The returned vector will be appended back into the same document.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\nThe result? Your bucket now holds PCAP sessions + their semantic fingerprint<\/b>, ready to be indexed.<\/p>\n
Here\u2019s the updated Eventing handler:<\/p>\n
function OnUpdate(doc, meta) {\r\n\u00a0\u00a0log(\"Eventing function started for doc id:\", meta.id);\r\n\u00a0\u00a0try {\r\n\r\n\u00a0\u00a0\u00a0\u00a0if (doc.type !== \"pcap_session\") {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0log(\"Skipping doc: type is\", doc.type);\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0return;\r\n\u00a0\u00a0\u00a0\u00a0}\r\n\r\n\u00a0\u00a0\u00a0\u00a0var OPENAI_KEY = \"YZX\";\u00a0 \/\/ <-- your OpenAI key\r\n\r\n\u00a0\u00a0\u00a0\u00a0\/\/ 1) Build enriched input text for embedding\r\n\u00a0\u00a0\u00a0\u00a0\/\/ Combine free-text + structured context so embeddings capture richer semantics\r\n\u00a0\u00a0\u00a0\u00a0var text = doc.summaryText || \"\";\r\n\u00a0\u00a0\u00a0\u00a0text += \" Proto:\" + (doc.proto || \"\");\r\n\u00a0\u00a0\u00a0\u00a0text += \" LossPct:\" + (doc.lossPct || 0);\r\n\u00a0\u00a0\u00a0\u00a0text += \" JitterMs:\" + (doc.jitterMs || 0);\r\n\u00a0\u00a0\u00a0\u00a0text += \" Retransmits:\" + (doc.retransmits || 0);\r\n\u00a0\u00a0\u00a0\u00a0text += \" Region:\" + (doc.region || \"\");\r\n\u00a0\u00a0\u00a0\u00a0text += \" Carrier:\" + (doc.carrier || \"\");\r\n\r\n\u00a0\u00a0\u00a0\u00a0log(\"Emritched text before embedding is: \" + text);\r\n\r\n\u00a0\u00a0\u00a0\u00a0\/\/ 2) Call OpenAI Embeddings API\r\n\u00a0\u00a0\u00a0\u00a0var request = {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0headers: {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"Authorization\": \"Bearer \" + OPENAI_KEY,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"Content-Type\": \"application\/json\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0body: JSON.stringify({\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"input\": text,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"model\": EMBEDDING_MODEL\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0})\r\n\u00a0\u00a0\u00a0\u00a0};\r\n\r\n\u00a0\u00a0\u00a0\u00a0try {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0var response = curl(\"POST\", EMBEDDING_API, request);\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0var body = response.body;\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0log(\"Response body parsed\");\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0if (typeof body === \"string\") {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0var result = JSON.parse(body);\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0} else if (typeof body === \"object\") {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\/\/ If already parsed, just assign\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0var result = body;\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0} else {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0log(\"Unexpected response.body type:\", typeof body);\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\/\/ Extract the embedding vector from first data element\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0if (result && result.data && result.data.length > 0 && result.data[0].embedding) {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0var embeddingVector = result.data[0].embedding;\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0log(\"Embedding vector length:\", embeddingVector.length);\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\/\/ 3) Write back embedding + quality heuristic\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0doc.embedding_vector = embeddingVector;\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0doc.embedding_model = EMBEDDING_MODEL;\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0doc.qualityLabel = (doc.lossPct > 0.5 || doc.jitterMs > 30 || doc.retransmits > 10)\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0? \"degraded\" : \"healthy\";\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\/\/ Update destination collection\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0dst[meta.id] = doc;\r\n\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0} else {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0log(\"Embedding not found in response:\", JSON.stringify(result));\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\r\n\u00a0\u00a0\u00a0\u00a0} catch (e) {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0log(\"Curl threw exception:\", e);\r\n\u00a0\u00a0\u00a0\u00a0}\r\n\r\n\u00a0\u00a0\u00a0\u00a0\/\/ 4) Raise anomaly alert if degraded\r\n\u00a0\u00a0\u00a0\u00a0if (doc.qualityLabel === \"degraded\") {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0var alertDoc = {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0type: \"pcap_alert\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0sessionId: doc.sessionId,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0ts: new Date().toISOString(),\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0reason: \"Heuristic threshold exceeded\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0lossPct: doc.lossPct,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0jitterMs: doc.jitterMs,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0retransmits: doc.retransmits,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0region: doc.region,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0carrier: doc.carrier\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0};\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0var alertKey = \"alert::\" + doc.sessionId;\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0alerts[alertKey] = alertDoc;\r\n\u00a0\u00a0\u00a0\u00a0}\r\n\r\n\u00a0\u00a0\u00a0\u00a0log(\"Document enriched with embedding + quality label:\", meta.id);\r\n\r\n\u00a0\u00a0} catch (e) {\r\n\u00a0\u00a0\u00a0\u00a0log(\" Eventing exception\", e);\r\n\u00a0\u00a0}\r\n}\r\n\r\nfunction OnDelete(meta, options) {\r\n\u00a0\u00a0\/\/ No-op for deletes\r\n}<\/pre>\nEvery new PCAP session summary now self-enriches<\/b> in real time.<\/p>\n![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image5-e1757014996578.png\")
Figure 5: Eventing Function javascript copy\/pasted in the last step of function definition.<\/p><\/div>\n
Finally deploy the function and it should turn green once ready.<\/p>\n
![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image3-e1757015651761.png\")
Figure 6: pcapEmbedding<\/em> function is deployed and showed up as green under status.<\/p><\/div>\nCheck the document and it should now have additional embedding_vector<\/em> y embedding_model<\/em> fields with the other fields like this:<\/p>\n{\r\n\u00a0\u00a0\"carrier\": \"cb-telecom\",\r\n\u00a0\u00a0\"dstIP\": \"52.0.0.5\",\r\n\u00a0\u00a0\"dstPort\": 16384,\r\n\u00a0\u00a0\"durationMs\": 600000,\r\n\u00a0\u00a0\"jitterMs\": 2.5,\r\n\u00a0\u00a0\"lossPct\": 0.05,\r\n\u00a0\u00a0\"packets\": 100000,\r\n\u00a0\u00a0\"proto\": \"RTP\",\r\n\u00a0\u00a0\"qualityLabel\": \"healthy\",\r\n\u00a0\u00a0\"region\": \"us-east-1\",\r\n\u00a0\u00a0\"retransmits\": 0,\r\n\u00a0\u00a0\"sessionId\": \"sess::1\",\r\n\u00a0\u00a0\"srcIP\": \"10.0.0.1\",\r\n\u00a0\u00a0\"srcPort\": 16384,\r\n\u00a0\u00a0\"summaryText\": \"Stable RTP media stream, negligible packet loss and low jitter\",\r\n\u00a0\u00a0\"ts\": \"2025-08-21T09:00:00Z\",\r\n\u00a0\u00a0\"type\": \"pcap_session\",\r\n\u00a0\u00a0\"embedding_model\": \"text-embedding-3-small\",\r\n\u00a0\u00a0\"embedding_vector\": [-0.004560039, -0.0018385303, 0.033093546, 0.0023359614, ...]\r\n}<\/pre>\nCreating a vector-aware FTS index in Couchbase<\/h3>\n
Now that each PCAP session document carries both an embedding vector<\/b> y enriched metadata<\/b> (region, proto, carrier, jitter, loss, retransmits), the next step is to make these fields searchable. Couchbase\u2019s Full Text Search (FTS) engine now supports vector indexing<\/b>, meaning we can store those high-dimensional embeddings right alongside traditional keyword and numeric fields.<\/p>\n
\u00bfPor qu\u00e9 es importante?
\nBecause it allows us to run semantic queries<\/b> como \u201cfind sessions similar to this degraded call in Asia carried over LTE\u201d<\/i> \u2014 combining similitud sem\u00e1ntica<\/b> (via vector search) with structured filtering<\/b> (region, proto, carrier).<\/p>\n
Here\u2019s a simple JSON definition of such an index (from the FTS console, you\u2019d create a new index and paste this in):<\/p>\n
{\r\n\u00a0\u00a0\"type\": \"fulltext-index\",\r\n\u00a0\u00a0\"name\": \"pcap.telco.pcapEmbeddingIndex\",\r\n\u00a0\u00a0\"uuid\": \"2fd519311de37177\",\r\n\u00a0\u00a0\"sourceType\": \"gocbcore\",\r\n\u00a0\u00a0\"sourceName\": \"pcap\",\r\n\u00a0\u00a0\"sourceUUID\": \"a576b1ee361c33974e47371d03098b72\",\r\n\u00a0\u00a0\"planParams\": {\r\n\u00a0\u00a0\u00a0\u00a0\"maxPartitionsPerPIndex\": 1024,\r\n\u00a0\u00a0\u00a0\u00a0\"indexPartitions\": 1\r\n\u00a0\u00a0},\r\n\u00a0\u00a0\"params\": {\r\n\u00a0\u00a0\u00a0\u00a0\"doc_config\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"docid_prefix_delim\": \"\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"docid_regexp\": \"\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"mode\": \"scope.collection.type_field\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type_field\": \"type\"\r\n\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\"mapping\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"analysis\": {},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"default_analyzer\": \"standard\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"default_datetime_parser\": \"dateTimeOptional\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"default_field\": \"_all\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"default_mapping\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": false\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"default_type\": \"_default\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"docvalues_dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index_dynamic\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store_dynamic\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type_field\": \"_type\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"types\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"telco.sessions\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"properties\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"carrier\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"analyzer\": \"en\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"carrier\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"text\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"embedding_vector\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dims\": 1536,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"embedding_vector\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"similarity\": \"dot_product\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"vector\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"vector_index_optimized_for\": \"recall\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"jitterMs\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"jitterMs\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"number\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"lossPct\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"lossPct\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"number\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"proto\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"analyzer\": \"en\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"proto\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"text\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"qualityLabel\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"analyzer\": \"en\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"qualityLabel\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"text\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"region\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"analyzer\": \"en\",\r\n \u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"region\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"text\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"retransmits\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"dynamic\": false,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"enabled\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"fields\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"index\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"name\": \"retransmits\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"store\": true,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"type\": \"number\"\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0},\r\n\u00a0\u00a0\u00a0\u00a0\"store\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"indexType\": \"scorch\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"segmentVersion\": 16\r\n\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0},\r\n\u00a0\u00a0\"sourceParams\": {}\r\n}<\/pre>\nLet\u2019s break it down in plain English:<\/p>\n
\n- \n
\n- embedding_vector<\/b> \u2192 This is the semantic backbone, a vector field where similarity queries happen. We\u2019ve chosen dot product<\/b> as the similarity metric since it works well with OpenAI embeddings.<\/li>\n
- regi\u00f3n<\/b>, <\/b>proto<\/b>, <\/b>carrier<\/b> \u2192 Indexed as text fields so we can filter by telecom region, packet protocol, or carrier.<\/li>\n
- lossPct<\/b>, <\/b>jitterMs<\/b>, <\/b>retransmits<\/b> \u2192 Numeric fields that allow range queries (e.g., \u201csessions with jitter > 50ms\u201d).<\/li>\n
- qualityLabel<\/b> \u2192 Our Eventing function already tagged calls as \u201chealthy\u201d or \u201cdegraded\u201d, which now becomes a searchable field.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n
This dual structure \u2014 vector + metadata<\/b> \u2014 is what makes the solution powerful. You\u2019re not forced to choose between semantic similarity and structured filtering; you can blend both in a single query.<\/p>\n![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image8-1024x758.png\")
Figure 7: This is how you would create a vector index from Search tab<\/p><\/div>\n
![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image2-e1757014936842.png\")
Figure 8: All the required fields within the sesi\u00f3n<\/em> document are included in the search<\/p><\/div>\nHighlighting anomaly detection with hybrid search<\/h3>\n
Finally, let\u2019s see the real payoff: anomaly detection powered by hybrid vector search<\/b>.<\/p>\n
Imagine you\u2019ve had a rash of complaints about call drops in New York. You could run a query like:<\/p>\n
SELECT META(s).id, s.sessionId, s.summaryText, s.qualityLabel, s.region, s.proto, s.carrier\r\nFROM `pcap`.`telco`.`sessions` AS s\r\nWHERE SEARCH(s, {\r\n\u00a0\u00a0\"fields\": [\"*\"],\r\n\u00a0\u00a0\"knn\": [\r\n\u00a0\u00a0\u00a0\u00a0{\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"k\": 10,\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"field\": \"embedding_vector\",\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"vector\": [\/* ... fill with your actual embedding ... *\/],\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"filter\": {\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\"conjuncts\": [\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{ \"match\": \"degraded\", \"field\": \"qualityLabel\" },\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{ \"match\": \"us-east-1\", \"field\": \"region\" },\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{ \"match\": \"SIP\", \"field\": \"proto\" },\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0{ \"match\": \"cb-telecom\", \"field\": \"carrier\" }\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0]\r\n\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0\u00a0\u00a0}\r\n\u00a0\u00a0]\r\n});<\/pre>\nThis query says:<\/p>\n
\n- \n
\n- Find me 10 sessions most similar to a <\/i>degraded<\/i> SIP call (semantic similarity)<\/i><\/li>\n
- But only if they occurred in <\/i>us-este-1<\/i>, were SIP calls<\/i><\/li>\n<\/ul>\n<\/li>\n<\/ul>\n
What you get back is not just a list of \u201cbad calls\u201d \u2014 it\u2019s a cluster of semantically related anomalies<\/b> that helps you pinpoint the root cause. If they\u2019re all happening on one carrier, you\u2019ve just isolated a provider issue. If they spike at certain hours, maybe it\u2019s a routing bottleneck.<\/p>\n
This is where vector search stops being \u201ccool math\u201d and starts delivering real operational insight<\/b>.<\/p>\n
\nVector search as the backbone of agentic applications<\/h2>\n
Agentic applications are designed not only to retrieve information, but to interpret and act on it. Whether it\u2019s a customer support copilot, a fraud detection engine, or a telecom anomaly detector, these systems need:<\/p>\n
\n- \n
\n- Contextual recall<\/b>: Retrieve the derecha<\/i> information, not just literal matches.<\/li>\n
- Reasoning capabilities<\/b>: Understand relationships and intent.<\/li>\n
- Autonomy<\/b>: Trigger workflows and decisions without human intervention.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n
All three pillars rest on b\u00fasqueda vectorial<\/b>. Without embeddings, agents lack memory. Without similarity search, they lack reasoning. Without semantic context, they cannot act effectively.<\/p>\n
This is why vector search is more than just a new search method \u2014 it is the knowledge backbone<\/b> of the agentic era.<\/p>\n
\nConclusion & what\u2019s next<\/h2>\n
Vector search is transforming industries by shifting search from keywords to context. It powers everything from telecom anomaly detection to customer support copilots and fraud detection. At its core, it lays the foundation for aplicaciones ag\u00e9nticas<\/b> \u2014 intelligent systems that can recall, reason, and act.<\/p>\n
Couchbase brings this to life with its combination of Full Text Search, vector indexing, and eventing<\/b>, enabling enterprises to operationalize semantic search in real time.<\/p>\n
In the next installment, we\u2019ll take this a step further: exploring how LLMs + vector search<\/b> converge to build truly autonomous agentic applications that not only understand context but also generate insights and take proactive actions.<\/p>\n
<\/p>","protected":false},"excerpt":{"rendered":"
The way we search and interact with information has shifted dramatically over the past decade. Traditional keyword-based search engines once served us well in finding documents or answers, but today\u2019s business challenges demand much more than exact keyword matches. Modern […]<\/p>","protected":false},"author":33279,"featured_media":17541,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[10123,9936,9937],"tags":[],"ppma_author":[9090],"class_list":["post-17532","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-agentic-ai-apps","category-search","category-vector-search"],"acf":[],"yoast_head":"\n
Building Smarter Agents: How Vector Search Drives Semantic Intelligence - The Couchbase Blog<\/title>\n<meta name=\"description\" content=\"Vector search has become essential and Couchbase is enabling this transformation with Full Text Search (FTS) and Eventing.\" \/>\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-smarter-agents-with-vector-search\/\" \/>\n<meta property=\"og:locale\" content=\"es_MX\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Building Smarter Agents: How Vector Search Drives Semantic Intelligence\" \/>\n<meta property=\"og:description\" content=\"Vector search has become essential and Couchbase is enabling this transformation with Full Text Search (FTS) and Eventing.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.couchbase.com\/blog\/es\/building-smarter-agents-with-vector-search\/\" \/>\n<meta property=\"og:site_name\" content=\"The Couchbase Blog\" \/>\n<meta property=\"article:published_time\" content=\"2025-09-04T20:01:40+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png\" \/>\n\t<meta property=\"og:image:width\" content=\"2400\" \/>\n\t<meta property=\"og:image:height\" content=\"1256\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"author\" content=\"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"13 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-smarter-agents-with-vector-search\/#article\",\"isPartOf\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/\"},\"author\":{\"name\":\"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/21c735da109667147c580bb2cb351c1c\"},\"headline\":\"Building Smarter Agents: How Vector Search Drives Semantic Intelligence\",\"datePublished\":\"2025-09-04T20:01:40+00:00\",\"mainEntityOfPage\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/\"},\"wordCount\":2482,\"commentCount\":0,\"publisher\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#organization\"},\"image\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png\",\"articleSection\":[\"Agentic AI Applications\",\"Search\",\"Vector Search\"],\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/\",\"url\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/\",\"name\":\"Building Smarter Agents: How Vector Search Drives Semantic Intelligence - The Couchbase Blog\",\"isPartOf\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png\",\"datePublished\":\"2025-09-04T20:01:40+00:00\",\"description\":\"Vector search has become essential and Couchbase is enabling this transformation with Full Text Search (FTS) and Eventing.\",\"breadcrumb\":{\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#breadcrumb\"},\"inLanguage\":\"es\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage\",\"url\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png\",\"contentUrl\":\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png\",\"width\":2400,\"height\":1256},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.couchbase.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Building Smarter Agents: How Vector Search Drives Semantic Intelligence\"}]},{\"@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\/21c735da109667147c580bb2cb351c1c\",\"name\":\"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"es\",\"@id\":\"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/image\/5e9708314822fac560c43a5fbdc9b74f\",\"url\":\"https:\/\/secure.gravatar.com\/avatar\/cb8391905c8ac6ff579c79c90aeaa4e9cf773b87a25e710ee107104c5659deb6?s=96&d=mm&r=g\",\"contentUrl\":\"https:\/\/secure.gravatar.com\/avatar\/cb8391905c8ac6ff579c79c90aeaa4e9cf773b87a25e710ee107104c5659deb6?s=96&d=mm&r=g\",\"caption\":\"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase\"},\"description\":\"Anuj Sahni is a Solutions & Cloud Architecture leader on the Capella team, helping customers design scalable, high-performance enterprise applications and shape their cloud migration journeys using cloud-native technologies and the Couchbase stack. He combines deep expertise in cloud architectures with solutions architecture leadership to help enterprises modernize their applications effectively. Prior to joining Couchbase, Anuj served as Principal Product Manager at Oracle, leading initiatives for Oracle Service Cloud. He brings extensive experience in building distributed, always-available relational and non-relational database systems. Anuj holds an M.S. in Electrical and Computer Engineering from the University of Florida.\",\"sameAs\":[\"https:\/\/www.linkedin.com\/in\/anuj-sahni-6a80b617\"],\"url\":\"https:\/\/www.couchbase.com\/blog\/es\/author\/anujsahni\/\"}]}<\/script>\n<!-- \/ Yoast SEO Premium plugin. -->","yoast_head_json":{"title":"Building Smarter Agents: How Vector Search Drives Semantic Intelligence - The Couchbase Blog","description":"La b\u00fasqueda vectorial se ha vuelto esencial y Couchbase est\u00e1 permitiendo esta transformaci\u00f3n con Full Text Search (FTS) y Eventing.","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-smarter-agents-with-vector-search\/","og_locale":"es_MX","og_type":"article","og_title":"Building Smarter Agents: How Vector Search Drives Semantic Intelligence","og_description":"Vector search has become essential and Couchbase is enabling this transformation with Full Text Search (FTS) and Eventing.","og_url":"https:\/\/www.couchbase.com\/blog\/es\/building-smarter-agents-with-vector-search\/","og_site_name":"The Couchbase Blog","article_published_time":"2025-09-04T20:01:40+00:00","og_image":[{"width":2400,"height":1256,"url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png","type":"image\/png"}],"author":"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase","twitter_card":"summary_large_image","twitter_misc":{"Written by":"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase","Est. reading time":"13 minutos"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#article","isPartOf":{"@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/"},"author":{"name":"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/21c735da109667147c580bb2cb351c1c"},"headline":"Building Smarter Agents: How Vector Search Drives Semantic Intelligence","datePublished":"2025-09-04T20:01:40+00:00","mainEntityOfPage":{"@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/"},"wordCount":2482,"commentCount":0,"publisher":{"@id":"https:\/\/www.couchbase.com\/blog\/#organization"},"image":{"@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage"},"thumbnailUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png","articleSection":["Agentic AI Applications","Search","Vector Search"],"inLanguage":"es","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/","url":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/","name":"Building Smarter Agents: How Vector Search Drives Semantic Intelligence - The Couchbase Blog","isPartOf":{"@id":"https:\/\/www.couchbase.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage"},"image":{"@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage"},"thumbnailUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png","datePublished":"2025-09-04T20:01:40+00:00","description":"La b\u00fasqueda vectorial se ha vuelto esencial y Couchbase est\u00e1 permitiendo esta transformaci\u00f3n con Full Text Search (FTS) y Eventing.","breadcrumb":{"@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#breadcrumb"},"inLanguage":"es","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/"]}]},{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#primaryimage","url":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png","contentUrl":"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/blog-smarter-agents.png","width":2400,"height":1256},{"@type":"BreadcrumbList","@id":"https:\/\/www.couchbase.com\/blog\/building-smarter-agents-with-vector-search\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.couchbase.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Building Smarter Agents: How Vector Search Drives Semantic Intelligence"}]},{"@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\/21c735da109667147c580bb2cb351c1c","name":"Anuj Sahni, Responsable de soluciones y arquitectura en la nube, Couchbase","image":{"@type":"ImageObject","inLanguage":"es","@id":"https:\/\/www.couchbase.com\/blog\/#\/schema\/person\/image\/5e9708314822fac560c43a5fbdc9b74f","url":"https:\/\/secure.gravatar.com\/avatar\/cb8391905c8ac6ff579c79c90aeaa4e9cf773b87a25e710ee107104c5659deb6?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/cb8391905c8ac6ff579c79c90aeaa4e9cf773b87a25e710ee107104c5659deb6?s=96&d=mm&r=g","caption":"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase"},"description":"Anuj Sahni es un l\u00edder de Soluciones y Arquitectura de la Nube en el equipo de Capella, ayudando a los clientes a dise\u00f1ar aplicaciones empresariales escalables y de alto rendimiento y a dar forma a sus viajes de migraci\u00f3n a la nube utilizando tecnolog\u00edas nativas de la nube y la pila de Couchbase. Combina una profunda experiencia en arquitecturas en la nube con el liderazgo en arquitectura de soluciones para ayudar a las empresas a modernizar sus aplicaciones de forma eficaz. Antes de unirse a Couchbase, Anuj trabaj\u00f3 como Director Principal de Producto en Oracle, liderando iniciativas para Oracle Service Cloud. Aporta una amplia experiencia en la creaci\u00f3n de sistemas de bases de datos relacionales y no relacionales distribuidos y siempre disponibles. Anuj tiene un m\u00e1ster en Ingenier\u00eda El\u00e9ctrica e Inform\u00e1tica por la Universidad de Florida.","sameAs":["https:\/\/www.linkedin.com\/in\/anuj-sahni-6a80b617"],"url":"https:\/\/www.couchbase.com\/blog\/es\/author\/anujsahni\/"}]}},"authors":[{"term_id":9090,"user_id":33279,"is_guest":0,"slug":"anujsahni","display_name":"Anuj Sahni, Solutions & Cloud Architecture Leader, Couchbase","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/cb8391905c8ac6ff579c79c90aeaa4e9cf773b87a25e710ee107104c5659deb6?s=96&d=mm&r=g","author_category":"1","last_name":"Sahni, Solutions & Cloud Architecture Leader, Couchbase","first_name":"Anuj","job_title":"","user_url":"https:\/\/www.linkedin.com\/in\/anuj-sahni-6a80b617","description":"<p data-start=\"231\" data-end=\"963\"><strong data-start=\"231\" data-end=\"963\">Anuj Sahni es un l\u00edder de Soluciones y Arquitectura de la Nube en el equipo de Capella, ayudando a los clientes a dise\u00f1ar aplicaciones empresariales escalables y de alto rendimiento y a dar forma a sus viajes de migraci\u00f3n a la nube utilizando tecnolog\u00edas nativas de la nube y la pila de Couchbase. Combina una profunda experiencia en arquitecturas en la nube con el liderazgo en arquitectura de soluciones para ayudar a las empresas a modernizar sus aplicaciones de forma eficaz. Antes de unirse a Couchbase, Anuj trabaj\u00f3 como Director Principal de Producto en Oracle, liderando iniciativas para Oracle Service Cloud. Aporta una amplia experiencia en la creaci\u00f3n de sistemas de bases de datos relacionales y no relacionales distribuidos y siempre disponibles. Anuj tiene un m\u00e1ster en Ingenier\u00eda El\u00e9ctrica e Inform\u00e1tica por la Universidad de Florida.<\/strong><\/p>"}],"_links":{"self":[{"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/posts\/17532","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\/33279"}],"replies":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/comments?post=17532"}],"version-history":[{"count":0,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/posts\/17532\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/media\/17541"}],"wp:attachment":[{"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/media?parent=17532"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/categories?post=17532"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/tags?post=17532"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.couchbase.com\/blog\/es\/wp-json\/wp\/v2\/ppma_author?post=17532"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image4-1024x683.png\")
![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image1-1024x395.png\")
![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image7-e1757015169650.png\")
![\"\"](\"https:\/\/www.couchbase.com\/blog\/wp-content\/uploads\/sites\/1\/2025\/09\/image6-e1757015043238.png\")