{"id":17737,"date":"2025-12-03T15:16:57","date_gmt":"2025-12-03T23:16:57","guid":{"rendered":"https:\/\/www.couchbase.com\/blog\/?p=17737"},"modified":"2025-12-08T10:31:19","modified_gmt":"2025-12-08T18:31:19","slug":"building-multi-agent-ai-workflows-with-couchbase-capella-ai-services","status":"publish","type":"post","link":"https:\/\/www.couchbase.com\/blog\/es\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/","title":{"rendered":"Creaci\u00f3n de flujos de trabajo de IA multiagente con los servicios de IA de Couchbase Capella"},"content":{"rendered":"<h3>A Step-by-Step Guide Using CrewAI and Capella AI Services<\/h3>\n<p><span style=\"font-weight: 400\">In this tutorial, you will learn how to build a sophisticated multi-agent AI system that generates creative content using <\/span><b>Couchbase Capella AI Services<\/b><span style=\"font-weight: 400\"> for storing data, generating embeddings using embedding models and LLM inference. We will create a \u201cSeinfeld Script Generator\u201d that demonstrates:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Multi-agent orchestration with CrewAI<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">RAG (Retrieval Augmented Generation) with Couchbase Query Vector Search<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Couchbase Capella Model Service for hosting the embedding model and LLM<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Couchbase Vectorization Service for vectorizing data stored in Couchbase<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400\">By the end, you will have a working system where multiple specialized AI agents collaborate to generate authentic TV scripts.<\/span><\/p>\n<h3><span style=\"font-weight: 400\">What Are Multi-Agent Workflows?<\/span><\/h3>\n<p><span style=\"font-weight: 400\">Multi-agent workflows involve multiple AI agents working together, each specializing in a specific task \u2014 much like a TV writers\u2019 room.<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-17738\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-9.57.45-AM.png\" alt=\"\" width=\"1076\" height=\"598\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-9.57.45-AM.png 1076w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-9.57.45-AM-300x167.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-9.57.45-AM-1024x569.png 1024w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-9.57.45-AM-768x427.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-9.57.45-AM-18x10.png 18w\" sizes=\"auto, (max-width: 1076px) 100vw, 1076px\" \/><\/p>\n<p><b>Agents and Their Roles<\/b><\/p>\n<table style=\"width: 100%;border-collapse: collapse;margin: 20px 0;font-family: inherit\">\n<tbody>\n<tr style=\"background: #f4f4f4;font-weight: bold\">\n<td style=\"border: 1px solid #ddd;padding: 10px\">Agente<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Papel<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Specialty<\/td>\n<\/tr>\n<tr style=\"background: #fff\">\n<td style=\"border: 1px solid #ddd;padding: 10px\">Theme Analyzer<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Breaks down the theme<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Identifies comedic angles<\/td>\n<\/tr>\n<tr style=\"background: #fafafa\">\n<td style=\"border: 1px solid #ddd;padding: 10px\">Plot Architect<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Designs story structure<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Creates A\/B\/C threads<\/td>\n<\/tr>\n<tr style=\"background: #fff\">\n<td style=\"border: 1px solid #ddd;padding: 10px\">Character Voice Expert<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Ensures authenticity<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Matches character speech<\/td>\n<\/tr>\n<tr style=\"background: #fafafa\">\n<td style=\"border: 1px solid #ddd;padding: 10px\">Dialogue Writer<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Writes scenes<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Dialogue + stage directions<\/td>\n<\/tr>\n<tr style=\"background: #fff\">\n<td style=\"border: 1px solid #ddd;padding: 10px\">Quality Reviewer<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Final editor<\/td>\n<td style=\"border: 1px solid #ddd;padding: 10px\">Ensures consistency<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p>&nbsp;<\/p>\n<h4>Why Couchbase Capella AI Services?<\/h4>\n<p><span style=\"font-weight: 400\">Couchbase Capella AI Services provides:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Unified platform: Database + Vectorization + Search + Models<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Vectorization for document embeddings<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Embeddings API<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">LLM inference<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Vector Search for semantic matching<\/span><\/li>\n<\/ul>\n<h3><span style=\"font-weight: 400\">Setting up Couchbase Capella Services<\/span><\/h3>\n<h4><span style=\"font-weight: 400\">Create a Cluster in Couchbase Capella<\/span><\/h4>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Entrar en <\/span><a href=\"https:\/\/cloud.couchbase.com\"><span style=\"font-weight: 400\">Couchbase Capella<\/span><\/a><span style=\"font-weight: 400\">.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Create a new cluster or use an existing one. Note that the Cluster needs to run the latest version of Couchbase Server (8.0) with the Data, Query, Index and the Eventing services.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Create a bucket (e.g., <\/span><i><span style=\"font-weight: 400\">seinfeld<\/span><\/i><span style=\"font-weight: 400\">)<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Create a scope (e.g., <\/span><i><span style=\"font-weight: 400\">episodes<\/span><\/i><span style=\"font-weight: 400\">) and collection (e.g., <\/span><i><span style=\"font-weight: 400\">guiones<\/span><\/i><span style=\"font-weight: 400\">) for your data<\/span><\/li>\n<\/ol>\n<h4><span style=\"font-weight: 400\">Enable AI Services<\/span><\/h4>\n<ol>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Navigate to Capella&#8217;s AI Services section on the UI.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Deploy the Embeddings and LLM models<\/span>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">You need to launch an embedding &amp; an LLM for this demo in the same region as the Capella cluster where the data will be stored.<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">For this demo to work well, you need to deploy a large language model (LLM) that has tool calling capabilities such as <\/span><i><span style=\"font-weight: 400\">mistralai\/mistral-7b-instruct-v0.3<\/span><\/i><span style=\"font-weight: 400\">. For embeddings, you can choose a model like the <\/span><i><span style=\"font-weight: 400\">nvidia\/llama-3.2-nv-embedqa-1b-v2<\/span><\/i><span style=\"font-weight: 400\">.<\/span><\/li>\n<\/ul>\n<\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Note down the endpoint URL and generate API keys.<\/span><\/li>\n<\/ol>\n<p><span style=\"font-weight: 400\">For more details on launching AI models, you can check the <\/span><a href=\"https:\/\/docs.couchbase.com\/ai\/build\/model-service\/model-service.html\"><span style=\"font-weight: 400\">documentaci\u00f3n oficial<\/span><\/a><span style=\"font-weight: 400\">.<\/span><\/p>\n<p>&nbsp;<\/p>\n<h4><span style=\"font-weight: 400\">Load Your Data<\/span><\/h4>\n<p><span style=\"font-weight: 400\">For this tutorial, we are using the public dataset containing all the dialogues from Seinfeld from <\/span><a href=\"https:\/\/www.kaggle.com\/datasets\/thec03u5\/seinfeld-chronicles\"><span style=\"font-weight: 400\">Kaggle<\/span><\/a><span style=\"font-weight: 400\">. We can import this into our Couchbase Capella cluster using any of the supported <\/span><a href=\"https:\/\/docs.couchbase.com\/cloud\/guides\/load.html\"><span style=\"font-weight: 400\">import modes<\/span><\/a><span style=\"font-weight: 400\"> como <\/span><i><span style=\"font-weight: 400\">cbimport<\/span><\/i><span style=\"font-weight: 400\"> or the UI.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">Your documents should have this structure:<\/span><\/p>\n<pre class=\"lang:default decode:true\">json\r\n{\r\n\"Character\": \"JERRY\",\r\n\"Dialogue\": \"What's the deal with airline peanuts?\",\r\n\"Season\": 3,\r\n\"EpisodeNo\": 15,\r\n}<\/pre>\n<h4><span style=\"font-weight: 400\">Vectorization &amp; Creating Vector Search Index<\/span><\/h4>\n<p><span style=\"font-weight: 400\">We can use the Vectorization Service for structured data to vectorize the dialogues stored in the Couchbase collection.<\/span><\/p>\n<p><span style=\"font-weight: 400\">In this case as our data is already in a structured format inside the Couchbase cluster, we can use the <\/span><a href=\"https:\/\/docs.couchbase.com\/ai\/build\/vectorization-service\/vectorize-structured-data-capella.html\"><span style=\"font-weight: 400\">Vectorize from Structured Data workflow<\/span><\/a><span style=\"font-weight: 400\">.\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">We need to embed the <\/span><i><span style=\"font-weight: 400\">Dialogue<\/span><\/i><span style=\"font-weight: 400\"> field into a new field, <\/span><i><span style=\"font-weight: 400\">dialogue_embedding<\/span><\/i><span style=\"font-weight: 400\">.<\/span><\/p>\n<p><span style=\"font-weight: 400\">During the Vectorization workflow, we can also create the highly performant <\/span><a href=\"https:\/\/docs.couchbase.com\/cloud\/vector-index\/hyperscale-vector-index.html\"><span style=\"font-weight: 400\">Hyperscale Vector Index<\/span><\/a><span style=\"font-weight: 400\"> for vector search with good default values.<\/span><\/p>\n<p><span style=\"font-weight: 400\">After the workflow is completed, we will see an additional field in all the documents containing the <\/span><i><span style=\"font-weight: 400\">dialogue_embedding<\/span><\/i><span style=\"font-weight: 400\"> campo.<\/span><\/p>\n<h3><span style=\"font-weight: 400\">Building the Agent<\/span><\/h3>\n<p><span style=\"font-weight: 400\">We build out multiple agents using <\/span><a href=\"https:\/\/www.crewai.com\/\"><span style=\"font-weight: 400\">CrewAI<\/span><\/a><span style=\"font-weight: 400\"> for orchestrating the agents. Each agent has a dedicated function related to the overall task of generating the script. The agents communicate with each other using the shared context to achieve the overall goal.<\/span><\/p>\n<p><span style=\"font-weight: 400\">The code for the agent can be found in this <\/span><a href=\"https:\/\/github.com\/couchbase-examples\/multi-agent-capella-ai-services\"><span style=\"font-weight: 400\">Github Repository<\/span><\/a><span style=\"font-weight: 400\"> como referencia.<\/span><\/p>\n<h4><span style=\"font-weight: 400\">Key Concepts<\/span><\/h4>\n<h5><span style=\"font-weight: 400\">RAG (Generaci\u00f3n Aumentada de Recuperaci\u00f3n)<\/span><\/h5>\n<p><span style=\"font-weight: 400\">RAG enhances LLM outputs by providing relevant context from a database. In this case, we provide dialogues similar to the user provided input.<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-17739\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.31.18-AM.png\" alt=\"\" width=\"1000\" height=\"904\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.31.18-AM.png 1000w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.31.18-AM-300x271.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.31.18-AM-768x694.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.31.18-AM-13x12.png 13w\" sizes=\"auto, (max-width: 1000px) 100vw, 1000px\" \/><\/p>\n<h5><span style=\"font-weight: 400\">Agent Collaboration<\/span><\/h5>\n<p><span style=\"font-weight: 400\">Agents pass information through task context:<\/span><\/p>\n<p><img loading=\"lazy\" decoding=\"async\" class=\"aligncenter size-full wp-image-17740\" src=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.32.07-AM.png\" alt=\"\" width=\"986\" height=\"748\" srcset=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.32.07-AM.png 986w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.32.07-AM-300x228.png 300w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.32.07-AM-768x583.png 768w, https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/12\/Screenshot-2025-12-03-at-10.32.07-AM-16x12.png 16w\" sizes=\"auto, (max-width: 986px) 100vw, 986px\" \/><\/p>\n<h5><span style=\"font-weight: 400\">Capella AI Model Services Integration<\/span><\/h5>\n<p><span style=\"font-weight: 400\">Couchbase Capella AI Services provides OpenAI-compatible endpoints that are used by the Agents. For embeddings, we are using the LangChain OpenAI package as it is used in association with the <\/span><a href=\"https:\/\/couchbase-ecosystem.github.io\/langchain-couchbase\/\"><span style=\"font-weight: 400\">LangChain Couchbase integration<\/span><\/a><span style=\"font-weight: 400\">. For the LLM, we are using the Capella model through <\/span><a href=\"https:\/\/www.litellm.ai\/\"><span style=\"font-weight: 400\">LiteLLM<\/span><\/a><span style=\"font-weight: 400\"> in CrewAI.<\/span><\/p>\n<pre class=\"lang:python decode:true\">python\r\n\r\n# Embeddings\r\n\r\nfrom langchain_openai import OpenAIEmbeddings\r\n\r\nembeddings = OpenAIEmbeddings(\r\n\u00a0\u00a0\u00a0\u00a0openai_api_key=CAPELLA_EMBEDDING_KEY,\r\n\u00a0\u00a0\u00a0\u00a0openai_api_base=CAPELLA_ENDPOINT,\u00a0\r\n\u00a0\u00a0\u00a0\u00a0model=EMBEDDING_MODEL_NAME,\r\n)\r\n\r\n# LLM\r\n\r\nfrom crewai import LLM\r\n\r\nllm = LLM(\r\n\u00a0\u00a0\u00a0\u00a0model=LLM_NAME,\u00a0\r\n\u00a0\u00a0\u00a0\u00a0api_key=CAPELLA_LLM_KEY,\r\n\u00a0\u00a0\u00a0\u00a0base_url=CAPELLA_ENDPOINT,\r\n)<\/pre>\n<p>&nbsp;<\/p>\n<h3><span style=\"font-weight: 400\">Testing it Out<\/span><\/h3>\n<p><span style=\"font-weight: 400\">Input: <\/span><i><span style=\"font-weight: 400\">Jerry gets a smart speaker that mishears everything<\/span><\/i><\/p>\n<p><span style=\"font-weight: 400\">Salida:\u00a0<\/span><\/p>\n<p><i><span style=\"font-weight: 400\"># Seinfeld Episode: Jerry gets a smart speaker that mishears everything<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**Title:** The Smart Speaker<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Cold Open \u2013 INT. JERRY&#8217;S APARTMENT<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry stands by his new smart speaker on the counter, trying to keep patience.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Play \u201cTake Five\u201d by Dave Brubeck.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**SPEAKER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Ordering five cans of decaf.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry blinks, deadpan.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Well, at least my caffeine addiction\u2019s been acknowledged.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Kramer bursts in, wild-eyed and waving his arms.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**KRAMER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Jerry! You gotta get one of these! It\u2019s the future, buddy!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Elaine enters, arms crossed, scowling.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**ELAINE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">It just called me \u201cHelen.\u201d Helen! Who\u2019s Helen?<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(George frantically calls from next door.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**GEORGE (O.S.):**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Jerry, I think it\u2019s spying on me!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry shrugs.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Great, now the toaster\u2019s taking sides.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(He turns to camera.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">For something called \u201csmart,\u201d this is the dumbest roommate I\u2019ve ever had.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Scene 2 \u2013 INT. JERRY&#8217;S APARTMENT<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry holds his phone, increasingly annoyed. The speaker sits innocently.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Set reminder: buy milk.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**SPEAKER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Playing \u201cDon\u2019t Cry for Me, Argentina.\u201d<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">That\u2019s not a reminder. That\u2019s a musical betrayal.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Elaine storms in, glaring.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**ELAINE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Called me Helen again. Helen! Who\u2019s Helen?<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Maybe it\u2019s trying to give you a new identity.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**ELAINE:** *(sarcastic)*\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Wonderful. A witness protection program via electronics.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Kramer slides in proudly, holding a contraption hooked to the speaker.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**KRAMER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Relax! The Kramer upgrade! Predicts what you want before you know it!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:** *(skeptical)*\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Last time you fixed something, I ended up with a fountain show in my living room.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**KRAMER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Hey, artistry!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Scene 3 \u2013 INT. GEORGE\u2019S OFFICE<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(George paces nervously, whispering on phone.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**GEORGE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">It\u2019s spying, Jerry! I found recordings\u2026 conversations plotting against me!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Plays a garbled clip.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**GEORGE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Proof!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Coworker passes, smirks.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**COWORKER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Talking to your phone again? Chill, George.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**GEORGE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">They want silence! That\u2019s what they want!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Scene 4 \u2013 INT. ELAINE\u2019S OFFICE<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Elaine on video call; speaker mispronounces.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**SPEAKER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Playing \u201cHelen of Troy\u201d audiobook.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**ELAINE:** *(shouting)*\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">No! Not Helen! Elaine!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Coworker offscreen whispers.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**COWORKER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Is her phone possessed or what?<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Scene 5 \u2013 INT. JERRY&#8217;S APARTMENT \u2013 NIGHT<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry\u2019s on a date; suddenly goat noises blare from speaker.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY&#8217;S DATE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">What was that?!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">My smart speaker\u2026 less smart than me.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Elaine hears speaker loudly call out \u201cHelen\u201d nearby, folding arms.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**ELAINE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Helen strikes again.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry and Elaine exchange a look.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Scene 6 \u2013 INT. JERRY&#8217;S APARTMENT<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Kramer unveils modded speaker.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**KRAMER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Trust me! This baby anticipates what you want!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Presses button; speaker erupts with goat bleats, random announcements; lights flicker.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Great. It\u2019s a jazz club haunted house.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Elaine yells at device; George storms in frantic.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**GEORGE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Kramer! You\u2019re involved! This is sabotage!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**KRAMER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">No, just a little chaos for creativity!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Speaker blasts George\u2019s conspiracy tape at full volume.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**GEORGE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">No! Not the tape!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Lights go out; silence.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Finale \u2013 INT. MONK&#8217;S CAF\u00c9<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(The group sits, exhausted.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">For something called \u201csmart,\u201d this is the dumbest roommate I\u2019ve ever had.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**ELAINE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">It still calls me Helen. Helen! I don\u2019t know any Helen!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**GEORGE:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Lost my job, my date. If it listens one more time, I\u2019m moving.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**KRAMER:** *(grinning)*\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">I\u2019m working on the next version. It\u2019s gonna be revolutionary!<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:** *(to camera, dry)*\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Revolutions never go quietly.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">&#8212;<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">### Tag \u2013 INT. JERRY\u2019S APARTMENT \u2013 NIGHT<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry unplugs the speaker, sighs.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**SPEAKER:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">(static) Goodbye, Jerry.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Jerry looks to camera.)*<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">**JERRY:**\u00a0\u00a0<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">Even the dumb ones say goodbye.<\/span><\/i><\/p>\n<p><i><span style=\"font-weight: 400\">*(Fade out.)*<\/span><\/i><\/p>\n<p><span style=\"font-weight: 400\">&#8212;<\/span><\/p>\n<p><span style=\"font-weight: 400\">**Quality Rating:** 9\/10<\/span><\/p>\n<p><span style=\"font-weight: 400\">**Notes:**\u00a0\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">&#8211; Character voices ring true: Jerry\u2019s sardonic, dry wit perfectly captures Seinfeld\u2019s observational humor on tech failings. George\u2019s paranoid neurosis sharply escalates in classic fashion. Elaine\u2019s indignation about mistaken names is on point and amusingly personal. Kramer\u2019s wild enthusiasm undercuts the chaos effectively.\u00a0\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">&#8211; Plot threads interweave cleanly and resolve with escalating miscommunications coming to head in Kramer\u2019s \u201cupgrade\u201d fiasco.\u00a0\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">&#8211; Callbacks (\u201cHelen!\u201d, George\u2019s \u201cIt\u2019s spying!\u201d, Kramer\u2019s \u201crevolutionary\u201d fix) are well-timed and hit naturally.\u00a0\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">&#8211; The humor is observational, grounded in very modern but mundane tech frustrations, avoiding slapstick or overly broad jokes.\u00a0\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">&#8211; Scene pacing is brisk, with normal scene lengths reflecting classic sitcom rhythm; stage directions cue timing and reaction beats to maximize punchlines.\u00a0\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">&#8211; Dialogue incrementally polished for tighter punchlines and clarity, retaining classic Seinfeld rhythm and pacing.\u00a0\u00a0<\/span><\/p>\n<p><span style=\"font-weight: 400\">&#8211; Ending punchline and tag scene effectively mirror Seinfeld\u2019s customary dry closing meta-commentary.<\/span><\/p>\n<p><span style=\"font-weight: 400\">This episode would fit seamlessly into the original series, showcasing each character\u2019s neurotic response to a simple modern annoyance blown hilariously out of proportion.<\/span><\/p>\n<h3><span style=\"font-weight: 400\">Resumen<\/span><\/h3>\n<p><span style=\"font-weight: 400\">In this tutorial, you learned how to:<\/span><\/p>\n<ul>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Build a multi-agent AI system with CrewAI<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Vectorize data using Couchbase Vectorization Workflows<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Use Couchbase Capella AI Services for embeddings and LLM\u00a0\u00a0<\/span><\/li>\n<li style=\"font-weight: 400\"><span style=\"font-weight: 400\">Implement RAG with Couchbase Vector Search (Hyperscale Index)\u00a0<\/span><\/li>\n<\/ul>\n<p><span style=\"font-weight: 400\">The combination of Couchbase&#8217;s unified data platform with CrewAI&#8217;s multi-agent framework creates powerful AI applications that can generate high-quality, contextually-aware content.<\/span><\/p>","protected":false},"excerpt":{"rendered":"<p>A Step-by-Step Guide Using CrewAI and Capella AI Services In this tutorial, you will learn how to build a sophisticated multi-agent AI system that generates creative content using Couchbase Capella AI Services for storing data, generating embeddings using embedding models [&hellip;]<\/p>","protected":false},"author":80878,"featured_media":16988,"comment_status":"open","ping_status":"open","sticky":true,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[10123,10122],"tags":[],"ppma_author":[9543],"class_list":["post-17737","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-agentic-ai-apps","category-artificial-intelligence-ai"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO Premium plugin v26.5 (Yoast SEO v26.5) - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Building Multi-Agent AI Workflows with Couchbase Capella AI Services - The Couchbase Blog<\/title>\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\/es\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/\" \/>\n<meta property=\"og:locale\" content=\"es_MX\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Building Multi-Agent AI Workflows with Couchbase Capella AI Services\" \/>\n<meta property=\"og:description\" content=\"A Step-by-Step Guide Using CrewAI and Capella AI Services In this tutorial, you will learn how to build a sophisticated multi-agent AI system that generates creative content using Couchbase Capella AI Services for storing data, generating embeddings using embedding models [&hellip;]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.couchbase.com\/blog\/es\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/\" \/>\n<meta property=\"og:site_name\" content=\"The Couchbase Blog\" \/>\n<meta property=\"article:published_time\" content=\"2025-12-03T23:16:57+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2025-12-08T18:31:19+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8-1024x536.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=\"Nithish Raghunandanan\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Nithish Raghunandanan\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"8 minutos\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/\"},\"author\":{\"name\":\"nithishr\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/c5a843d75ad78b5b698f59ca6d123af2\"},\"headline\":\"Building Multi-Agent AI Workflows with Couchbase Capella AI Services\",\"datePublished\":\"2025-12-03T23:16:57+00:00\",\"dateModified\":\"2025-12-08T18:31:19+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/\"},\"wordCount\":1522,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png\",\"articleSection\":[\"Agentic AI Applications\",\"Artificial Intelligence (AI)\"],\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/\",\"url\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/\",\"name\":\"Building Multi-Agent AI Workflows with Couchbase Capella AI Services - The Couchbase Blog\",\"isPartOf\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png\",\"datePublished\":\"2025-12-03T23:16:57+00:00\",\"dateModified\":\"2025-12-08T18:31:19+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage\",\"url\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png\",\"contentUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png\",\"width\":2400,\"height\":1256,\"caption\":\"columnar data store overview\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.couchbase.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Building Multi-Agent AI Workflows with Couchbase Capella AI Services\"}]},{\"@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\":\"es\"},{\"@type\":\"Organization\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#organization\",\"name\":\"The Couchbase Blog\",\"url\":\"https:\/\/www.couchbase.com\/blog\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@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\/c5a843d75ad78b5b698f59ca6d123af2\",\"name\":\"nithishr\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/image\/63270a592008f9080fe48b7652fe559f\",\"url\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2022\/03\/image-4.png\",\"contentUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2022\/03\/image-4.png\",\"caption\":\"nithishr\"},\"description\":\"Nithish is an engineer who loves to build products that solve real-world problems in short spans of time. He has experienced different areas of the industry having worked in diverse companies in Germany and India. Apart from work, he likes to travel and interact and engage with the tech community through Meetups &amp; Hackathons. In his free time, he likes to try stuff out by hacking things together.\",\"url\":\"https:\/\/www.couchbase.com\/blog\/es\/author\/nithishr\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Building Multi-Agent AI Workflows with Couchbase Capella AI Services - The Couchbase Blog","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\/es\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/","og_locale":"es_MX","og_type":"article","og_title":"Building Multi-Agent AI Workflows with Couchbase Capella AI Services","og_description":"A Step-by-Step Guide Using CrewAI and Capella AI Services In this tutorial, you will learn how to build a sophisticated multi-agent AI system that generates creative content using Couchbase Capella AI Services for storing data, generating embeddings using embedding models [&hellip;]","og_url":"https:\/\/www.couchbase.com\/blog\/es\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/","og_site_name":"The Couchbase Blog","article_published_time":"2025-12-03T23:16:57+00:00","article_modified_time":"2025-12-08T18:31:19+00:00","og_image":[{"width":1024,"height":536,"url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8-1024x536.png","type":"image\/png"}],"author":"Nithish Raghunandanan","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Nithish Raghunandanan","Est. reading time":"8 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#article","isPartOf":{"@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/"},"author":{"name":"nithishr","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/c5a843d75ad78b5b698f59ca6d123af2"},"headline":"Building Multi-Agent AI Workflows with Couchbase Capella AI Services","datePublished":"2025-12-03T23:16:57+00:00","dateModified":"2025-12-08T18:31:19+00:00","mainEntityOfPage":{"@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/"},"wordCount":1522,"commentCount":0,"publisher":{"@id":"https:\/\/www.couchbase.com\/blog\/#organization"},"image":{"@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage"},"thumbnailUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png","articleSection":["Agentic AI Applications","Artificial Intelligence (AI)"],"inLanguage":"es","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/","url":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/","name":"Building Multi-Agent AI Workflows with Couchbase Capella AI Services - The Couchbase Blog","isPartOf":{"@id":"https:\/\/www.couchbase.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage"},"image":{"@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage"},"thumbnailUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png","datePublished":"2025-12-03T23:16:57+00:00","dateModified":"2025-12-08T18:31:19+00:00","breadcrumb":{"@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/"]}]},{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#primaryimage","url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png","contentUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/03\/blog_header_images_2025-8.png","width":2400,"height":1256,"caption":"columnar data store overview"},{"@type":"BreadcrumbList","@id":"https:\/\/www.couchbase.com\/blog\/building-multi-agent-ai-workflows-with-couchbase-capella-ai-services\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.couchbase.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Building Multi-Agent AI Workflows with Couchbase Capella AI Services"}]},{"@type":"WebSite","@id":"https:\/\/www.couchbase.com\/blog\/#website","url":"https:\/\/www.couchbase.com\/blog\/","name":"El blog de Couchbase","description":"Couchbase, la base de datos NoSQL","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":"es"},{"@type":"Organization","@id":"https:\/\/www.couchbase.com\/blog\/#organization","name":"El blog de Couchbase","url":"https:\/\/www.couchbase.com\/blog\/","logo":{"@type":"ImageObject","inLanguage":"es","@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\/c5a843d75ad78b5b698f59ca6d123af2","name":"nithishr","image":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/image\/63270a592008f9080fe48b7652fe559f","url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2022\/03\/image-4.png","contentUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2022\/03\/image-4.png","caption":"nithishr"},"description":"Nithish es un ingeniero al que le encanta crear productos que resuelvan problemas del mundo real en poco tiempo. Ha trabajado en diferentes \u00e1reas de la industria en diversas empresas de Alemania y la India. Aparte del trabajo, le gusta viajar e interactuar con la comunidad tecnol\u00f3gica a trav\u00e9s de Meetups y Hackathons. En su tiempo libre, le gusta probar cosas hacke\u00e1ndolas.","url":"https:\/\/www.couchbase.com\/blog\/es\/author\/nithishr\/"}]}},"authors":[{"term_id":9543,"user_id":80878,"is_guest":0,"slug":"nithishr","display_name":"Nithish Raghunandanan","avatar_url":{"url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2022\/03\/image-4.png","url2x":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2022\/03\/image-4.png"},"author_category":"","last_name":"Raghunandanan","first_name":"Nithish","job_title":"","user_url":"","description":"Nithish es un ingeniero al que le encanta crear productos que resuelvan problemas del mundo real en poco tiempo. Ha trabajado en diferentes \u00e1reas de la industria en diversas empresas de Alemania y la India. Aparte del trabajo, le gusta viajar e interactuar con la comunidad tecnol\u00f3gica a trav\u00e9s de Meetups y Hackathons. En su tiempo libre, le gusta probar cosas hacke\u00e1ndolas."}],"_links":{"self":[{"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/posts\/17737","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/users\/80878"}],"replies":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/comments?post=17737"}],"version-history":[{"count":0,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/posts\/17737\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/media\/16988"}],"wp:attachment":[{"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/media?parent=17737"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/categories?post=17737"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/tags?post=17737"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/ppma_author?post=17737"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}