-13T23:39:42+00:00","description":"Couchbase unveils AI Services in Capella to streamline GenAI agent development with model hosting, data processing, and real-time vectorization.","breadcrumb":{"@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#primaryimage","url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png","contentUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2024\/12\/blog-ai-services.png","width":2400,"height":1256},{"@type":"BreadcrumbList","@id":"https:\/\/www.couchbase.com\/blog\/ai-services-expedite-agent-development\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.couchbase.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Couchbase Introduces Capella AI Services to Expedite Agent Development"}]},{"@type":"WebSite","@id":"https:\/\/www.couchbase.com\/blog\/#website","url":"https:\/\/www.couchbase.com\/blog\/","name":"The Couchbase Blog","description":"Couchbase, the NoSQL Database","publisher":{"@id":"https:\/\/www.couchbase.com\/blog\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.couchbase.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/www.couchbase.com\/blog\/#organization","name":"The Couchbase Blog","url":"https:\/\/www.couchbase.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/logo\/image\/","url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/2023\/04\/admin-logo.png","contentUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/2023\/04\/admin-logo.png","width":218,"height":34,"caption":"The Couchbase Blog"},"image":{"@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/logo\/image\/"}},{"@type":"Person","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/d64e614a24acc9ed36e77607fc2fb647","name":"Jeff Morris, VP Product Marketing","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/image\/d30352f9b7e0c9862c1707074f15bcd0","url":"https:\/\/secure.gravatar.com\/avatar\/8c718e94092d1dde50a7ed8a265dcb948a7d005dd850bfd0daefe013cbe388a6?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/8c718e94092d1dde50a7ed8a265dcb948a7d005dd850bfd0daefe013cbe388a6?s=96&d=mm&r=g","caption":"Jeff Morris, VP Product Marketing"},"description":"Jeff Morris is VP of Product, Solutions and Customer Marketing at Couchbase. He's spent over three decades marketing software development tools, databases, analytic tools and other open source products. Needless to say, he's a big believer in Couchbase Capella because it is as easy as SQL, versatile for many use cases and blazingly fast, which delivers exceptionally low TCO.","sameAs":["https:\/\/www.linkedin.com\/in\/jeffmorris3\/","https:\/\/x.com\/JeffMMorris"],"url":"https:\/\/www.couchbase.com\/blog\/author\/jmorris\/"}]}},"authors":[{"term_id":8966,"user_id":62223,"is_guest":0,"slug":"jmorris","display_name":"Jeff Morris, VP Product Marketing","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/8c718e94092d1dde50a7ed8a265dcb948a7d005dd850bfd0daefe013cbe388a6?s=96&d=mm&r=g","author_category":"","last_name":"Morris, VP Product Marketing","first_name":"Jeff","job_title":"","user_url":"","description":"Jeff Morris is VP of Product and Solutions Marketing at Couchbase. He's spent over three decades marketing software development tools, databases, analytic tools, cloud services, and other open source products. He'd be the first to tell you that anyone looking for a fast, flexible, familiar, and affordable cloud-to-edge database-as-a-service can stop looking after they check out Couchbase. "}],"_links":{"self":[{"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/posts\/16590","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/users\/62223"}],"replies":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/comments?post=16590"}],"version-history":[{"count":0,"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/posts\/16590\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/media\/16629"}],"wp:attachment":[{"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/media?parent=16590"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/categories?post=16590"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/tags?post=16590"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/wp-json\/wp\/v2\/ppma_author?post=16590"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}