langflow-base-nightly 1.8.0.dev4__py3-none-any.whl → 1.8.0.dev11__py3-none-any.whl

langflow/frontend/assets/wheat-BcdibuPx.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const e=[["path",{d:"M2 22 16 8",key:"60hf96"}],["path",{d:"M3.47 12.53 5 11l1.53 1.53a3.5 3.5 0 0 1 0 4.94L5 19l-1.53-1.53a3.5 3.5 0 0 1 0-4.94Z",key:"1rdhi6"}],["path",{d:"M7.47 8.53 9 7l1.53 1.53a3.5 3.5 0 0 1 0 4.94L9 15l-1.53-1.53a3.5 3.5 0 0 1 0-4.94Z",key:"1sdzmb"}],["path",{d:"M11.47 4.53 13 3l1.53 1.53a3.5 3.5 0 0 1 0 4.94L13 11l-1.53-1.53a3.5 3.5 0 0 1 0-4.94Z",key:"eoatbi"}],["path",{d:"M20 2h2v2a4 4 0 0 1-4 4h-2V6a4 4 0 0 1 4-4Z",key:"19rau1"}],["path",{d:"M11.47 17.47 13 19l-1.53 1.53a3.5 3.5 0 0 1-4.94 0L5 19l1.53-1.53a3.5 3.5 0 0 1 4.94 0Z",key:"tc8ph9"}],["path",{d:"M15.47 13.47 17 15l-1.53 1.53a3.5 3.5 0 0 1-4.94 0L9 15l1.53-1.53a3.5 3.5 0 0 1 4.94 0Z",key:"2m8kc5"}],["path",{d:"M19.47 9.47 21 11l-1.53 1.53a3.5 3.5 0 0 1-4.94 0L13 11l1.53-1.53a3.5 3.5 0 0 1 4.94 0Z",key:"vex3ng"}]],h=a("wheat",e);export{e as __iconNode,h as default};

langflow/frontend/assets/wheat-off-DYS9hXhF.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const e=[["path",{d:"m2 22 10-10",key:"28ilpk"}],["path",{d:"m16 8-1.17 1.17",key:"1qqm82"}],["path",{d:"M3.47 12.53 5 11l1.53 1.53a3.5 3.5 0 0 1 0 4.94L5 19l-1.53-1.53a3.5 3.5 0 0 1 0-4.94Z",key:"1rdhi6"}],["path",{d:"m8 8-.53.53a3.5 3.5 0 0 0 0 4.94L9 15l1.53-1.53c.55-.55.88-1.25.98-1.97",key:"4wz8re"}],["path",{d:"M10.91 5.26c.15-.26.34-.51.56-.73L13 3l1.53 1.53a3.5 3.5 0 0 1 .28 4.62",key:"rves66"}],["path",{d:"M20 2h2v2a4 4 0 0 1-4 4h-2V6a4 4 0 0 1 4-4Z",key:"19rau1"}],["path",{d:"M11.47 17.47 13 19l-1.53 1.53a3.5 3.5 0 0 1-4.94 0L5 19l1.53-1.53a3.5 3.5 0 0 1 4.94 0Z",key:"tc8ph9"}],["path",{d:"m16 16-.53.53a3.5 3.5 0 0 1-4.94 0L9 15l1.53-1.53a3.49 3.49 0 0 1 1.97-.98",key:"ak46r"}],["path",{d:"M18.74 13.09c.26-.15.51-.34.73-.56L21 11l-1.53-1.53a3.5 3.5 0 0 0-4.62-.28",key:"1tw520"}],["line",{x1:"2",x2:"22",y1:"2",y2:"22",key:"a6p6uj"}]],h=a("wheat-off",e);export{e as __iconNode,h as default};

langflow/frontend/assets/whole-word-BNq8lJGc.js

@@ -0,0 +1 @@
+import{a8 as c}from"./index-DSh-ifkJ.js";const e=[["circle",{cx:"7",cy:"12",r:"3",key:"12clwm"}],["path",{d:"M10 9v6",key:"17i7lo"}],["circle",{cx:"17",cy:"12",r:"3",key:"gl7c2s"}],["path",{d:"M14 7v8",key:"dl84cr"}],["path",{d:"M22 17v1c0 .5-.5 1-1 1H3c-.5 0-1-.5-1-1v-1",key:"lt2kga"}]],r=c("whole-word",e);export{e as __iconNode,r as default};

langflow/frontend/assets/wifi-CnrlDkRV.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const a=[["path",{d:"M12 20h.01",key:"zekei9"}],["path",{d:"M2 8.82a15 15 0 0 1 20 0",key:"dnpr2z"}],["path",{d:"M5 12.859a10 10 0 0 1 14 0",key:"1x1e6c"}],["path",{d:"M8.5 16.429a5 5 0 0 1 7 0",key:"1bycff"}]],c=e("wifi",a);export{a as __iconNode,c as default};

langflow/frontend/assets/wifi-high-DDovLlfl.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const a=[["path",{d:"M12 20h.01",key:"zekei9"}],["path",{d:"M5 12.859a10 10 0 0 1 14 0",key:"1x1e6c"}],["path",{d:"M8.5 16.429a5 5 0 0 1 7 0",key:"1bycff"}]],t=e("wifi-high",a);export{a as __iconNode,t as default};

langflow/frontend/assets/wifi-low-DUN9EheD.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const o=[["path",{d:"M12 20h.01",key:"zekei9"}],["path",{d:"M8.5 16.429a5 5 0 0 1 7 0",key:"1bycff"}]],i=e("wifi-low",o);export{o as __iconNode,i as default};

langflow/frontend/assets/wifi-off-PZ6WUot3.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const e=[["path",{d:"M12 20h.01",key:"zekei9"}],["path",{d:"M8.5 16.429a5 5 0 0 1 7 0",key:"1bycff"}],["path",{d:"M5 12.859a10 10 0 0 1 5.17-2.69",key:"1dl1wf"}],["path",{d:"M19 12.859a10 10 0 0 0-2.007-1.523",key:"4k23kn"}],["path",{d:"M2 8.82a15 15 0 0 1 4.177-2.643",key:"1grhjp"}],["path",{d:"M22 8.82a15 15 0 0 0-11.288-3.764",key:"z3jwby"}],["path",{d:"m2 2 20 20",key:"1ooewy"}]],d=a("wifi-off",e);export{e as __iconNode,d as default};

langflow/frontend/assets/wifi-pen-Cw6sCKDl.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const e=[["path",{d:"M2 8.82a15 15 0 0 1 20 0",key:"dnpr2z"}],["path",{d:"M21.378 16.626a1 1 0 0 0-3.004-3.004l-4.01 4.012a2 2 0 0 0-.506.854l-.837 2.87a.5.5 0 0 0 .62.62l2.87-.837a2 2 0 0 0 .854-.506z",key:"1817ys"}],["path",{d:"M5 12.859a10 10 0 0 1 10.5-2.222",key:"rpb7oy"}],["path",{d:"M8.5 16.429a5 5 0 0 1 3-1.406",key:"r8bmzl"}]],o=a("wifi-pen",e);export{e as __iconNode,o as default};

langflow/frontend/assets/wifi-zero-DE_6VpUL.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const o=[["path",{d:"M12 20h.01",key:"zekei9"}]],t=e("wifi-zero",o);export{o as __iconNode,t as default};

langflow/frontend/assets/wind-D_SE2NrY.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const e=[["path",{d:"M12.8 19.6A2 2 0 1 0 14 16H2",key:"148xed"}],["path",{d:"M17.5 8a2.5 2.5 0 1 1 2 4H2",key:"1u4tom"}],["path",{d:"M9.8 4.4A2 2 0 1 1 11 8H2",key:"75valh"}]],d=a("wind",e);export{e as __iconNode,d as default};

langflow/frontend/assets/wind-arrow-down-DI4RxNdn.js

@@ -0,0 +1 @@
+import{a8 as d}from"./index-DSh-ifkJ.js";const o=[["path",{d:"M10 2v8",key:"d4bbey"}],["path",{d:"M12.8 21.6A2 2 0 1 0 14 18H2",key:"19kp1d"}],["path",{d:"M17.5 10a2.5 2.5 0 1 1 2 4H2",key:"19kpjc"}],["path",{d:"m6 6 4 4 4-4",key:"k13n16"}]],e=d("wind-arrow-down",o);export{o as __iconNode,e as default};

langflow/frontend/assets/wine-DIqR9qUt.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const a=[["path",{d:"M8 22h8",key:"rmew8v"}],["path",{d:"M7 10h10",key:"1101jm"}],["path",{d:"M12 15v7",key:"t2xh3l"}],["path",{d:"M12 15a5 5 0 0 0 5-5c0-2-.5-4-2-8H9c-1.5 4-2 6-2 8a5 5 0 0 0 5 5Z",key:"10ffi3"}]],c=e("wine",a);export{a as __iconNode,c as default};

langflow/frontend/assets/wine-off-DnU2PqND.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const a=[["path",{d:"M8 22h8",key:"rmew8v"}],["path",{d:"M7 10h3m7 0h-1.343",key:"v48bem"}],["path",{d:"M12 15v7",key:"t2xh3l"}],["path",{d:"M7.307 7.307A12.33 12.33 0 0 0 7 10a5 5 0 0 0 7.391 4.391M8.638 2.981C8.75 2.668 8.872 2.34 9 2h6c1.5 4 2 6 2 8 0 .407-.05.809-.145 1.198",key:"1ymjlu"}],["line",{x1:"2",x2:"22",y1:"2",y2:"22",key:"a6p6uj"}]],h=e("wine-off",a);export{a as __iconNode,h as default};

langflow/frontend/assets/workflow-cSRl99U0.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const t=[["rect",{width:"8",height:"8",x:"3",y:"3",rx:"2",key:"by2w9f"}],["path",{d:"M7 11v4a2 2 0 0 0 2 2h4",key:"xkn7yn"}],["rect",{width:"8",height:"8",x:"13",y:"13",rx:"2",key:"1cgmvn"}]],r=e("workflow",t);export{t as __iconNode,r as default};

langflow/frontend/assets/worm-TU3YBA1G.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const o=[["path",{d:"m19 12-1.5 3",key:"9bcu4o"}],["path",{d:"M19.63 18.81 22 20",key:"121v98"}],["path",{d:"M6.47 8.23a1.68 1.68 0 0 1 2.44 1.93l-.64 2.08a6.76 6.76 0 0 0 10.16 7.67l.42-.27a1 1 0 1 0-2.73-4.21l-.42.27a1.76 1.76 0 0 1-2.63-1.99l.64-2.08A6.66 6.66 0 0 0 3.94 3.9l-.7.4a1 1 0 1 0 2.55 4.34z",key:"1tij6q"}]],e=a("worm",o);export{o as __iconNode,e as default};

langflow/frontend/assets/wrap-text-DSFkrQHi.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const t=[["line",{x1:"3",x2:"21",y1:"6",y2:"6",key:"4m8b97"}],["path",{d:"M3 12h15a3 3 0 1 1 0 6h-4",key:"1cl7v7"}],["polyline",{points:"16 16 14 18 16 20",key:"1jznyi"}],["line",{x1:"3",x2:"10",y1:"18",y2:"18",key:"1h33wv"}]],y=e("wrap-text",t);export{t as __iconNode,y as default};

langflow/frontend/assets/wrench-C7cxDioe.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const c=[["path",{d:"M14.7 6.3a1 1 0 0 0 0 1.4l1.6 1.6a1 1 0 0 0 1.4 0l3.77-3.77a6 6 0 0 1-7.94 7.94l-6.91 6.91a2.12 2.12 0 0 1-3-3l6.91-6.91a6 6 0 0 1 7.94-7.94l-3.76 3.76z",key:"cbrjhi"}]],o=a("wrench",c);export{c as __iconNode,o as default};

langflow/frontend/assets/youtube-CO3qTdR8.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const o=[["path",{d:"M2.5 17a24.12 24.12 0 0 1 0-10 2 2 0 0 1 1.4-1.4 49.56 49.56 0 0 1 16.2 0A2 2 0 0 1 21.5 7a24.12 24.12 0 0 1 0 10 2 2 0 0 1-1.4 1.4 49.55 49.55 0 0 1-16.2 0A2 2 0 0 1 2.5 17",key:"1q2vi4"}],["path",{d:"m10 15 5-3-5-3z",key:"1jp15x"}]],a=e("youtube",o);export{o as __iconNode,a as default};

langflow/frontend/assets/zap-K1SLM8iI.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const o=[["path",{d:"M4 14a1 1 0 0 1-.78-1.63l9.9-10.2a.5.5 0 0 1 .86.46l-1.92 6.02A1 1 0 0 0 13 10h7a1 1 0 0 1 .78 1.63l-9.9 10.2a.5.5 0 0 1-.86-.46l1.92-6.02A1 1 0 0 0 11 14z",key:"1xq2db"}]],t=a("zap",o);export{o as __iconNode,t as default};

langflow/frontend/assets/zap-off-DnGdiLUv.js

@@ -0,0 +1 @@
+import{a8 as a}from"./index-DSh-ifkJ.js";const e=[["path",{d:"M10.513 4.856 13.12 2.17a.5.5 0 0 1 .86.46l-1.377 4.317",key:"193nxd"}],["path",{d:"M15.656 10H20a1 1 0 0 1 .78 1.63l-1.72 1.773",key:"27a7lr"}],["path",{d:"M16.273 16.273 10.88 21.83a.5.5 0 0 1-.86-.46l1.92-6.02A1 1 0 0 0 11 14H4a1 1 0 0 1-.78-1.63l4.507-4.643",key:"1e0qe9"}],["path",{d:"m2 2 20 20",key:"1ooewy"}]],t=a("zap-off",e);export{e as __iconNode,t as default};

langflow/frontend/assets/zoom-in-CmWlo1tn.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const o=[["circle",{cx:"11",cy:"11",r:"8",key:"4ej97u"}],["line",{x1:"21",x2:"16.65",y1:"21",y2:"16.65",key:"13gj7c"}],["line",{x1:"11",x2:"11",y1:"8",y2:"14",key:"1vmskp"}],["line",{x1:"8",x2:"14",y1:"11",y2:"11",key:"durymu"}]],c=e("zoom-in",o);export{o as __iconNode,c as default};

langflow/frontend/assets/zoom-out-CIsBOJZa.js

@@ -0,0 +1 @@
+import{a8 as e}from"./index-DSh-ifkJ.js";const o=[["circle",{cx:"11",cy:"11",r:"8",key:"4ej97u"}],["line",{x1:"21",x2:"16.65",y1:"21",y2:"16.65",key:"13gj7c"}],["line",{x1:"8",x2:"14",y1:"11",y2:"11",key:"durymu"}]],y=e("zoom-out",o);export{o as __iconNode,y as default};

langflow/frontend/index.html

@@ -14,8 +14,8 @@
       rel="stylesheet"
     />
     <title>Langflow</title>
-    <script type="module" crossorigin src="./assets/index-aLOJ61at.js"></script>
-    <link rel="stylesheet" crossorigin href="./assets/index-BvSy8f-Z.css">
+    <script type="module" crossorigin src="./assets/index-DSh-ifkJ.js"></script>
+    <link rel="stylesheet" crossorigin href="./assets/index-BB4Qrl-z.css">
   </head>
   <body id="body" class="dark" style="width: 100%; height: 100%">
     <noscript>You need to enable JavaScript to run this app.</noscript>

langflow/initial_setup/starter_projects/Basic Prompting.json

@@ -1049,7 +1049,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        # Get current model value - from field_value if model is being changed, otherwise from build_config\n        current_model_value = field_value if field_name == \"model\" else build_config.get(\"model\", {}).get(\"value\")\n        if isinstance(current_model_value, list) and len(current_model_value) > 0:\n            selected_model = current_model_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
               "input_value": {
                 "_input_type": "MessageInput",

langflow/initial_setup/starter_projects/Blog Writer.json

@@ -1018,7 +1018,7 @@
             "legacy": false,
             "lf_version": "1.4.2",
             "metadata": {
-              "code_hash": "47d3ccb92d71",
+              "code_hash": "f773f55e3820",
               "dependencies": {
                 "dependencies": [
                   {
@@ -1033,12 +1033,16 @@
                     "name": "langchain_community",
                     "version": "0.3.21"
                   },
+                  {
+                    "name": "markitdown",
+                    "version": "0.1.4"
+                  },
                   {
                     "name": "lfx",
                     "version": null
                   }
                 ],
-                "total_dependencies": 4
+                "total_dependencies": 5
               },
               "module": "lfx.components.data_source.url.URLComponent"
             },
@@ -1130,7 +1134,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import importlib\nimport re\n\nimport requests\nfrom bs4 import BeautifulSoup\nfrom langchain_community.document_loaders import RecursiveUrlLoader\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.helpers.data import safe_convert\nfrom lfx.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SliderInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.utils.request_utils import get_user_agent\n\n# Constants\nDEFAULT_TIMEOUT = 30\nDEFAULT_MAX_DEPTH = 1\nDEFAULT_FORMAT = \"Text\"\n\n\nURL_REGEX = re.compile(\n    r\"^(https?:\\/\\/)?\" r\"(www\\.)?\" r\"([a-zA-Z0-9.-]+)\" r\"(\\.[a-zA-Z]{2,})?\" r\"(:\\d+)?\" r\"(\\/[^\\s]*)?$\",\n    re.IGNORECASE,\n)\n\nUSER_AGENT = None\n# Check if langflow is installed using importlib.util.find_spec(name))\nif importlib.util.find_spec(\"langflow\"):\n    langflow_installed = True\n    USER_AGENT = get_user_agent()\nelse:\n    langflow_installed = False\n    USER_AGENT = \"lfx\"\n\n\nclass URLComponent(Component):\n    \"\"\"A component that loads and parses content from web pages recursively.\n\n    This component allows fetching content from one or more URLs, with options to:\n    - Control crawl depth\n    - Prevent crawling outside the root domain\n    - Use async loading for better performance\n    - Extract either raw HTML or clean text\n    - Configure request headers and timeouts\n    \"\"\"\n\n    display_name = \"URL\"\n    description = \"Fetch content from one or more web pages, following links recursively.\"\n    documentation: str = \"https://docs.langflow.org/url\"\n    icon = \"layout-template\"\n    name = \"URLComponent\"\n\n    inputs = [\n        MessageTextInput(\n            name=\"urls\",\n            display_name=\"URLs\",\n            info=\"Enter one or more URLs to crawl recursively, by clicking the '+' button.\",\n            is_list=True,\n            tool_mode=True,\n            placeholder=\"Enter a URL...\",\n            list_add_label=\"Add URL\",\n            input_types=[],\n        ),\n        SliderInput(\n            name=\"max_depth\",\n            display_name=\"Depth\",\n            info=(\n                \"Controls how many 'clicks' away from the initial page the crawler will go:\\n\"\n                \"- depth 1: only the initial page\\n\"\n                \"- depth 2: initial page + all pages linked directly from it\\n\"\n                \"- depth 3: initial page + direct links + links found on those direct link pages\\n\"\n                \"Note: This is about link traversal, not URL path depth.\"\n            ),\n            value=DEFAULT_MAX_DEPTH,\n            range_spec=RangeSpec(min=1, max=5, step=1),\n            required=False,\n            min_label=\" \",\n            max_label=\" \",\n            min_label_icon=\"None\",\n            max_label_icon=\"None\",\n            # slider_input=True\n        ),\n        BoolInput(\n            name=\"prevent_outside\",\n            display_name=\"Prevent Outside\",\n            info=(\n                \"If enabled, only crawls URLs within the same domain as the root URL. \"\n                \"This helps prevent the crawler from going to external websites.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"use_async\",\n            display_name=\"Use Async\",\n            info=(\n                \"If enabled, uses asynchronous loading which can be significantly faster \"\n                \"but might use more system resources.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"format\",\n            display_name=\"Output Format\",\n            info=\"Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.\",\n            options=[\"Text\", \"HTML\"],\n            value=DEFAULT_FORMAT,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"timeout\",\n            display_name=\"Timeout\",\n            info=\"Timeout for the request in seconds.\",\n            value=DEFAULT_TIMEOUT,\n            required=False,\n            advanced=True,\n        ),\n        TableInput(\n            name=\"headers\",\n            display_name=\"Headers\",\n            info=\"The headers to send with the request\",\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Header\",\n                    \"type\": \"str\",\n                    \"description\": \"Header name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Header value\",\n                },\n            ],\n            value=[{\"key\": \"User-Agent\", \"value\": USER_AGENT}],\n            advanced=True,\n            input_types=[\"DataFrame\"],\n        ),\n        BoolInput(\n            name=\"filter_text_html\",\n            display_name=\"Filter Text/HTML\",\n            info=\"If enabled, filters out text/css content type from the results.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"continue_on_failure\",\n            display_name=\"Continue on Failure\",\n            info=\"If enabled, continues crawling even if some requests fail.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"check_response_status\",\n            display_name=\"Check Response Status\",\n            info=\"If enabled, checks the response status of the request.\",\n            value=False,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autoset_encoding\",\n            display_name=\"Autoset Encoding\",\n            info=\"If enabled, automatically sets the encoding of the request.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Extracted Pages\", name=\"page_results\", method=\"fetch_content\"),\n        Output(display_name=\"Raw Content\", name=\"raw_results\", method=\"fetch_content_as_message\", tool_mode=False),\n    ]\n\n    @staticmethod\n    def validate_url(url: str) -> bool:\n        \"\"\"Validates if the given string matches URL pattern.\n\n        Args:\n            url: The URL string to validate\n\n        Returns:\n            bool: True if the URL is valid, False otherwise\n        \"\"\"\n        return bool(URL_REGEX.match(url))\n\n    def ensure_url(self, url: str) -> str:\n        \"\"\"Ensures the given string is a valid URL.\n\n        Args:\n            url: The URL string to validate and normalize\n\n        Returns:\n            str: The normalized URL\n\n        Raises:\n            ValueError: If the URL is invalid\n        \"\"\"\n        url = url.strip()\n        if not url.startswith((\"http://\", \"https://\")):\n            url = \"https://\" + url\n\n        if not self.validate_url(url):\n            msg = f\"Invalid URL: {url}\"\n            raise ValueError(msg)\n\n        return url\n\n    def _create_loader(self, url: str) -> RecursiveUrlLoader:\n        \"\"\"Creates a RecursiveUrlLoader instance with the configured settings.\n\n        Args:\n            url: The URL to load\n\n        Returns:\n            RecursiveUrlLoader: Configured loader instance\n        \"\"\"\n        headers_dict = {header[\"key\"]: header[\"value\"] for header in self.headers if header[\"value\"] is not None}\n        extractor = (lambda x: x) if self.format == \"HTML\" else (lambda x: BeautifulSoup(x, \"lxml\").get_text())\n\n        return RecursiveUrlLoader(\n            url=url,\n            max_depth=self.max_depth,\n            prevent_outside=self.prevent_outside,\n            use_async=self.use_async,\n            extractor=extractor,\n            timeout=self.timeout,\n            headers=headers_dict,\n            check_response_status=self.check_response_status,\n            continue_on_failure=self.continue_on_failure,\n            base_url=url,  # Add base_url to ensure consistent domain crawling\n            autoset_encoding=self.autoset_encoding,  # Enable automatic encoding detection\n            exclude_dirs=[],  # Allow customization of excluded directories\n            link_regex=None,  # Allow customization of link filtering\n        )\n\n    def fetch_url_contents(self) -> list[dict]:\n        \"\"\"Load documents from the configured URLs.\n\n        Returns:\n            List[Data]: List of Data objects containing the fetched content\n\n        Raises:\n            ValueError: If no valid URLs are provided or if there's an error loading documents\n        \"\"\"\n        try:\n            urls = list({self.ensure_url(url) for url in self.urls if url.strip()})\n            logger.debug(f\"URLs: {urls}\")\n            if not urls:\n                msg = \"No valid URLs provided.\"\n                raise ValueError(msg)\n\n            all_docs = []\n            for url in urls:\n                logger.debug(f\"Loading documents from {url}\")\n\n                try:\n                    loader = self._create_loader(url)\n                    docs = loader.load()\n\n                    if not docs:\n                        logger.warning(f\"No documents found for {url}\")\n                        continue\n\n                    logger.debug(f\"Found {len(docs)} documents from {url}\")\n                    all_docs.extend(docs)\n\n                except requests.exceptions.RequestException as e:\n                    logger.exception(f\"Error loading documents from {url}: {e}\")\n                    continue\n\n            if not all_docs:\n                msg = \"No documents were successfully loaded from any URL\"\n                raise ValueError(msg)\n\n            # data = [Data(text=doc.page_content, **doc.metadata) for doc in all_docs]\n            data = [\n                {\n                    \"text\": safe_convert(doc.page_content, clean_data=True),\n                    \"url\": doc.metadata.get(\"source\", \"\"),\n                    \"title\": doc.metadata.get(\"title\", \"\"),\n                    \"description\": doc.metadata.get(\"description\", \"\"),\n                    \"content_type\": doc.metadata.get(\"content_type\", \"\"),\n                    \"language\": doc.metadata.get(\"language\", \"\"),\n                }\n                for doc in all_docs\n            ]\n        except Exception as e:\n            error_msg = e.message if hasattr(e, \"message\") else e\n            msg = f\"Error loading documents: {error_msg!s}\"\n            logger.exception(msg)\n            raise ValueError(msg) from e\n        return data\n\n    def fetch_content(self) -> DataFrame:\n        \"\"\"Convert the documents to a DataFrame.\"\"\"\n        return DataFrame(data=self.fetch_url_contents())\n\n    def fetch_content_as_message(self) -> Message:\n        \"\"\"Convert the documents to a Message.\"\"\"\n        url_contents = self.fetch_url_contents()\n        return Message(text=\"\\n\\n\".join([x[\"text\"] for x in url_contents]), data={\"data\": url_contents})\n"
+                "value": "import importlib\nimport io\nimport re\n\nimport requests\nfrom bs4 import BeautifulSoup\nfrom langchain_community.document_loaders import RecursiveUrlLoader\nfrom markitdown import MarkItDown\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.helpers.data import safe_convert\nfrom lfx.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SliderInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.utils.request_utils import get_user_agent\n\n# Constants\nDEFAULT_TIMEOUT = 30\nDEFAULT_MAX_DEPTH = 1\nDEFAULT_FORMAT = \"Text\"\n\n\nURL_REGEX = re.compile(\n    r\"^(https?:\\/\\/)?\" r\"(www\\.)?\" r\"([a-zA-Z0-9.-]+)\" r\"(\\.[a-zA-Z]{2,})?\" r\"(:\\d+)?\" r\"(\\/[^\\s]*)?$\",\n    re.IGNORECASE,\n)\n\nUSER_AGENT = None\n# Check if langflow is installed using importlib.util.find_spec(name))\nif importlib.util.find_spec(\"langflow\"):\n    langflow_installed = True\n    USER_AGENT = get_user_agent()\nelse:\n    langflow_installed = False\n    USER_AGENT = \"lfx\"\n\n\nclass URLComponent(Component):\n    \"\"\"A component that loads and parses content from web pages recursively.\n\n    This component allows fetching content from one or more URLs, with options to:\n    - Control crawl depth\n    - Prevent crawling outside the root domain\n    - Use async loading for better performance\n    - Extract either raw HTML or clean text\n    - Configure request headers and timeouts\n    \"\"\"\n\n    display_name = \"URL\"\n    description = \"Fetch content from one or more web pages, following links recursively.\"\n    documentation: str = \"https://docs.langflow.org/url\"\n    icon = \"layout-template\"\n    name = \"URLComponent\"\n\n    inputs = [\n        MessageTextInput(\n            name=\"urls\",\n            display_name=\"URLs\",\n            info=\"Enter one or more URLs to crawl recursively, by clicking the '+' button.\",\n            is_list=True,\n            tool_mode=True,\n            placeholder=\"Enter a URL...\",\n            list_add_label=\"Add URL\",\n            input_types=[],\n        ),\n        SliderInput(\n            name=\"max_depth\",\n            display_name=\"Depth\",\n            info=(\n                \"Controls how many 'clicks' away from the initial page the crawler will go:\\n\"\n                \"- depth 1: only the initial page\\n\"\n                \"- depth 2: initial page + all pages linked directly from it\\n\"\n                \"- depth 3: initial page + direct links + links found on those direct link pages\\n\"\n                \"Note: This is about link traversal, not URL path depth.\"\n            ),\n            value=DEFAULT_MAX_DEPTH,\n            range_spec=RangeSpec(min=1, max=5, step=1),\n            required=False,\n            min_label=\" \",\n            max_label=\" \",\n            min_label_icon=\"None\",\n            max_label_icon=\"None\",\n            # slider_input=True\n        ),\n        BoolInput(\n            name=\"prevent_outside\",\n            display_name=\"Prevent Outside\",\n            info=(\n                \"If enabled, only crawls URLs within the same domain as the root URL. \"\n                \"This helps prevent the crawler from going to external websites.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"use_async\",\n            display_name=\"Use Async\",\n            info=(\n                \"If enabled, uses asynchronous loading which can be significantly faster \"\n                \"but might use more system resources.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"format\",\n            display_name=\"Output Format\",\n            info=(\n                \"Output Format. Use 'Text' to extract the text from the HTML, \"\n                \"'Markdown' to parse the HTML into Markdown format, or 'HTML' \"\n                \"for the raw HTML content.\"\n            ),\n            options=[\"Text\", \"HTML\", \"Markdown\"],\n            value=DEFAULT_FORMAT,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"timeout\",\n            display_name=\"Timeout\",\n            info=\"Timeout for the request in seconds.\",\n            value=DEFAULT_TIMEOUT,\n            required=False,\n            advanced=True,\n        ),\n        TableInput(\n            name=\"headers\",\n            display_name=\"Headers\",\n            info=\"The headers to send with the request\",\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Header\",\n                    \"type\": \"str\",\n                    \"description\": \"Header name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Header value\",\n                },\n            ],\n            value=[{\"key\": \"User-Agent\", \"value\": USER_AGENT}],\n            advanced=True,\n            input_types=[\"DataFrame\"],\n        ),\n        BoolInput(\n            name=\"filter_text_html\",\n            display_name=\"Filter Text/HTML\",\n            info=\"If enabled, filters out text/css content type from the results.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"continue_on_failure\",\n            display_name=\"Continue on Failure\",\n            info=\"If enabled, continues crawling even if some requests fail.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"check_response_status\",\n            display_name=\"Check Response Status\",\n            info=\"If enabled, checks the response status of the request.\",\n            value=False,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autoset_encoding\",\n            display_name=\"Autoset Encoding\",\n            info=\"If enabled, automatically sets the encoding of the request.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Extracted Pages\", name=\"page_results\", method=\"fetch_content\"),\n        Output(display_name=\"Raw Content\", name=\"raw_results\", method=\"fetch_content_as_message\", tool_mode=False),\n    ]\n\n    @staticmethod\n    def _html_extractor(x: str) -> str:\n        \"\"\"Extract raw HTML content.\"\"\"\n        return x\n\n    @staticmethod\n    def _text_extractor(x: str) -> str:\n        \"\"\"Extract clean text from HTML.\"\"\"\n        return BeautifulSoup(x, \"lxml\").get_text()\n\n    @staticmethod\n    def _markdown_extractor(x: str) -> str:\n        \"\"\"Convert HTML to Markdown format.\"\"\"\n        stream = io.BytesIO(x.encode(\"utf-8\"))\n        result = MarkItDown(enable_plugins=False).convert_stream(stream)\n        return result.markdown\n\n    @staticmethod\n    def validate_url(url: str) -> bool:\n        \"\"\"Validates if the given string matches URL pattern.\n\n        Args:\n            url: The URL string to validate\n\n        Returns:\n            bool: True if the URL is valid, False otherwise\n        \"\"\"\n        return bool(URL_REGEX.match(url))\n\n    def ensure_url(self, url: str) -> str:\n        \"\"\"Ensures the given string is a valid URL.\n\n        Args:\n            url: The URL string to validate and normalize\n\n        Returns:\n            str: The normalized URL\n\n        Raises:\n            ValueError: If the URL is invalid\n        \"\"\"\n        url = url.strip()\n        if not url.startswith((\"http://\", \"https://\")):\n            url = \"https://\" + url\n\n        if not self.validate_url(url):\n            msg = f\"Invalid URL: {url}\"\n            raise ValueError(msg)\n\n        return url\n\n    def _create_loader(self, url: str) -> RecursiveUrlLoader:\n        \"\"\"Creates a RecursiveUrlLoader instance with the configured settings.\n\n        Args:\n            url: The URL to load\n\n        Returns:\n            RecursiveUrlLoader: Configured loader instance\n        \"\"\"\n        headers_dict = {header[\"key\"]: header[\"value\"] for header in self.headers if header[\"value\"] is not None}\n        extractors = {\n            \"HTML\": self._html_extractor,\n            \"Markdown\": self._markdown_extractor,\n            \"Text\": self._text_extractor,\n        }\n        extractor = extractors.get(self.format, self._text_extractor)\n\n        return RecursiveUrlLoader(\n            url=url,\n            max_depth=self.max_depth,\n            prevent_outside=self.prevent_outside,\n            use_async=self.use_async,\n            extractor=extractor,\n            timeout=self.timeout,\n            headers=headers_dict,\n            check_response_status=self.check_response_status,\n            continue_on_failure=self.continue_on_failure,\n            base_url=url,  # Add base_url to ensure consistent domain crawling\n            autoset_encoding=self.autoset_encoding,  # Enable automatic encoding detection\n            exclude_dirs=[],  # Allow customization of excluded directories\n            link_regex=None,  # Allow customization of link filtering\n        )\n\n    def fetch_url_contents(self) -> list[dict]:\n        \"\"\"Load documents from the configured URLs.\n\n        Returns:\n            List[Data]: List of Data objects containing the fetched content\n\n        Raises:\n            ValueError: If no valid URLs are provided or if there's an error loading documents\n        \"\"\"\n        try:\n            urls = list({self.ensure_url(url) for url in self.urls if url.strip()})\n            logger.debug(f\"URLs: {urls}\")\n            if not urls:\n                msg = \"No valid URLs provided.\"\n                raise ValueError(msg)\n\n            all_docs = []\n            for url in urls:\n                logger.debug(f\"Loading documents from {url}\")\n\n                try:\n                    loader = self._create_loader(url)\n                    docs = loader.load()\n\n                    if not docs:\n                        logger.warning(f\"No documents found for {url}\")\n                        continue\n\n                    logger.debug(f\"Found {len(docs)} documents from {url}\")\n                    all_docs.extend(docs)\n\n                except requests.exceptions.RequestException as e:\n                    logger.exception(f\"Error loading documents from {url}: {e}\")\n                    continue\n\n            if not all_docs:\n                msg = \"No documents were successfully loaded from any URL\"\n                raise ValueError(msg)\n\n            # data = [Data(text=doc.page_content, **doc.metadata) for doc in all_docs]\n            data = [\n                {\n                    \"text\": safe_convert(doc.page_content, clean_data=True),\n                    \"url\": doc.metadata.get(\"source\", \"\"),\n                    \"title\": doc.metadata.get(\"title\", \"\"),\n                    \"description\": doc.metadata.get(\"description\", \"\"),\n                    \"content_type\": doc.metadata.get(\"content_type\", \"\"),\n                    \"language\": doc.metadata.get(\"language\", \"\"),\n                }\n                for doc in all_docs\n            ]\n        except Exception as e:\n            error_msg = e.message if hasattr(e, \"message\") else e\n            msg = f\"Error loading documents: {error_msg!s}\"\n            logger.exception(msg)\n            raise ValueError(msg) from e\n        return data\n\n    def fetch_content(self) -> DataFrame:\n        \"\"\"Convert the documents to a DataFrame.\"\"\"\n        return DataFrame(data=self.fetch_url_contents())\n\n    def fetch_content_as_message(self) -> Message:\n        \"\"\"Convert the documents to a Message.\"\"\"\n        url_contents = self.fetch_url_contents()\n        return Message(text=\"\\n\\n\".join([x[\"text\"] for x in url_contents]), data={\"data\": url_contents})\n"
               },
               "continue_on_failure": {
                 "_input_type": "BoolInput",
@@ -1175,11 +1179,12 @@
                 "dialog_inputs": {},
                 "display_name": "Output Format",
                 "dynamic": false,
-                "info": "Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.",
+                "info": "Output Format. Use 'Text' to extract the text from the HTML, 'Markdown' to parse the HTML into Markdown format, or 'HTML' for the raw HTML content.",
                 "name": "format",
                 "options": [
                   "Text",
-                  "HTML"
+                  "HTML",
+                  "Markdown"
                 ],
                 "options_metadata": [],
                 "placeholder": "",
@@ -1542,7 +1547,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        # Get current model value - from field_value if model is being changed, otherwise from build_config\n        current_model_value = field_value if field_name == \"model\" else build_config.get(\"model\", {}).get(\"value\")\n        if isinstance(current_model_value, list) and len(current_model_value) > 0:\n            selected_model = current_model_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
               "input_value": {
                 "_input_type": "MessageInput",

langflow/initial_setup/starter_projects/Custom Component Generator.json

@@ -2696,7 +2696,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        # Get current model value - from field_value if model is being changed, otherwise from build_config\n        current_model_value = field_value if field_name == \"model\" else build_config.get(\"model\", {}).get(\"value\")\n        if isinstance(current_model_value, list) and len(current_model_value) > 0:\n            selected_model = current_model_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
               "input_value": {
                 "_input_type": "MessageInput",

langflow/initial_setup/starter_projects/Document Q&A.json

@@ -1067,7 +1067,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        # Get current model value - from field_value if model is being changed, otherwise from build_config\n        current_model_value = field_value if field_name == \"model\" else build_config.get(\"model\", {}).get(\"value\")\n        if isinstance(current_model_value, list) and len(current_model_value) > 0:\n            selected_model = current_model_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
               "input_value": {
                 "_input_type": "MessageInput",

langflow/initial_setup/starter_projects/Image Sentiment Analysis.json

@@ -1723,7 +1723,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        # Get current model value - from field_value if model is being changed, otherwise from build_config\n        current_model_value = field_value if field_name == \"model\" else build_config.get(\"model\", {}).get(\"value\")\n        if isinstance(current_model_value, list) and len(current_model_value) > 0:\n            selected_model = current_model_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
               "input_value": {
                 "_input_type": "MessageInput",

langflow/initial_setup/starter_projects/Instagram Copywriter.json

@@ -2723,7 +2723,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        # Get current model value - from field_value if model is being changed, otherwise from build_config\n        current_model_value = field_value if field_name == \"model\" else build_config.get(\"model\", {}).get(\"value\")\n        if isinstance(current_model_value, list) and len(current_model_value) > 0:\n            selected_model = current_model_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
               "input_value": {
                 "_input_type": "MessageInput",
@@ -3100,7 +3100,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        if field_name == \"model\" and isinstance(field_value, list) and len(field_value) > 0:\n            selected_model = field_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
+                "value": "from lfx.base.models.model import LCModelComponent\nfrom lfx.base.models.unified_models import (\n    get_language_model_options,\n    get_llm,\n    update_model_options_in_build_config,\n)\nfrom lfx.base.models.watsonx_constants import IBM_WATSONX_URLS\nfrom lfx.field_typing import LanguageModel\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.inputs.inputs import BoolInput, DropdownInput, StrInput\nfrom lfx.io import MessageInput, ModelInput, MultilineInput, SecretStrInput, SliderInput\n\nDEFAULT_OLLAMA_URL = \"http://localhost:11434\"\n\n\nclass LanguageModelComponent(LCModelComponent):\n    display_name = \"Language Model\"\n    description = \"Runs a language model given a specified provider.\"\n    documentation: str = \"https://docs.langflow.org/components-models\"\n    icon = \"brain-circuit\"\n    category = \"models\"\n    priority = 0  # Set priority to 0 to make it appear first\n\n    inputs = [\n        ModelInput(\n            name=\"model\",\n            display_name=\"Language Model\",\n            info=\"Select your model provider\",\n            real_time_refresh=True,\n            required=True,\n        ),\n        SecretStrInput(\n            name=\"api_key\",\n            display_name=\"API Key\",\n            info=\"Model Provider API key\",\n            required=False,\n            show=True,\n            real_time_refresh=True,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"base_url_ibm_watsonx\",\n            display_name=\"watsonx API Endpoint\",\n            info=\"The base URL of the API (IBM watsonx.ai only)\",\n            options=IBM_WATSONX_URLS,\n            value=IBM_WATSONX_URLS[0],\n            show=False,\n            real_time_refresh=True,\n        ),\n        StrInput(\n            name=\"project_id\",\n            display_name=\"watsonx Project ID\",\n            info=\"The project ID associated with the foundation model (IBM watsonx.ai only)\",\n            show=False,\n            required=False,\n        ),\n        MessageInput(\n            name=\"ollama_base_url\",\n            display_name=\"Ollama API URL\",\n            info=f\"Endpoint of the Ollama API (Ollama only). Defaults to {DEFAULT_OLLAMA_URL}\",\n            value=DEFAULT_OLLAMA_URL,\n            show=False,\n            real_time_refresh=True,\n            load_from_db=True,\n        ),\n        MessageInput(\n            name=\"input_value\",\n            display_name=\"Input\",\n            info=\"The input text to send to the model\",\n        ),\n        MultilineInput(\n            name=\"system_message\",\n            display_name=\"System Message\",\n            info=\"A system message that helps set the behavior of the assistant\",\n            advanced=False,\n        ),\n        BoolInput(\n            name=\"stream\",\n            display_name=\"Stream\",\n            info=\"Whether to stream the response\",\n            value=False,\n            advanced=True,\n        ),\n        SliderInput(\n            name=\"temperature\",\n            display_name=\"Temperature\",\n            value=0.1,\n            info=\"Controls randomness in responses\",\n            range_spec=RangeSpec(min=0, max=1, step=0.01),\n            advanced=True,\n        ),\n    ]\n\n    def build_model(self) -> LanguageModel:\n        return get_llm(\n            model=self.model,\n            user_id=self.user_id,\n            api_key=self.api_key,\n            temperature=self.temperature,\n            stream=self.stream,\n            watsonx_url=getattr(self, \"base_url_ibm_watsonx\", None),\n            watsonx_project_id=getattr(self, \"project_id\", None),\n            ollama_base_url=getattr(self, \"ollama_base_url\", None),\n        )\n\n    def update_build_config(self, build_config: dict, field_value: str, field_name: str | None = None):\n        \"\"\"Dynamically update build config with user-filtered model options.\"\"\"\n        # Update model options\n        build_config = update_model_options_in_build_config(\n            component=self,\n            build_config=build_config,\n            cache_key_prefix=\"language_model_options\",\n            get_options_func=get_language_model_options,\n            field_name=field_name,\n            field_value=field_value,\n        )\n\n        # Show/hide provider-specific fields based on selected model\n        # Get current model value - from field_value if model is being changed, otherwise from build_config\n        current_model_value = field_value if field_name == \"model\" else build_config.get(\"model\", {}).get(\"value\")\n        if isinstance(current_model_value, list) and len(current_model_value) > 0:\n            selected_model = current_model_value[0]\n            provider = selected_model.get(\"provider\", \"\")\n\n            # Show/hide watsonx fields\n            is_watsonx = provider == \"IBM WatsonX\"\n            build_config[\"base_url_ibm_watsonx\"][\"show\"] = is_watsonx\n            build_config[\"project_id\"][\"show\"] = is_watsonx\n            build_config[\"base_url_ibm_watsonx\"][\"required\"] = is_watsonx\n            build_config[\"project_id\"][\"required\"] = is_watsonx\n\n            # Show/hide Ollama fields\n            is_ollama = provider == \"Ollama\"\n            build_config[\"ollama_base_url\"][\"show\"] = is_ollama\n\n        return build_config\n"
               },
               "input_value": {
                 "_input_type": "MessageInput",

langflow/initial_setup/starter_projects/Knowledge Ingestion.json

@@ -353,7 +353,7 @@
             "legacy": false,
             "lf_version": "1.5.0.post1",
             "metadata": {
-              "code_hash": "47d3ccb92d71",
+              "code_hash": "f773f55e3820",
               "dependencies": {
                 "dependencies": [
                   {
@@ -368,12 +368,16 @@
                     "name": "langchain_community",
                     "version": "0.3.21"
                   },
+                  {
+                    "name": "markitdown",
+                    "version": "0.1.4"
+                  },
                   {
                     "name": "lfx",
                     "version": null
                   }
                 ],
-                "total_dependencies": 4
+                "total_dependencies": 5
               },
               "module": "lfx.components.data_source.url.URLComponent"
             },
@@ -464,7 +468,7 @@
                 "show": true,
                 "title_case": false,
                 "type": "code",
-                "value": "import importlib\nimport re\n\nimport requests\nfrom bs4 import BeautifulSoup\nfrom langchain_community.document_loaders import RecursiveUrlLoader\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.helpers.data import safe_convert\nfrom lfx.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SliderInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.utils.request_utils import get_user_agent\n\n# Constants\nDEFAULT_TIMEOUT = 30\nDEFAULT_MAX_DEPTH = 1\nDEFAULT_FORMAT = \"Text\"\n\n\nURL_REGEX = re.compile(\n    r\"^(https?:\\/\\/)?\" r\"(www\\.)?\" r\"([a-zA-Z0-9.-]+)\" r\"(\\.[a-zA-Z]{2,})?\" r\"(:\\d+)?\" r\"(\\/[^\\s]*)?$\",\n    re.IGNORECASE,\n)\n\nUSER_AGENT = None\n# Check if langflow is installed using importlib.util.find_spec(name))\nif importlib.util.find_spec(\"langflow\"):\n    langflow_installed = True\n    USER_AGENT = get_user_agent()\nelse:\n    langflow_installed = False\n    USER_AGENT = \"lfx\"\n\n\nclass URLComponent(Component):\n    \"\"\"A component that loads and parses content from web pages recursively.\n\n    This component allows fetching content from one or more URLs, with options to:\n    - Control crawl depth\n    - Prevent crawling outside the root domain\n    - Use async loading for better performance\n    - Extract either raw HTML or clean text\n    - Configure request headers and timeouts\n    \"\"\"\n\n    display_name = \"URL\"\n    description = \"Fetch content from one or more web pages, following links recursively.\"\n    documentation: str = \"https://docs.langflow.org/url\"\n    icon = \"layout-template\"\n    name = \"URLComponent\"\n\n    inputs = [\n        MessageTextInput(\n            name=\"urls\",\n            display_name=\"URLs\",\n            info=\"Enter one or more URLs to crawl recursively, by clicking the '+' button.\",\n            is_list=True,\n            tool_mode=True,\n            placeholder=\"Enter a URL...\",\n            list_add_label=\"Add URL\",\n            input_types=[],\n        ),\n        SliderInput(\n            name=\"max_depth\",\n            display_name=\"Depth\",\n            info=(\n                \"Controls how many 'clicks' away from the initial page the crawler will go:\\n\"\n                \"- depth 1: only the initial page\\n\"\n                \"- depth 2: initial page + all pages linked directly from it\\n\"\n                \"- depth 3: initial page + direct links + links found on those direct link pages\\n\"\n                \"Note: This is about link traversal, not URL path depth.\"\n            ),\n            value=DEFAULT_MAX_DEPTH,\n            range_spec=RangeSpec(min=1, max=5, step=1),\n            required=False,\n            min_label=\" \",\n            max_label=\" \",\n            min_label_icon=\"None\",\n            max_label_icon=\"None\",\n            # slider_input=True\n        ),\n        BoolInput(\n            name=\"prevent_outside\",\n            display_name=\"Prevent Outside\",\n            info=(\n                \"If enabled, only crawls URLs within the same domain as the root URL. \"\n                \"This helps prevent the crawler from going to external websites.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"use_async\",\n            display_name=\"Use Async\",\n            info=(\n                \"If enabled, uses asynchronous loading which can be significantly faster \"\n                \"but might use more system resources.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"format\",\n            display_name=\"Output Format\",\n            info=\"Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.\",\n            options=[\"Text\", \"HTML\"],\n            value=DEFAULT_FORMAT,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"timeout\",\n            display_name=\"Timeout\",\n            info=\"Timeout for the request in seconds.\",\n            value=DEFAULT_TIMEOUT,\n            required=False,\n            advanced=True,\n        ),\n        TableInput(\n            name=\"headers\",\n            display_name=\"Headers\",\n            info=\"The headers to send with the request\",\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Header\",\n                    \"type\": \"str\",\n                    \"description\": \"Header name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Header value\",\n                },\n            ],\n            value=[{\"key\": \"User-Agent\", \"value\": USER_AGENT}],\n            advanced=True,\n            input_types=[\"DataFrame\"],\n        ),\n        BoolInput(\n            name=\"filter_text_html\",\n            display_name=\"Filter Text/HTML\",\n            info=\"If enabled, filters out text/css content type from the results.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"continue_on_failure\",\n            display_name=\"Continue on Failure\",\n            info=\"If enabled, continues crawling even if some requests fail.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"check_response_status\",\n            display_name=\"Check Response Status\",\n            info=\"If enabled, checks the response status of the request.\",\n            value=False,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autoset_encoding\",\n            display_name=\"Autoset Encoding\",\n            info=\"If enabled, automatically sets the encoding of the request.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Extracted Pages\", name=\"page_results\", method=\"fetch_content\"),\n        Output(display_name=\"Raw Content\", name=\"raw_results\", method=\"fetch_content_as_message\", tool_mode=False),\n    ]\n\n    @staticmethod\n    def validate_url(url: str) -> bool:\n        \"\"\"Validates if the given string matches URL pattern.\n\n        Args:\n            url: The URL string to validate\n\n        Returns:\n            bool: True if the URL is valid, False otherwise\n        \"\"\"\n        return bool(URL_REGEX.match(url))\n\n    def ensure_url(self, url: str) -> str:\n        \"\"\"Ensures the given string is a valid URL.\n\n        Args:\n            url: The URL string to validate and normalize\n\n        Returns:\n            str: The normalized URL\n\n        Raises:\n            ValueError: If the URL is invalid\n        \"\"\"\n        url = url.strip()\n        if not url.startswith((\"http://\", \"https://\")):\n            url = \"https://\" + url\n\n        if not self.validate_url(url):\n            msg = f\"Invalid URL: {url}\"\n            raise ValueError(msg)\n\n        return url\n\n    def _create_loader(self, url: str) -> RecursiveUrlLoader:\n        \"\"\"Creates a RecursiveUrlLoader instance with the configured settings.\n\n        Args:\n            url: The URL to load\n\n        Returns:\n            RecursiveUrlLoader: Configured loader instance\n        \"\"\"\n        headers_dict = {header[\"key\"]: header[\"value\"] for header in self.headers if header[\"value\"] is not None}\n        extractor = (lambda x: x) if self.format == \"HTML\" else (lambda x: BeautifulSoup(x, \"lxml\").get_text())\n\n        return RecursiveUrlLoader(\n            url=url,\n            max_depth=self.max_depth,\n            prevent_outside=self.prevent_outside,\n            use_async=self.use_async,\n            extractor=extractor,\n            timeout=self.timeout,\n            headers=headers_dict,\n            check_response_status=self.check_response_status,\n            continue_on_failure=self.continue_on_failure,\n            base_url=url,  # Add base_url to ensure consistent domain crawling\n            autoset_encoding=self.autoset_encoding,  # Enable automatic encoding detection\n            exclude_dirs=[],  # Allow customization of excluded directories\n            link_regex=None,  # Allow customization of link filtering\n        )\n\n    def fetch_url_contents(self) -> list[dict]:\n        \"\"\"Load documents from the configured URLs.\n\n        Returns:\n            List[Data]: List of Data objects containing the fetched content\n\n        Raises:\n            ValueError: If no valid URLs are provided or if there's an error loading documents\n        \"\"\"\n        try:\n            urls = list({self.ensure_url(url) for url in self.urls if url.strip()})\n            logger.debug(f\"URLs: {urls}\")\n            if not urls:\n                msg = \"No valid URLs provided.\"\n                raise ValueError(msg)\n\n            all_docs = []\n            for url in urls:\n                logger.debug(f\"Loading documents from {url}\")\n\n                try:\n                    loader = self._create_loader(url)\n                    docs = loader.load()\n\n                    if not docs:\n                        logger.warning(f\"No documents found for {url}\")\n                        continue\n\n                    logger.debug(f\"Found {len(docs)} documents from {url}\")\n                    all_docs.extend(docs)\n\n                except requests.exceptions.RequestException as e:\n                    logger.exception(f\"Error loading documents from {url}: {e}\")\n                    continue\n\n            if not all_docs:\n                msg = \"No documents were successfully loaded from any URL\"\n                raise ValueError(msg)\n\n            # data = [Data(text=doc.page_content, **doc.metadata) for doc in all_docs]\n            data = [\n                {\n                    \"text\": safe_convert(doc.page_content, clean_data=True),\n                    \"url\": doc.metadata.get(\"source\", \"\"),\n                    \"title\": doc.metadata.get(\"title\", \"\"),\n                    \"description\": doc.metadata.get(\"description\", \"\"),\n                    \"content_type\": doc.metadata.get(\"content_type\", \"\"),\n                    \"language\": doc.metadata.get(\"language\", \"\"),\n                }\n                for doc in all_docs\n            ]\n        except Exception as e:\n            error_msg = e.message if hasattr(e, \"message\") else e\n            msg = f\"Error loading documents: {error_msg!s}\"\n            logger.exception(msg)\n            raise ValueError(msg) from e\n        return data\n\n    def fetch_content(self) -> DataFrame:\n        \"\"\"Convert the documents to a DataFrame.\"\"\"\n        return DataFrame(data=self.fetch_url_contents())\n\n    def fetch_content_as_message(self) -> Message:\n        \"\"\"Convert the documents to a Message.\"\"\"\n        url_contents = self.fetch_url_contents()\n        return Message(text=\"\\n\\n\".join([x[\"text\"] for x in url_contents]), data={\"data\": url_contents})\n"
+                "value": "import importlib\nimport io\nimport re\n\nimport requests\nfrom bs4 import BeautifulSoup\nfrom langchain_community.document_loaders import RecursiveUrlLoader\nfrom markitdown import MarkItDown\n\nfrom lfx.custom.custom_component.component import Component\nfrom lfx.field_typing.range_spec import RangeSpec\nfrom lfx.helpers.data import safe_convert\nfrom lfx.io import BoolInput, DropdownInput, IntInput, MessageTextInput, Output, SliderInput, TableInput\nfrom lfx.log.logger import logger\nfrom lfx.schema.dataframe import DataFrame\nfrom lfx.schema.message import Message\nfrom lfx.utils.request_utils import get_user_agent\n\n# Constants\nDEFAULT_TIMEOUT = 30\nDEFAULT_MAX_DEPTH = 1\nDEFAULT_FORMAT = \"Text\"\n\n\nURL_REGEX = re.compile(\n    r\"^(https?:\\/\\/)?\" r\"(www\\.)?\" r\"([a-zA-Z0-9.-]+)\" r\"(\\.[a-zA-Z]{2,})?\" r\"(:\\d+)?\" r\"(\\/[^\\s]*)?$\",\n    re.IGNORECASE,\n)\n\nUSER_AGENT = None\n# Check if langflow is installed using importlib.util.find_spec(name))\nif importlib.util.find_spec(\"langflow\"):\n    langflow_installed = True\n    USER_AGENT = get_user_agent()\nelse:\n    langflow_installed = False\n    USER_AGENT = \"lfx\"\n\n\nclass URLComponent(Component):\n    \"\"\"A component that loads and parses content from web pages recursively.\n\n    This component allows fetching content from one or more URLs, with options to:\n    - Control crawl depth\n    - Prevent crawling outside the root domain\n    - Use async loading for better performance\n    - Extract either raw HTML or clean text\n    - Configure request headers and timeouts\n    \"\"\"\n\n    display_name = \"URL\"\n    description = \"Fetch content from one or more web pages, following links recursively.\"\n    documentation: str = \"https://docs.langflow.org/url\"\n    icon = \"layout-template\"\n    name = \"URLComponent\"\n\n    inputs = [\n        MessageTextInput(\n            name=\"urls\",\n            display_name=\"URLs\",\n            info=\"Enter one or more URLs to crawl recursively, by clicking the '+' button.\",\n            is_list=True,\n            tool_mode=True,\n            placeholder=\"Enter a URL...\",\n            list_add_label=\"Add URL\",\n            input_types=[],\n        ),\n        SliderInput(\n            name=\"max_depth\",\n            display_name=\"Depth\",\n            info=(\n                \"Controls how many 'clicks' away from the initial page the crawler will go:\\n\"\n                \"- depth 1: only the initial page\\n\"\n                \"- depth 2: initial page + all pages linked directly from it\\n\"\n                \"- depth 3: initial page + direct links + links found on those direct link pages\\n\"\n                \"Note: This is about link traversal, not URL path depth.\"\n            ),\n            value=DEFAULT_MAX_DEPTH,\n            range_spec=RangeSpec(min=1, max=5, step=1),\n            required=False,\n            min_label=\" \",\n            max_label=\" \",\n            min_label_icon=\"None\",\n            max_label_icon=\"None\",\n            # slider_input=True\n        ),\n        BoolInput(\n            name=\"prevent_outside\",\n            display_name=\"Prevent Outside\",\n            info=(\n                \"If enabled, only crawls URLs within the same domain as the root URL. \"\n                \"This helps prevent the crawler from going to external websites.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"use_async\",\n            display_name=\"Use Async\",\n            info=(\n                \"If enabled, uses asynchronous loading which can be significantly faster \"\n                \"but might use more system resources.\"\n            ),\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        DropdownInput(\n            name=\"format\",\n            display_name=\"Output Format\",\n            info=(\n                \"Output Format. Use 'Text' to extract the text from the HTML, \"\n                \"'Markdown' to parse the HTML into Markdown format, or 'HTML' \"\n                \"for the raw HTML content.\"\n            ),\n            options=[\"Text\", \"HTML\", \"Markdown\"],\n            value=DEFAULT_FORMAT,\n            advanced=True,\n        ),\n        IntInput(\n            name=\"timeout\",\n            display_name=\"Timeout\",\n            info=\"Timeout for the request in seconds.\",\n            value=DEFAULT_TIMEOUT,\n            required=False,\n            advanced=True,\n        ),\n        TableInput(\n            name=\"headers\",\n            display_name=\"Headers\",\n            info=\"The headers to send with the request\",\n            table_schema=[\n                {\n                    \"name\": \"key\",\n                    \"display_name\": \"Header\",\n                    \"type\": \"str\",\n                    \"description\": \"Header name\",\n                },\n                {\n                    \"name\": \"value\",\n                    \"display_name\": \"Value\",\n                    \"type\": \"str\",\n                    \"description\": \"Header value\",\n                },\n            ],\n            value=[{\"key\": \"User-Agent\", \"value\": USER_AGENT}],\n            advanced=True,\n            input_types=[\"DataFrame\"],\n        ),\n        BoolInput(\n            name=\"filter_text_html\",\n            display_name=\"Filter Text/HTML\",\n            info=\"If enabled, filters out text/css content type from the results.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"continue_on_failure\",\n            display_name=\"Continue on Failure\",\n            info=\"If enabled, continues crawling even if some requests fail.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"check_response_status\",\n            display_name=\"Check Response Status\",\n            info=\"If enabled, checks the response status of the request.\",\n            value=False,\n            required=False,\n            advanced=True,\n        ),\n        BoolInput(\n            name=\"autoset_encoding\",\n            display_name=\"Autoset Encoding\",\n            info=\"If enabled, automatically sets the encoding of the request.\",\n            value=True,\n            required=False,\n            advanced=True,\n        ),\n    ]\n\n    outputs = [\n        Output(display_name=\"Extracted Pages\", name=\"page_results\", method=\"fetch_content\"),\n        Output(display_name=\"Raw Content\", name=\"raw_results\", method=\"fetch_content_as_message\", tool_mode=False),\n    ]\n\n    @staticmethod\n    def _html_extractor(x: str) -> str:\n        \"\"\"Extract raw HTML content.\"\"\"\n        return x\n\n    @staticmethod\n    def _text_extractor(x: str) -> str:\n        \"\"\"Extract clean text from HTML.\"\"\"\n        return BeautifulSoup(x, \"lxml\").get_text()\n\n    @staticmethod\n    def _markdown_extractor(x: str) -> str:\n        \"\"\"Convert HTML to Markdown format.\"\"\"\n        stream = io.BytesIO(x.encode(\"utf-8\"))\n        result = MarkItDown(enable_plugins=False).convert_stream(stream)\n        return result.markdown\n\n    @staticmethod\n    def validate_url(url: str) -> bool:\n        \"\"\"Validates if the given string matches URL pattern.\n\n        Args:\n            url: The URL string to validate\n\n        Returns:\n            bool: True if the URL is valid, False otherwise\n        \"\"\"\n        return bool(URL_REGEX.match(url))\n\n    def ensure_url(self, url: str) -> str:\n        \"\"\"Ensures the given string is a valid URL.\n\n        Args:\n            url: The URL string to validate and normalize\n\n        Returns:\n            str: The normalized URL\n\n        Raises:\n            ValueError: If the URL is invalid\n        \"\"\"\n        url = url.strip()\n        if not url.startswith((\"http://\", \"https://\")):\n            url = \"https://\" + url\n\n        if not self.validate_url(url):\n            msg = f\"Invalid URL: {url}\"\n            raise ValueError(msg)\n\n        return url\n\n    def _create_loader(self, url: str) -> RecursiveUrlLoader:\n        \"\"\"Creates a RecursiveUrlLoader instance with the configured settings.\n\n        Args:\n            url: The URL to load\n\n        Returns:\n            RecursiveUrlLoader: Configured loader instance\n        \"\"\"\n        headers_dict = {header[\"key\"]: header[\"value\"] for header in self.headers if header[\"value\"] is not None}\n        extractors = {\n            \"HTML\": self._html_extractor,\n            \"Markdown\": self._markdown_extractor,\n            \"Text\": self._text_extractor,\n        }\n        extractor = extractors.get(self.format, self._text_extractor)\n\n        return RecursiveUrlLoader(\n            url=url,\n            max_depth=self.max_depth,\n            prevent_outside=self.prevent_outside,\n            use_async=self.use_async,\n            extractor=extractor,\n            timeout=self.timeout,\n            headers=headers_dict,\n            check_response_status=self.check_response_status,\n            continue_on_failure=self.continue_on_failure,\n            base_url=url,  # Add base_url to ensure consistent domain crawling\n            autoset_encoding=self.autoset_encoding,  # Enable automatic encoding detection\n            exclude_dirs=[],  # Allow customization of excluded directories\n            link_regex=None,  # Allow customization of link filtering\n        )\n\n    def fetch_url_contents(self) -> list[dict]:\n        \"\"\"Load documents from the configured URLs.\n\n        Returns:\n            List[Data]: List of Data objects containing the fetched content\n\n        Raises:\n            ValueError: If no valid URLs are provided or if there's an error loading documents\n        \"\"\"\n        try:\n            urls = list({self.ensure_url(url) for url in self.urls if url.strip()})\n            logger.debug(f\"URLs: {urls}\")\n            if not urls:\n                msg = \"No valid URLs provided.\"\n                raise ValueError(msg)\n\n            all_docs = []\n            for url in urls:\n                logger.debug(f\"Loading documents from {url}\")\n\n                try:\n                    loader = self._create_loader(url)\n                    docs = loader.load()\n\n                    if not docs:\n                        logger.warning(f\"No documents found for {url}\")\n                        continue\n\n                    logger.debug(f\"Found {len(docs)} documents from {url}\")\n                    all_docs.extend(docs)\n\n                except requests.exceptions.RequestException as e:\n                    logger.exception(f\"Error loading documents from {url}: {e}\")\n                    continue\n\n            if not all_docs:\n                msg = \"No documents were successfully loaded from any URL\"\n                raise ValueError(msg)\n\n            # data = [Data(text=doc.page_content, **doc.metadata) for doc in all_docs]\n            data = [\n                {\n                    \"text\": safe_convert(doc.page_content, clean_data=True),\n                    \"url\": doc.metadata.get(\"source\", \"\"),\n                    \"title\": doc.metadata.get(\"title\", \"\"),\n                    \"description\": doc.metadata.get(\"description\", \"\"),\n                    \"content_type\": doc.metadata.get(\"content_type\", \"\"),\n                    \"language\": doc.metadata.get(\"language\", \"\"),\n                }\n                for doc in all_docs\n            ]\n        except Exception as e:\n            error_msg = e.message if hasattr(e, \"message\") else e\n            msg = f\"Error loading documents: {error_msg!s}\"\n            logger.exception(msg)\n            raise ValueError(msg) from e\n        return data\n\n    def fetch_content(self) -> DataFrame:\n        \"\"\"Convert the documents to a DataFrame.\"\"\"\n        return DataFrame(data=self.fetch_url_contents())\n\n    def fetch_content_as_message(self) -> Message:\n        \"\"\"Convert the documents to a Message.\"\"\"\n        url_contents = self.fetch_url_contents()\n        return Message(text=\"\\n\\n\".join([x[\"text\"] for x in url_contents]), data={\"data\": url_contents})\n"
               },
               "continue_on_failure": {
                 "_input_type": "BoolInput",
@@ -509,11 +513,12 @@
                 "dialog_inputs": {},
                 "display_name": "Output Format",
                 "dynamic": false,
-                "info": "Output Format. Use 'Text' to extract the text from the HTML or 'HTML' for the raw HTML content.",
+                "info": "Output Format. Use 'Text' to extract the text from the HTML, 'Markdown' to parse the HTML into Markdown format, or 'HTML' for the raw HTML content.",
                 "name": "format",
                 "options": [
                   "Text",
-                  "HTML"
+                  "HTML",
+                  "Markdown"
                 ],
                 "options_metadata": [],
                 "placeholder": "",