diff --git a/docs/docs/Components/bundles-db2.mdx b/docs/docs/Components/bundles-db2.mdx
index bdc84bd3e3..37db9a1c30 100644
--- a/docs/docs/Components/bundles-db2.mdx
+++ b/docs/docs/Components/bundles-db2.mdx
@@ -35,9 +35,7 @@ IBM Db2 Vector Store provides enterprise-grade vector search capabilities with b
 
 ### Use the IBM Db2 Vector Store component in a flow
 
-The following example flow uses one **IBM Db2 Vector Store** component for both reads and writes:
-
-![IBM Db2 Vector Store receiving split text](/img/component-db2-vector-store.png)
+The **IBM Db2 Vector Store** component can be used for both reads and writes:
 
 * When writing, it splits `JSON` from a [**URL** component](/url) into chunks, computes embeddings with attached **Embedding Model** component, and then loads the chunks and embeddings into the Db2 vector store.
 To trigger writes, click <Icon name="Play" aria-hidden="true"/> **Run component** on the **IBM Db2 Vector Store** component.
diff --git a/src/frontend/package-lock.json b/src/frontend/package-lock.json
index 9af722b693..bb99ff3992 100644
--- a/src/frontend/package-lock.json
+++ b/src/frontend/package-lock.json
@@ -217,7 +217,6 @@
       "integrity": "sha512-CGOfOJqWjg2qW/Mb6zNsDm+u5vFQ8DxXfbM09z69p5Z6+mE1ikP2jUXw+j42Pf1XTYED2Rni5f95npYeuwMDQA==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@babel/code-frame": "^7.29.0",
         "@babel/generator": "^7.29.0",
@@ -1083,7 +1082,6 @@
       "resolved": "https://registry.npmjs.org/@chakra-ui/styled-system/-/styled-system-2.9.2.tgz",
       "integrity": "sha512-To/Z92oHpIE+4nk11uVMWqo2GGRS86coeMmjxtpnErmWRdLcp1WVCVRAvn+ZwpLiNR+reWFr2FFqJRsREuZdAg==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@chakra-ui/shared-utils": "2.0.5",
         "csstype": "^3.1.2",
@@ -1095,7 +1093,6 @@
       "resolved": "https://registry.npmjs.org/@chakra-ui/system/-/system-2.6.2.tgz",
       "integrity": "sha512-EGtpoEjLrUu4W1fHD+a62XR+hzC5YfsWm+6lO0Kybcga3yYEij9beegO0jZgug27V+Rf7vns95VPVP6mFd/DEQ==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@chakra-ui/color-mode": "2.2.0",
         "@chakra-ui/object-utils": "2.1.0",
@@ -1202,7 +1199,6 @@
       "resolved": "https://registry.npmjs.org/@codemirror/language/-/language-6.12.3.tgz",
       "integrity": "sha512-QwCZW6Tt1siP37Jet9Tb02Zs81TQt6qQrZR2H+eGMcFsL1zMrk2/b9CLC7/9ieP1fjIUMgviLWMmgiHoJrj+ZA==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@codemirror/state": "^6.0.0",
         "@codemirror/view": "^6.23.0",
@@ -1239,7 +1235,6 @@
       "resolved": "https://registry.npmjs.org/@codemirror/state/-/state-6.6.0.tgz",
       "integrity": "sha512-4nbvra5R5EtiCzr9BTHiTLc+MLXK2QGiAVYMyi8PkQd3SR+6ixar/Q/01Fa21TBIDOZXgeWV4WppsQolSreAPQ==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@marijn/find-cluster-break": "^1.0.0"
       }
@@ -1249,7 +1244,6 @@
       "resolved": "https://registry.npmjs.org/@codemirror/view/-/view-6.41.1.tgz",
       "integrity": "sha512-ToDnWKbBnke+ZLrP6vgTTDScGi5H37YYuZGniQaBzxMVdtCxMrslsmtnOvbPZk4RX9bvkQqnWR/WS/35tJA0qg==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@codemirror/state": "^6.6.0",
         "crelt": "^1.0.6",
@@ -1345,7 +1339,6 @@
         }
       ],
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=18"
       },
@@ -1369,7 +1362,6 @@
         }
       ],
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=18"
       }
@@ -6015,7 +6007,6 @@
       "dev": true,
       "hasInstallScript": true,
       "license": "Apache-2.0",
-      "peer": true,
       "dependencies": {
         "@swc/counter": "^0.1.3",
         "@swc/types": "^0.1.26"
@@ -6422,7 +6413,6 @@
       "integrity": "sha512-o4PXJQidqJl82ckFaXUeoAW+XysPLauYI43Abki5hABd853iMhitooc6znOnczgbTYmEP6U6/y1ZyKAIsvMKGg==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@babel/code-frame": "^7.10.4",
         "@babel/runtime": "^7.12.5",
@@ -7134,7 +7124,6 @@
       "resolved": "https://registry.npmjs.org/@types/react/-/react-19.2.14.tgz",
       "integrity": "sha512-ilcTH/UniCkMdtexkoCN0bI7pMcJDvmQFPvuPvmEaYA/NSfFTAgdUSLAoVjaRJm7+6PvcM+q1zYOwS4wTYMF9w==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "csstype": "^3.2.2"
       }
@@ -7145,7 +7134,6 @@
       "integrity": "sha512-jp2L/eY6fn+KgVVQAOqYItbF0VY/YApe5Mz2F0aykSO8gx31bYCZyvSeYxCHKvzHG5eZjc+zyaS5BrBWya2+kQ==",
       "devOptional": true,
       "license": "MIT",
-      "peer": true,
       "peerDependencies": {
         "@types/react": "^19.2.0"
       }
@@ -7161,8 +7149,7 @@
       "version": "1.15.9",
       "resolved": "https://registry.npmjs.org/@types/sortablejs/-/sortablejs-1.15.9.tgz",
       "integrity": "sha512-7HP+rZGE2p886PKV9c9OJzLBI6BBJu1O7lJGYnPyG3fS4/duUCcngkNCjsLwIMV+WMqANe3tt4irrXHSIe68OQ==",
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
     },
     "node_modules/@types/stack-utils": {
       "version": "2.0.3",
@@ -7794,7 +7781,6 @@
       "resolved": "https://registry.npmjs.org/acorn/-/acorn-8.16.0.tgz",
       "integrity": "sha512-UVJyE9MttOsBQIDKw1skb9nAwQuR5wuGD3+82K6JgJlm/Y+KI92oNsMNGZCYdDsVtRHSak0pcV5Dno5+4jh9sw==",
       "license": "MIT",
-      "peer": true,
       "bin": {
         "acorn": "bin/acorn"
       },
@@ -8295,7 +8281,6 @@
       "integrity": "sha512-riJjyv1/mHLIPX4RwiK+oW9/4c3TEUeORHKefKAKnZ5kyslbN+HXowtbaVEqt4IMUB7OXlfixcs6gsFeo/jhiQ==",
       "dev": true,
       "license": "Apache-2.0",
-      "peer": true,
       "peerDependencies": {
         "bare-abort-controller": "*"
       },
@@ -8564,7 +8549,6 @@
         }
       ],
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "baseline-browser-mapping": "^2.10.12",
         "caniuse-lite": "^1.0.30001782",
@@ -8957,7 +8941,6 @@
       "resolved": "https://registry.npmjs.org/chokidar/-/chokidar-3.6.0.tgz",
       "integrity": "sha512-7VT13fmjotKpGipCW9JEQAusEPE+Ei8nl6/g4FBAmIm0GOOLMua9NDDo/DWp0ZAxCr3cPq5ZpBqmPAQgDda2Pw==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "anymatch": "~3.1.2",
         "braces": "~3.0.2",
@@ -9398,7 +9381,6 @@
       "resolved": "https://registry.npmjs.org/d3-selection/-/d3-selection-3.0.0.tgz",
       "integrity": "sha512-fmTRWbNMmsmWq6xJV8D19U/gw/bwrHfNXxrIN+HfZgnzqTHp9jOmKMhsTUjXOJnZOdZY9Q28y4yebKzqDKlxlQ==",
       "license": "ISC",
-      "peer": true,
       "engines": {
         "node": ">=12"
       }
@@ -9975,7 +9957,6 @@
       "integrity": "sha512-bbPBYYrtZbkt6Os6FiTLCTFxvq4tt3JKall1vRwshA3fdVztsLAatFaZobhkBC8/BrPetoa0oksYoKXoG4ryJg==",
       "hasInstallScript": true,
       "license": "MIT",
-      "peer": true,
       "bin": {
         "esbuild": "bin/esbuild"
       },
@@ -10254,7 +10235,6 @@
       "integrity": "sha512-hIS4idWWai69NezIdRt2xFVofaF4j+6INOpJlVOLDO8zXGpUVEVzIYk12UUi2JzjEzWL3IOAxcTubgz9Po0yXw==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "accepts": "^2.0.0",
         "body-parser": "^2.2.1",
@@ -11387,7 +11367,6 @@
       "integrity": "sha512-jN0ZewiNAWSe5khM3EyCmBb250+b40wWbwNILNfEvq84VREWwOIkuUsFONk/3i3nqkz7Oe1PcpM2mwQEK2L9Kg==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=16.9.0"
       }
@@ -11540,7 +11519,6 @@
         }
       ],
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@babel/runtime": "^7.29.2"
       },
@@ -12100,7 +12078,6 @@
       "integrity": "sha512-AkXIIFcaazymvey2i/+F94XRnM6TsVLZDhBMLsd1Sf/W0wzsvvpjeyUrCZD6HGG4SDYPgDJDBKeiJTBb10WzMg==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@jest/core": "30.3.0",
         "@jest/types": "30.3.0",
@@ -13687,7 +13664,6 @@
       "resolved": "https://registry.npmjs.org/jiti/-/jiti-1.21.7.tgz",
       "integrity": "sha512-/imKNG4EbWNrVjoNC/1H5/9GFy+tqjGBHCaSsN+P2RnPqjsLmv6UD3Ej+Kj8nBWaRAwyk7kK5ZUc+OEatnTR3A==",
       "license": "MIT",
-      "peer": true,
       "bin": {
         "jiti": "bin/jiti.js"
       }
@@ -13737,7 +13713,6 @@
       "integrity": "sha512-Cvc9WUhxSMEo4McES3P7oK3QaXldCfNWp7pl2NNeiIFlCoLr3kfq9kb1fxftiwk1FLV7CvpvDfonxtzUDeSOPg==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "cssstyle": "^4.2.1",
         "data-urls": "^5.0.0",
@@ -13777,7 +13752,6 @@
       "resolved": "https://registry.npmjs.org/jsep/-/jsep-1.4.0.tgz",
       "integrity": "sha512-B7qPcEVE3NVkmSJbaYxvv4cHkVW7DQsZz13pUMrfS8z8Q/BuShN+gcTXrUlPiGqM2/t/EEaI030bpxMqY8gMlw==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">= 10.16.0"
       }
@@ -16273,7 +16247,6 @@
         }
       ],
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "nanoid": "^3.3.11",
         "picocolors": "^1.1.1",
@@ -16696,7 +16669,6 @@
       "resolved": "https://registry.npmjs.org/react/-/react-19.2.5.tgz",
       "integrity": "sha512-llUJLzz1zTUBrskt2pwZgLq59AemifIftw4aB7JxOqf1HY2FDaGDxgwpAPVzHU1kdWabH7FauP4i1oEeer2WCA==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=0.10.0"
       }
@@ -16790,7 +16762,6 @@
       "resolved": "https://registry.npmjs.org/react-dom/-/react-dom-19.2.5.tgz",
       "integrity": "sha512-J5bAZz+DXMMwW/wV3xzKke59Af6CHY7G4uYLN1OvBcKEsWOs4pQExj86BBKamxl/Ik5bx9whOrvBlSDfWzgSag==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "scheduler": "^0.27.0"
       },
@@ -16821,7 +16792,6 @@
       "resolved": "https://registry.npmjs.org/react-hook-form/-/react-hook-form-7.74.0.tgz",
       "integrity": "sha512-yR6wHr99p9wFv686jhRWVSFhUvDvNbdUf2dKlbno8/VKOCuoNobDGC6S+M2dua9A9Yo8vpcrp8assIYbsZCQ9g==",
       "license": "MIT",
-      "peer": true,
       "engines": {
         "node": ">=18.0.0"
       },
@@ -17515,7 +17485,6 @@
       "integrity": "sha512-J9qZyW++QK/09NyN/zeO0dG/1GdGfyp9lV8ajHnRVLfo/uFsbji5mHnDgn/qYdUHyCkM2N+8VyspgZclfAh0eQ==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@types/estree": "1.0.8"
       },
@@ -18034,8 +18003,7 @@
       "version": "1.15.7",
       "resolved": "https://registry.npmjs.org/sortablejs/-/sortablejs-1.15.7.tgz",
       "integrity": "sha512-Kk8wLQPlS+yi1ZEf48a4+fzHa4yxjC30M/Sr2AnQu+f/MPwvvX9XjZ6OWejiz8crBsLwSq8GHqaxaET7u6ux0A==",
-      "license": "MIT",
-      "peer": true
+      "license": "MIT"
     },
     "node_modules/source-map": {
       "version": "0.5.7",
@@ -18214,7 +18182,6 @@
       "integrity": "sha512-vbSz7g/1rGMC1uAULqMZjALkIuLu2QABqfhRYhyr/11kzyesi+vAmwyJLukZP1FfecxGOgMwOh6GS0YsGpHAvQ==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@storybook/global": "^5.0.0",
         "@storybook/icons": "^2.0.1",
@@ -18589,7 +18556,6 @@
       "resolved": "https://registry.npmjs.org/tailwindcss/-/tailwindcss-3.4.19.tgz",
       "integrity": "sha512-3ofp+LL8E+pK/JuPLPggVAIaEuhvIz4qNcf3nA1Xn2o/7fb7s/TYpHhwGDv1ZU3PkBluUVaF8PyCHcm48cKLWQ==",
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "@alloc/quick-lru": "^5.2.0",
         "arg": "^5.0.2",
@@ -19186,7 +19152,6 @@
       "integrity": "sha512-jl1vZzPDinLr9eUt3J/t7V6FgNEw9QjvBPdysz9KfQDD41fQrC2Y4vKQdiaUpFT4bXlb1RHhLpp8wtm6M5TgSw==",
       "devOptional": true,
       "license": "Apache-2.0",
-      "peer": true,
       "bin": {
         "tsc": "bin/tsc",
         "tsserver": "bin/tsserver"
@@ -19700,7 +19665,6 @@
       "integrity": "sha512-Bby3NOsna2jsjfLVOHKes8sGwgl4TT0E6vvpYgnAYDIF/tie7MRaFthmKuHx1NSXjiTueXH3do80FMQgvEktRg==",
       "dev": true,
       "license": "MIT",
-      "peer": true,
       "dependencies": {
         "esbuild": "^0.27.0",
         "fdir": "^6.5.0",
@@ -20685,7 +20649,6 @@
       "resolved": "https://registry.npmjs.org/zod/-/zod-3.25.76.tgz",
       "integrity": "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ==",
       "license": "MIT",
-      "peer": true,
       "funding": {
         "url": "https://github.com/sponsors/colinhacks"
       }
diff --git a/src/lfx/src/lfx/_assets/component_index.json b/src/lfx/src/lfx/_assets/component_index.json
index 0124606884..03a5e9861e 100644
--- a/src/lfx/src/lfx/_assets/component_index.json
+++ b/src/lfx/src/lfx/_assets/component_index.json
@@ -305,7 +305,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "bs4",
@@ -482,7 +482,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -623,7 +623,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -792,7 +792,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -933,7 +933,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -1103,7 +1103,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -1274,7 +1274,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -1467,7 +1467,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -3252,7 +3252,7 @@
                 },
                 {
                   "name": "openai",
-                  "version": "2.33.0"
+                  "version": "2.37.0"
                 }
               ],
               "total_dependencies": 4
@@ -5727,7 +5727,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "pydantic",
@@ -5743,7 +5743,7 @@
                 },
                 {
                   "name": "anthropic",
-                  "version": "0.97.0"
+                  "version": "0.102.0"
                 }
               ],
               "total_dependencies": 5
@@ -9900,7 +9900,7 @@
                 },
                 {
                   "name": "chromadb",
-                  "version": "1.5.8"
+                  "version": "1.5.9"
                 },
                 {
                   "name": "langchain_community",
@@ -11989,7 +11989,7 @@
                 },
                 {
                   "name": "smolagents",
-                  "version": "1.22.0"
+                  "version": "1.25.0"
                 },
                 {
                   "name": "OpenDsStar",
@@ -13405,7 +13405,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_openai",
@@ -56715,7 +56715,7 @@
                 },
                 {
                   "name": "cuga",
-                  "version": "0.2.25"
+                  "version": "0.2.28"
                 }
               ],
               "total_dependencies": 3
@@ -58318,7 +58318,7 @@
                 },
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "bs4",
@@ -58564,7 +58564,7 @@
                 },
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "bs4",
@@ -58885,7 +58885,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "bs4",
@@ -59267,7 +59267,7 @@
                 },
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "bs4",
@@ -60440,7 +60440,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -62446,7 +62446,7 @@
               "dependencies": [
                 {
                   "name": "orjson",
-                  "version": "3.11.8"
+                  "version": "3.11.9"
                 },
                 {
                   "name": "lfx",
@@ -65200,7 +65200,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "pydantic",
@@ -65220,7 +65220,7 @@
                 },
                 {
                   "name": "openai",
-                  "version": "2.33.0"
+                  "version": "2.37.0"
                 }
               ],
               "total_dependencies": 6
@@ -65582,11 +65582,11 @@
               "dependencies": [
                 {
                   "name": "tiktoken",
-                  "version": "0.12.0"
+                  "version": "0.13.0"
                 },
                 {
                   "name": "docling_core",
-                  "version": "2.74.1"
+                  "version": "2.76.0"
                 },
                 {
                   "name": "lfx",
@@ -65891,7 +65891,7 @@
                 },
                 {
                   "name": "docling_core",
-                  "version": "2.74.1"
+                  "version": "2.76.0"
                 }
               ],
               "total_dependencies": 2
@@ -66281,7 +66281,7 @@
                 },
                 {
                   "name": "docling_core",
-                  "version": "2.74.1"
+                  "version": "2.76.0"
                 },
                 {
                   "name": "pydantic",
@@ -66666,7 +66666,7 @@
               "dependencies": [
                 {
                   "name": "docling_core",
-                  "version": "2.74.1"
+                  "version": "2.76.0"
                 },
                 {
                   "name": "lfx",
@@ -68716,7 +68716,7 @@
               "dependencies": [
                 {
                   "name": "numpy",
-                  "version": "2.4.4"
+                  "version": "2.4.5"
                 },
                 {
                   "name": "lfx",
@@ -69448,7 +69448,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 }
               ],
               "total_dependencies": 4
@@ -70282,7 +70282,7 @@
                 },
                 {
                   "name": "cryptography",
-                  "version": "47.0.0"
+                  "version": "46.0.7"
                 },
                 {
                   "name": "langchain_chroma",
@@ -70298,11 +70298,11 @@
                 },
                 {
                   "name": "numpy",
-                  "version": "2.4.4"
+                  "version": "2.4.5"
                 },
                 {
                   "name": "chromadb",
-                  "version": "1.5.8"
+                  "version": "1.5.9"
                 }
               ],
               "total_dependencies": 7
@@ -71817,11 +71817,11 @@
               "dependencies": [
                 {
                   "name": "chromadb",
-                  "version": "1.5.8"
+                  "version": "1.5.9"
                 },
                 {
                   "name": "numpy",
-                  "version": "2.4.4"
+                  "version": "2.4.5"
                 },
                 {
                   "name": "langchain_chroma",
@@ -72034,7 +72034,7 @@
               "dependencies": [
                 {
                   "name": "orjson",
-                  "version": "3.11.8"
+                  "version": "3.11.9"
                 },
                 {
                   "name": "pandas",
@@ -72058,7 +72058,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 }
               ],
               "total_dependencies": 7
@@ -75945,7 +75945,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 },
                 {
                   "name": "langchain_core",
@@ -76360,7 +76360,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 },
                 {
                   "name": "lfx",
@@ -76634,7 +76634,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "pydantic",
@@ -77014,7 +77014,7 @@
                 },
                 {
                   "name": "google_auth_oauthlib",
-                  "version": "1.3.1"
+                  "version": "1.4.0"
                 },
                 {
                   "name": "lfx",
@@ -77819,7 +77819,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -78002,7 +78002,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -78168,7 +78168,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_community",
@@ -78818,13 +78818,14 @@
             "allow_duplicates",
             "search_type",
             "number_of_results",
+            "score_threshold",
             "distance_strategy"
           ],
           "frozen": false,
           "icon": "DB2",
           "legacy": false,
           "metadata": {
-            "code_hash": "53666f5e9296",
+            "code_hash": "bff56c2e51e1",
             "dependencies": {
               "dependencies": [
                 {
@@ -78929,7 +78930,7 @@
               "show": true,
               "title_case": false,
               "type": "code",
-              "value": "\"\"\"IBM Db2 Vector Store Component for Langflow.\"\"\"\n\nfrom lfx.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom lfx.components.ibm.db2_security import (\n    create_safe_error_message,\n    validate_database_name,\n    validate_hostname,\n    validate_identifier,\n    validate_port,\n)\nfrom lfx.helpers.data import docs_to_data\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, HandleInput, IntInput, SecretStrInput, StrInput\nfrom lfx.io import Output, QueryInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DB2VectorStoreComponent(LCVectorStoreComponent):\n    \"\"\"IBM Db2 Vector Store with search capabilities.\"\"\"\n\n    display_name: str = \"IBM Db2 Vector Store\"\n    description: str = (\n        \"IBM Db2 Vector Store with search capabilities. \"\n        \"Use Generic-typed global variables for connection parameters (database, hostname, username). \"\n        \"Only password should use Credential-typed variables.\"\n    )\n    documentation: str = \"https://www.ibm.com/docs/en/db2/11.5\"\n    name = \"DB2VectorStore\"\n    icon = \"DB2\"\n\n    inputs = [\n        StrInput(\n            name=\"collection_name\",\n            display_name=\"Table Name\",\n            value=\"LANGFLOW_VECTORS\",\n            required=True,\n            info=\"Name of the DB2 table to store vectors (will be created if it doesn't exist)\",\n        ),\n        HandleInput(\n            name=\"embedding\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            required=True,\n            info=\"Embedding model to use for vectorization\",\n        ),\n        HandleInput(\n            name=\"ingest_data\",\n            display_name=\"Ingest Data\",\n            input_types=[\"Data\", \"DataFrame\", \"Table\", \"Message\"],\n            is_list=True,\n            info=\"Data to ingest into the vector store. Supports Data, DataFrame, Table, and Message objects.\",\n        ),\n        QueryInput(\n            name=\"search_query\",\n            display_name=\"Search Query\",\n            info=\"Enter a query to run a similarity search.\",\n            placeholder=\"Enter a query...\",\n            tool_mode=True,\n        ),\n        # DB2 Connection Credentials (Advanced Settings)\n        StrInput(\n            name=\"database\",\n            display_name=\"Database Name\",\n            required=True,\n            advanced=True,\n            info=\"Name of the Db2 database. Use a Generic-typed global variable or direct input. \"\n            \"Credential-typed variables are not allowed for database names.\",\n        ),\n        StrInput(\n            name=\"hostname\",\n            display_name=\"Hostname\",\n            required=True,\n            advanced=True,\n            info=\"Db2 server hostname or IP address. Use a Generic-typed global variable or direct input.\",\n        ),\n        IntInput(\n            name=\"port\",\n            display_name=\"Port\",\n            value=50000,\n            required=True,\n            advanced=True,\n            info=\"Db2 server port (default: 50000)\",\n        ),\n        StrInput(\n            name=\"username\",\n            display_name=\"Username\",\n            required=True,\n            advanced=True,\n            info=\"Db2 database username. Use a Generic-typed global variable or direct input.\",\n        ),\n        SecretStrInput(\n            name=\"password\",\n            display_name=\"Password\",\n            required=True,\n            advanced=True,\n            info=\"Db2 database password\",\n        ),\n        # Advanced Settings\n        BoolInput(\n            name=\"should_cache_vector_store\",\n            display_name=\"Cache Vector Store\",\n            value=True,\n            advanced=True,\n            info=\"If True, the vector store will be cached for the current build of the component.\",\n        ),\n        BoolInput(\n            name=\"allow_duplicates\",\n            display_name=\"Allow Duplicates\",\n            advanced=True,\n            value=True,\n            info=\"If false, will not add documents that are already in the Vector Store.\",\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            options=[\"Similarity\", \"MMR\", \"similarity_score_threshold\"],\n            value=\"Similarity\",\n            advanced=True,\n            info=\"Type of search to perform\",\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Results\",\n            value=4,\n            advanced=True,\n            info=\"Number of results to return from search\",\n        ),\n        DropdownInput(\n            name=\"distance_strategy\",\n            display_name=\"Distance Strategy\",\n            options=[\"COSINE\", \"EUCLIDEAN_DISTANCE\", \"DOT_PRODUCT\"],\n            value=\"COSINE\",\n            advanced=True,\n            info=\"Distance calculation strategy\",\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"Search Results\",\n            name=\"search_results\",\n            method=\"search_documents\",\n        ),\n        Output(\n            display_name=\"Vector Store\",\n            name=\"vector_store\",\n            method=\"build_vector_store\",\n        ),\n        Output(\n            display_name=\"Table\",\n            name=\"dataframe\",\n            method=\"perform_search\",\n        ),\n    ]\n\n    def perform_search(self) -> DataFrame:\n        \"\"\"Return search results as a DataFrame.\"\"\"\n        from lfx.schema.dataframe import DataFrame\n\n        # Get search results\n        results = self.search_documents()\n\n        # Return DataFrame wrapping the Data objects\n        # DataFrame constructor will handle Data objects properly\n        return DataFrame(results)\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        \"\"\"Adds documents to the Vector Store - SIMPLIFIED like Chroma.\"\"\"\n        from copy import deepcopy\n\n        if not self.ingest_data:\n            self.status = \"\"\n            return\n\n        # Convert DataFrame to Data if needed using parent's method\n        ingest_data = self._prepare_ingest_data()\n\n        # Get existing documents for duplicate checking (simplified)\n        stored_documents_without_id = []\n        if not self.allow_duplicates:\n            # TODO: Implement db2_collection_to_data utility\n            # For now, skip duplicate checking to match Chroma's approach\n            stored_data = []\n            for value in deepcopy(stored_data):\n                if hasattr(value, \"id\"):\n                    del value.id\n                stored_documents_without_id.append(value)\n\n        # Process only Data objects (like Chroma)\n        documents = []\n        for _input in ingest_data or []:\n            if isinstance(_input, Data):\n                if _input not in stored_documents_without_id:\n                    documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        # Add documents with metadata filtering (like Chroma)\n        if documents and self.embedding is not None:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                from langchain_community.vectorstores.utils import filter_complex_metadata\n\n                filtered_documents = filter_complex_metadata(documents)\n                vector_store.add_documents(filtered_documents)\n            except ImportError:\n                self.log(\"Warning: Could not import filter_complex_metadata. Adding documents without filtering.\")\n                vector_store.add_documents(documents)\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    @check_cached_vector_store\n    def build_vector_store(self):  # type: ignore[override]\n        \"\"\"Build and return the DB2 vector store instance.\"\"\"\n        try:\n            import ibm_db_dbi\n            from langchain_community.vectorstores.utils import DistanceStrategy\n\n            from lfx.components.ibm.db2vs import DB2VS\n        except ImportError as e:\n            msg = \"Could not import required DB2 packages. Please install ibm_db and ibm_db_dbi.\"\n            raise ImportError(msg) from e\n\n        # SECURITY: Validate all connection parameters\n        try:\n            validated_database = validate_database_name(self.database)\n            validated_hostname = validate_hostname(self.hostname)\n            validated_port = validate_port(self.port)\n            validated_table_name = validate_identifier(self.collection_name, \"table name\")\n        except ValueError as e:\n            msg = f\"Invalid connection parameters: {e}\"\n            raise ValueError(msg) from e\n\n        if not self.username or not self.password:\n            msg = \"Missing required credentials: username and password are required\"\n            raise ValueError(msg)\n\n        # Create connection string with validated parameters\n        conn_str = (\n            f\"DATABASE={validated_database};\"\n            f\"HOSTNAME={validated_hostname};\"\n            f\"PORT={validated_port};\"\n            f\"PROTOCOL=TCPIP;\"\n            f\"UID={self.username};\"\n            f\"PWD={self.password};\"\n        )\n\n        # Create connection with safe error handling\n        try:\n            connection = ibm_db_dbi.connect(conn_str, \"\", \"\")\n            self.log(f\"Connected to DB2 database: {validated_database}\")\n        except Exception as e:\n            # SECURITY: Use safe error messages that don't expose sensitive info\n            safe_msg = create_safe_error_message(e, \"while connecting to database\")\n            self.log(f\"Connection failed: {safe_msg}\")\n            raise ConnectionError(safe_msg) from e\n\n        # Map distance strategy\n        distance_strategy_map = {\n            \"COSINE\": DistanceStrategy.COSINE,\n            \"EUCLIDEAN_DISTANCE\": DistanceStrategy.EUCLIDEAN_DISTANCE,\n            \"DOT_PRODUCT\": DistanceStrategy.DOT_PRODUCT,\n        }\n\n        try:\n            # Validate embedding model is provided\n            if not self.embedding:\n                msg = (\n                    \"❌ Embedding Model Required\\n\\n\"\n                    \"Please connect an embedding model to the 'Embedding Model' input.\\n\"\n                    \"This is required to generate embeddings for your data.\"\n                )\n                raise ValueError(msg)\n\n            # Build vector store (will automatically generate embeddings for existing empty rows)\n            self.log(f\"Connecting to DB2 table: {validated_table_name}\")\n            vector_store = DB2VS(\n                client=connection,\n                embedding_function=self.embedding,\n                table_name=validated_table_name,\n                distance_strategy=distance_strategy_map.get(self.distance_strategy, DistanceStrategy.COSINE),\n            )\n\n            self.log(f\"Connected to DB2 table: {validated_table_name}\")\n\n            # Add documents if provided - SIMPLIFIED like Chroma\n            self._add_documents_to_vector_store(vector_store)\n        except Exception:\n            # Ensure connection is closed on error\n            connection.close()\n            raise\n\n        return vector_store\n\n    def search_documents(self) -> list[Data]:\n        \"\"\"Perform similarity search and return results.\"\"\"\n        if not self.search_query:\n            return []\n\n        # Extract text from search_query (handle Message, Data, or string)\n        query_text = self.search_query\n        if hasattr(self.search_query, \"text\"):\n            # Handle Message objects\n            query_text = self.search_query.text\n        elif isinstance(self.search_query, Data):\n            # Handle Data objects - try different attributes\n            if hasattr(self.search_query, \"text_data\") and self.search_query.text_data:\n                query_text = self.search_query.text_data\n            elif hasattr(self.search_query, \"data\") and self.search_query.data:\n                # If data is a dict or JSON, convert to string\n                if isinstance(self.search_query.data, dict):\n                    # Extract text from common fields\n                    query_text = (\n                        self.search_query.data.get(\"text\")\n                        or self.search_query.data.get(\"content\")\n                        or self.search_query.data.get(\"query\")\n                        or str(self.search_query.data)\n                    )\n                else:\n                    query_text = str(self.search_query.data)\n            else:\n                query_text = str(self.search_query)\n        elif not isinstance(self.search_query, str):\n            # Convert any other type to string\n            query_text = str(self.search_query)\n\n        # Build vector store\n        vector_store = self.build_vector_store()\n\n        # Perform search based on search type\n        if self.search_type == \"Similarity\":\n            docs = vector_store.similarity_search(\n                query=query_text,\n                k=self.number_of_results,\n            )\n        elif self.search_type == \"similarity_score_threshold\":\n            docs_and_scores = vector_store.similarity_search_with_relevance_scores(\n                query=query_text,\n                k=self.number_of_results,\n            )\n            docs = [doc for doc, _score in docs_and_scores]\n        else:  # MMR\n            docs = vector_store.max_marginal_relevance_search(\n                query=query_text,\n                k=self.number_of_results,\n            )\n\n        return docs_to_data(docs)\n\n    def build(self):  # type: ignore[override]\n        \"\"\"Build the component based on the selected mode.\"\"\"\n        mode = getattr(self, \"mode\", \"Ingest\")\n\n        if mode == \"Search\":\n            # Search mode: return search results\n            return self.search_documents()\n        if mode == \"Vector Store\":\n            # Vector Store mode: return the vector store instance\n            return self.build_vector_store()\n        # Ingest mode (default): build vector store with data ingestion\n        return self.build_vector_store()\n\n\n# Made with Bob\n"
+              "value": "\"\"\"IBM Db2 Vector Store Component for Langflow.\"\"\"\n\nfrom lfx.base.vectorstores.model import LCVectorStoreComponent, check_cached_vector_store\nfrom lfx.components.ibm.db2_security import (\n    create_safe_error_message,\n    validate_database_name,\n    validate_hostname,\n    validate_identifier,\n    validate_port,\n)\nfrom lfx.helpers.data import docs_to_data\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, FloatInput, HandleInput, IntInput, SecretStrInput, StrInput\nfrom lfx.io import Output, QueryInput\nfrom lfx.schema.data import Data\nfrom lfx.schema.dataframe import DataFrame\n\n\nclass DB2VectorStoreComponent(LCVectorStoreComponent):\n    \"\"\"IBM Db2 Vector Store with search capabilities.\"\"\"\n\n    display_name: str = \"IBM Db2 Vector Store\"\n    description: str = (\n        \"IBM Db2 Vector Store with search capabilities. \"\n        \"Use Generic-typed global variables for connection parameters (database, hostname, username). \"\n        \"Only password should use Credential-typed variables.\"\n    )\n    documentation: str = \"https://www.ibm.com/docs/en/db2/11.5\"\n    name = \"DB2VectorStore\"\n    icon = \"DB2\"\n\n    inputs = [\n        StrInput(\n            name=\"collection_name\",\n            display_name=\"Table Name\",\n            value=\"LANGFLOW_VECTORS\",\n            required=True,\n            info=\"Name of the DB2 table to store vectors (will be created if it doesn't exist)\",\n        ),\n        HandleInput(\n            name=\"embedding\",\n            display_name=\"Embedding Model\",\n            input_types=[\"Embeddings\"],\n            required=True,\n            info=\"Embedding model to use for vectorization\",\n        ),\n        HandleInput(\n            name=\"ingest_data\",\n            display_name=\"Ingest Data\",\n            input_types=[\"Data\", \"DataFrame\", \"Table\", \"Message\"],\n            is_list=True,\n            info=\"Data to ingest into the vector store. Supports Data, DataFrame, Table, and Message objects.\",\n        ),\n        QueryInput(\n            name=\"search_query\",\n            display_name=\"Search Query\",\n            info=\"Enter a query to run a similarity search.\",\n            placeholder=\"Enter a query...\",\n            tool_mode=True,\n        ),\n        # DB2 Connection Credentials (Advanced Settings)\n        StrInput(\n            name=\"database\",\n            display_name=\"Database Name\",\n            required=True,\n            advanced=True,\n            info=\"Name of the Db2 database. Use a Generic-typed global variable or direct input. \"\n            \"Credential-typed variables are not allowed for database names.\",\n        ),\n        StrInput(\n            name=\"hostname\",\n            display_name=\"Hostname\",\n            required=True,\n            advanced=True,\n            info=\"Db2 server hostname or IP address. Use a Generic-typed global variable or direct input.\",\n        ),\n        IntInput(\n            name=\"port\",\n            display_name=\"Port\",\n            value=50000,\n            required=True,\n            advanced=True,\n            info=\"Db2 server port (default: 50000)\",\n        ),\n        StrInput(\n            name=\"username\",\n            display_name=\"Username\",\n            required=True,\n            advanced=True,\n            info=\"Db2 database username. Use a Generic-typed global variable or direct input.\",\n        ),\n        SecretStrInput(\n            name=\"password\",\n            display_name=\"Password\",\n            required=True,\n            advanced=True,\n            info=\"Db2 database password\",\n        ),\n        # Advanced Settings\n        BoolInput(\n            name=\"should_cache_vector_store\",\n            display_name=\"Cache Vector Store\",\n            value=True,\n            advanced=True,\n            info=\"If True, the vector store will be cached for the current build of the component.\",\n        ),\n        BoolInput(\n            name=\"allow_duplicates\",\n            display_name=\"Allow Duplicates\",\n            advanced=True,\n            value=True,\n            info=\"If false, will not add documents that are already in the Vector Store.\",\n        ),\n        DropdownInput(\n            name=\"search_type\",\n            display_name=\"Search Type\",\n            options=[\"Similarity\", \"MMR\", \"similarity_score_threshold\"],\n            value=\"Similarity\",\n            advanced=True,\n            info=\"Type of search to perform\",\n        ),\n        IntInput(\n            name=\"number_of_results\",\n            display_name=\"Number of Results\",\n            value=4,\n            advanced=True,\n            info=\"Number of results to return from search\",\n        ),\n        FloatInput(\n            name=\"score_threshold\",\n            display_name=\"Score Threshold\",\n            value=0.5,\n            advanced=True,\n            info=\"Minimum relevance score (0-1) for similarity_score_threshold mode\",\n        ),\n        DropdownInput(\n            name=\"distance_strategy\",\n            display_name=\"Distance Strategy\",\n            options=[\"COSINE\", \"EUCLIDEAN_DISTANCE\", \"DOT_PRODUCT\"],\n            value=\"COSINE\",\n            advanced=True,\n            info=\"Distance calculation strategy\",\n        ),\n    ]\n\n    outputs = [\n        Output(\n            display_name=\"Search Results\",\n            name=\"search_results\",\n            method=\"search_documents\",\n        ),\n        Output(\n            display_name=\"Vector Store\",\n            name=\"vector_store\",\n            method=\"build_vector_store\",\n        ),\n        Output(\n            display_name=\"Table\",\n            name=\"dataframe\",\n            method=\"perform_search\",\n        ),\n    ]\n\n    def perform_search(self) -> DataFrame:\n        \"\"\"Return search results as a DataFrame.\"\"\"\n        from lfx.schema.dataframe import DataFrame\n\n        # Get search results\n        results = self.search_documents()\n\n        # Return DataFrame wrapping the Data objects\n        # DataFrame constructor will handle Data objects properly\n        return DataFrame(results)\n\n    def _add_documents_to_vector_store(self, vector_store) -> None:\n        \"\"\"Adds documents to the Vector Store - SIMPLIFIED like Chroma.\"\"\"\n        from copy import deepcopy\n\n        if not self.ingest_data:\n            self.status = \"\"\n            return\n\n        # Convert DataFrame to Data if needed using parent's method\n        ingest_data = self._prepare_ingest_data()\n\n        # Get existing documents for duplicate checking (simplified)\n        stored_documents_without_id = []\n        if not self.allow_duplicates:\n            # TODO: Implement db2_collection_to_data utility\n            # For now, skip duplicate checking to match Chroma's approach\n            stored_data = []\n            for value in deepcopy(stored_data):\n                if hasattr(value, \"id\"):\n                    del value.id\n                stored_documents_without_id.append(value)\n\n        # Process only Data objects (like Chroma)\n        documents = []\n        for _input in ingest_data or []:\n            if isinstance(_input, Data):\n                if _input not in stored_documents_without_id:\n                    documents.append(_input.to_lc_document())\n            else:\n                msg = \"Vector Store Inputs must be Data objects.\"\n                raise TypeError(msg)\n\n        # Add documents with metadata filtering (like Chroma)\n        if documents and self.embedding is not None:\n            self.log(f\"Adding {len(documents)} documents to the Vector Store.\")\n            try:\n                from langchain_community.vectorstores.utils import filter_complex_metadata\n\n                filtered_documents = filter_complex_metadata(documents)\n                vector_store.add_documents(filtered_documents)\n            except ImportError:\n                self.log(\"Warning: Could not import filter_complex_metadata. Adding documents without filtering.\")\n                vector_store.add_documents(documents)\n        else:\n            self.log(\"No documents to add to the Vector Store.\")\n\n    @check_cached_vector_store\n    def build_vector_store(self):  # type: ignore[override]\n        \"\"\"Build and return the DB2 vector store instance.\"\"\"\n        try:\n            import ibm_db_dbi\n            from langchain_community.vectorstores.utils import DistanceStrategy\n\n            from lfx.components.ibm.db2vs import DB2VS\n        except ImportError as e:\n            msg = \"Could not import required DB2 packages. Please install ibm_db and ibm_db_dbi.\"\n            raise ImportError(msg) from e\n\n        # SECURITY: Validate all connection parameters\n        try:\n            validated_database = validate_database_name(self.database)\n            validated_hostname = validate_hostname(self.hostname)\n            validated_port = validate_port(self.port)\n            validated_table_name = validate_identifier(self.collection_name, \"table name\")\n        except ValueError as e:\n            msg = f\"Invalid connection parameters: {e}\"\n            raise ValueError(msg) from e\n\n        if not self.username or not self.password:\n            msg = \"Missing required credentials: username and password are required\"\n            raise ValueError(msg)\n\n        # Create connection string with validated parameters\n        conn_str = (\n            f\"DATABASE={validated_database};\"\n            f\"HOSTNAME={validated_hostname};\"\n            f\"PORT={validated_port};\"\n            f\"PROTOCOL=TCPIP;\"\n            f\"UID={self.username};\"\n            f\"PWD={self.password};\"\n        )\n\n        # Create connection with safe error handling\n        try:\n            connection = ibm_db_dbi.connect(conn_str, \"\", \"\")\n            self.log(f\"Connected to DB2 database: {validated_database}\")\n        except Exception as e:\n            # SECURITY: Use safe error messages that don't expose sensitive info\n            safe_msg = create_safe_error_message(e, \"while connecting to database\")\n            self.log(f\"Connection failed: {safe_msg}\")\n            raise ConnectionError(safe_msg) from e\n\n        # Map distance strategy\n        distance_strategy_map = {\n            \"COSINE\": DistanceStrategy.COSINE,\n            \"EUCLIDEAN_DISTANCE\": DistanceStrategy.EUCLIDEAN_DISTANCE,\n            \"DOT_PRODUCT\": DistanceStrategy.DOT_PRODUCT,\n        }\n\n        try:\n            # Validate embedding model is provided\n            if not self.embedding:\n                msg = (\n                    \"❌ Embedding Model Required\\n\\n\"\n                    \"Please connect an embedding model to the 'Embedding Model' input.\\n\"\n                    \"This is required to generate embeddings for your data.\"\n                )\n                raise ValueError(msg)\n\n            # Build vector store (will automatically generate embeddings for existing empty rows)\n            self.log(f\"Connecting to DB2 table: {validated_table_name}\")\n            vector_store = DB2VS(\n                client=connection,\n                embedding_function=self.embedding,\n                table_name=validated_table_name,\n                distance_strategy=distance_strategy_map.get(self.distance_strategy, DistanceStrategy.COSINE),\n            )\n\n            self.log(f\"Connected to DB2 table: {validated_table_name}\")\n\n            # Add documents if provided - SIMPLIFIED like Chroma\n            self._add_documents_to_vector_store(vector_store)\n        except Exception:\n            # Ensure connection is closed on error\n            connection.close()\n            raise\n\n        return vector_store\n\n    def search_documents(self) -> list[Data]:\n        \"\"\"Perform similarity search and return results.\"\"\"\n        if not self.search_query:\n            return []\n\n        # Extract text from search_query (handle Message, Data, or string)\n        query_text = self.search_query\n        if hasattr(self.search_query, \"text\"):\n            # Handle Message objects\n            query_text = self.search_query.text\n        elif isinstance(self.search_query, Data):\n            # Handle Data objects - try different attributes\n            if hasattr(self.search_query, \"text_data\") and self.search_query.text_data:\n                query_text = self.search_query.text_data\n            elif hasattr(self.search_query, \"data\") and self.search_query.data:\n                # If data is a dict or JSON, convert to string\n                if isinstance(self.search_query.data, dict):\n                    # Extract text from common fields\n                    query_text = (\n                        self.search_query.data.get(\"text\")\n                        or self.search_query.data.get(\"content\")\n                        or self.search_query.data.get(\"query\")\n                        or str(self.search_query.data)\n                    )\n                else:\n                    query_text = str(self.search_query.data)\n            else:\n                query_text = str(self.search_query)\n        elif not isinstance(self.search_query, str):\n            # Convert any other type to string\n            query_text = str(self.search_query)\n\n        # Build vector store\n        vector_store = self.build_vector_store()\n\n        # Perform search based on search type\n        if self.search_type == \"Similarity\":\n            docs = vector_store.similarity_search(\n                query=query_text,\n                k=self.number_of_results,\n            )\n        elif self.search_type == \"similarity_score_threshold\":\n            docs_and_scores = vector_store.similarity_search_with_relevance_scores(\n                query=query_text,\n                k=self.number_of_results,\n            )\n            # Apply threshold filtering\n            docs = [doc for doc, score in docs_and_scores if score >= self.score_threshold]\n        else:  # MMR\n            docs = vector_store.max_marginal_relevance_search(\n                query=query_text,\n                k=self.number_of_results,\n            )\n\n        return docs_to_data(docs)\n\n    def build(self):  # type: ignore[override]\n        \"\"\"Build the component based on the selected mode.\"\"\"\n        mode = getattr(self, \"mode\", \"Ingest\")\n\n        if mode == \"Search\":\n            # Search mode: return search results\n            return self.search_documents()\n        if mode == \"Vector Store\":\n            # Vector Store mode: return the vector store instance\n            return self.build_vector_store()\n        # Ingest mode (default): build vector store with data ingestion\n        return self.build_vector_store()\n\n\n# Made with Bob\n"
             },
             "collection_name": {
               "_input_type": "StrInput",
@@ -79128,6 +79129,26 @@
               "type": "int",
               "value": 50000
             },
+            "score_threshold": {
+              "_input_type": "FloatInput",
+              "advanced": true,
+              "display_name": "Score Threshold",
+              "dynamic": false,
+              "info": "Minimum relevance score (0-1) for similarity_score_threshold mode",
+              "list": false,
+              "list_add_label": "Add More",
+              "name": "score_threshold",
+              "override_skip": false,
+              "placeholder": "",
+              "required": false,
+              "show": true,
+              "title_case": false,
+              "tool_mode": false,
+              "trace_as_metadata": true,
+              "track_in_telemetry": true,
+              "type": "float",
+              "value": 0.5
+            },
             "search_query": {
               "_input_type": "QueryInput",
               "advanced": false,
@@ -79266,7 +79287,7 @@
               "dependencies": [
                 {
                   "name": "langchain_ibm",
-                  "version": "1.0.7"
+                  "version": "1.0.10"
                 },
                 {
                   "name": "lfx",
@@ -79815,11 +79836,11 @@
               "dependencies": [
                 {
                   "name": "ibm_watsonx_ai",
-                  "version": "1.5.10"
+                  "version": "1.5.11"
                 },
                 {
                   "name": "langchain_ibm",
-                  "version": "1.0.7"
+                  "version": "1.0.10"
                 },
                 {
                   "name": "lfx",
@@ -80061,7 +80082,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "lfx",
@@ -80556,7 +80577,7 @@
               "dependencies": [
                 {
                   "name": "orjson",
-                  "version": "3.11.8"
+                  "version": "3.11.9"
                 },
                 {
                   "name": "fastapi",
@@ -84686,7 +84707,7 @@
                 },
                 {
                   "name": "langchain",
-                  "version": "1.2.17"
+                  "version": "1.2.18"
                 }
               ],
               "total_dependencies": 3
@@ -89480,7 +89501,7 @@
                 },
                 {
                   "name": "openai",
-                  "version": "2.33.0"
+                  "version": "2.37.0"
                 }
               ],
               "total_dependencies": 4
@@ -91767,7 +91788,7 @@
                 },
                 {
                   "name": "openai",
-                  "version": "2.33.0"
+                  "version": "2.37.0"
                 }
               ],
               "total_dependencies": 4
@@ -93151,7 +93172,7 @@
               "dependencies": [
                 {
                   "name": "langchain_mistralai",
-                  "version": "1.1.2"
+                  "version": "1.1.4"
                 },
                 {
                   "name": "pydantic",
@@ -93381,7 +93402,7 @@
               "dependencies": [
                 {
                   "name": "langchain_mistralai",
-                  "version": "1.1.2"
+                  "version": "1.1.4"
                 },
                 {
                   "name": "pydantic",
@@ -93809,7 +93830,7 @@
               "dependencies": [
                 {
                   "name": "langchain",
-                  "version": "1.2.17"
+                  "version": "1.2.18"
                 },
                 {
                   "name": "lfx",
@@ -96809,7 +96830,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_core",
@@ -97086,7 +97107,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_openai",
@@ -98044,7 +98065,7 @@
               "dependencies": [
                 {
                   "name": "pypdf",
-                  "version": "6.10.2"
+                  "version": "6.11.0"
                 },
                 {
                   "name": "lfx",
@@ -100800,7 +100821,7 @@
                 },
                 {
                   "name": "openai",
-                  "version": "2.33.0"
+                  "version": "2.37.0"
                 }
               ],
               "total_dependencies": 3
@@ -102135,7 +102156,7 @@
               "dependencies": [
                 {
                   "name": "numpy",
-                  "version": "2.4.4"
+                  "version": "2.4.5"
                 },
                 {
                   "name": "langchain_core",
@@ -111721,7 +111742,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_classic",
@@ -117839,7 +117860,7 @@
                 },
                 {
                   "name": "openai",
-                  "version": "2.33.0"
+                  "version": "2.37.0"
                 }
               ],
               "total_dependencies": 4
@@ -118240,7 +118261,7 @@
                 },
                 {
                   "name": "vlmrun",
-                  "version": "0.6.2"
+                  "version": "0.6.3"
                 }
               ],
               "total_dependencies": 3
@@ -119244,7 +119265,7 @@
               "dependencies": [
                 {
                   "name": "requests",
-                  "version": "2.33.1"
+                  "version": "2.34.2"
                 },
                 {
                   "name": "langchain_openai",
@@ -119264,7 +119285,7 @@
                 },
                 {
                   "name": "openai",
-                  "version": "2.33.0"
+                  "version": "2.37.0"
                 }
               ],
               "total_dependencies": 6
@@ -119816,7 +119837,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 },
                 {
                   "name": "lfx",
@@ -120005,7 +120026,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 },
                 {
                   "name": "lfx",
@@ -120321,7 +120342,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 },
                 {
                   "name": "lfx",
@@ -120720,7 +120741,7 @@
                 },
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 },
                 {
                   "name": "lfx",
@@ -120983,7 +121004,7 @@
               "dependencies": [
                 {
                   "name": "googleapiclient",
-                  "version": "2.195.0"
+                  "version": "2.196.0"
                 },
                 {
                   "name": "pandas",
@@ -121354,6 +121375,6 @@
     "num_components": 363,
     "num_modules": 97
   },
-  "sha256": "89b8c2cf05facd7a733e149c0833d142db0cb255b62df0372062c1b60b1d1d3f",
+  "sha256": "f79b14435df8ff3ae3be22fc28236061251d3c5ac58467fa0f458f22ec9ba097",
   "version": "0.5.0"
 }