@n8n-as-code/skills 2.1.0-next.49 → 2.1.0

package/dist/assets/n8n-docs-complete.json

@@ -1,13 +1,13 @@
 {
-  "generatedAt": "2026-05-11T11:30:58.451Z",
+  "generatedAt": "2026-05-11T13:29:19.741Z",
   "version": "1.0.0",
   "sourceUrl": "https://docs.n8n.io/llms.txt",
-  "totalPages": 1276,
+  "totalPages": 1278,
   "statistics": {
     "byCategory": {
-      "other": 514,
+      "other": 513,
       "tutorials": 27,
-      "advanced-ai": 25,
+      "advanced-ai": 28,
       "api": 6,
       "code": 20,
       "data": 38,
@@ -21,12 +21,12 @@
     },
     "withNodeNames": 471,
     "withUseCases": 40,
-    "withCodeExamples": 185
+    "withCodeExamples": 186
   },
   "categories": {
     "other": {
       "description": "General documentation and guides",
-      "totalPages": 514,
+      "totalPages": 513,
       "pages": [
         "page-0001",
         "page-0002",
@@ -49,7 +49,6 @@
         "page-0237",
         "page-0238",
         "page-0239",
-        "page-0240",
         "page-0654",
         "page-0655",
         "page-0656",
@@ -579,7 +578,7 @@
     },
     "advanced-ai": {
       "description": "AI agents, chains, RAG, memory, and LangChain integration",
-      "totalPages": 25,
+      "totalPages": 28,
       "pages": [
         "page-0017",
         "page-0018",
@@ -602,6 +601,9 @@
         "page-0035",
         "page-0036",
         "page-0037",
+        "page-0038",
+        "page-0039",
+        "page-0040",
         "page-0041",
         "page-0042",
         "page-0043",
@@ -4838,6 +4840,99 @@
     },
     {
       "id": "page-0037",
+      "title": "Let AI specify tool parameters",
+      "url": "https://docs.n8n.io/advanced-ai/examples/using-the-fromai-function/index.md",
+      "urlPath": "advanced-ai/examples/using-the-fromai-function/index.md",
+      "category": "advanced-ai",
+      "subcategory": "examples",
+      "nodeName": null,
+      "nodeType": null,
+      "content": {
+        "markdown": "# Let AI specify the tool parameters\n\nWhen configuring [tools](../../../glossary/#ai-tool) connected to the Tools Agent, many parameters can be filled in by the AI model itself. The AI model will use the context from the task and information from other connected tools to fill in the appropriate details.\n\nThere are two ways to do this, and you can switch between them.\n\n## Let the model fill in the parameter\n\nEach appropriate parameter field in the tool's editing dialog has an extra button at the end:\n\nOn activating this button, the [AI Agent](../../../glossary/#ai-agent) will fill in the expression for you, with no need for any further user input. The field itself is filled in with a message indicating that the parameter has been defined automatically by the model.\n\nIf you want to define the parameter yourself, click on the 'X' in this box to revert to user-defined values. Note that the 'expression' field will now contain the expression generated by this feature, though you can now edit it further to add extra details as described in the following section.\n\nWarning\n\nActivating this feature will overwrite any manual definition you may have already added.\n\n## Use the `$fromAI()` function\n\nThe `$fromAI()` function uses AI to dynamically fill in parameters for tools connected to the [Tools AI agent](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/).\n\nOnly for tools\n\nThe `$fromAI()` function is only available for tools connected to the AI Agent node. The `$fromAI()` function doesn't work with the [Code](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcode/) tool or with [other non-tool cluster sub-nodes](../../../integrations/builtin/cluster-nodes/sub-nodes/).\n\nTo use the `$fromAI()` function, call it with the required `key` parameter:\n\n```\n{{ $fromAI('email') }}\n```\n\nThe `key` parameter and other arguments to the `$fromAI()` function aren't references to existing values. Instead, think of these arguments as hints that the AI model will use to populate the right data.\n\nFor instance, if you choose a key called `email`, the AI Model will look for an email address in its context, other tools, and input data. In chat workflows, it may ask the user for an email address if it can't find one elsewhere. You can optionally pass other parameters like `description` to give extra context to the AI model.\n\n### Parameters\n\nThe `$fromAI()` function accepts the following parameters:\n\n| Parameter      | Type   | Required? | Description                                                                                                                                                                                             |\n| -------------- | ------ | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `key`          | string |           | A string representing the key or name of the argument. This must be between 1 and 64 characters in length and can only contain lowercase letters, uppercase letters, numbers, underscores, and hyphens. |\n| `description`  | string |           | A string describing the argument.                                                                                                                                                                       |\n| `type`         | string |           | A string specifying the data type. Can be string, number, boolean, or json (defaults to string).                                                                                                        |\n| `defaultValue` | any    |           | The default value to use for the argument.                                                                                                                                                              |\n\n### Examples\n\nAs an example, you could use the following `$fromAI()` expression to dynamically populate a field with a name:\n\n```\n$fromAI(\"name\", \"The commenter's name\", \"string\", \"Jane Doe\")\n```\n\nIf you don't need the optional parameters, you could simplify this as:\n\n```\n$fromAI(\"name\")\n```\n\nTo dynamically populate the number of items you have in stock, you could use a `$fromAI()` expression like this:\n\n```\n$fromAI(\"numItemsInStock\", \"Number of items in stock\", \"number\", 5)\n```\n\nIf you only want to fill in parts of a field with a dynamic value from the model, you can use it in a normal expression as well. For example, if you want the model to fill out the `subject` parameter for an e-mail, but always pre-fix the generated value with the string 'Generated by AI:', you could use the following expression:\n\n```\nGenerated by AI: {{ $fromAI(\"subject\") }}\n```\n\n### Templates\n\nYou can see the `$fromAI()` function in action in the following [templates](../../../glossary/#template-n8n):\n\n- [Angie, Personal AI Assistant with Telegram Voice and Text](https://n8n.io/workflows/2462-angie-personal-ai-assistant-with-telegram-voice-and-text/)\n- [Automate Customer Support Issue Resolution using AI Text Classifier](https://n8n.io/workflows/2468-automate-customer-support-issue-resolution-using-ai-text-classifier/)\n- [Scale Deal Flow with a Pitch Deck AI Vision, Chatbot and QDrant Vector Store](https://n8n.io/workflows/2464-scale-deal-flow-with-a-pitch-deck-ai-vision-chatbot-and-qdrant-vector-store/)\n",
+        "excerpt": "# Let AI specify the tool parameters  When configuring [tools](../../../glossary/#ai-tool) connected to the Tools Agent, many parameters can be filled in by the AI model itself. The AI model will use the context from the task and information from other connected tools to fill in the appropriate details.  There are two ways to do this, and you can switch between them.  ## Let the model fill in the parameter  Each appropriate parameter field in the tool's editing dialog has an extra button at the...",
+        "sections": [
+          {
+            "title": "Let AI specify the tool parameters",
+            "level": 1,
+            "content": "When configuring [tools](../../../glossary/#ai-tool) connected to the Tools Agent, many parameters can be filled in by the AI model itself. The AI model will use the context from the task and information from other connected tools to fill in the appropriate details.\n\nThere are two ways to do this, and you can switch between them."
+          }
+        ]
+      },
+      "metadata": {
+        "keywords": [
+          "specify",
+          "tool",
+          "parameters",
+          "model",
+          "fill",
+          "parameter",
+          "`$fromai()`",
+          "function",
+          "examples",
+          "templates"
+        ],
+        "useCases": [],
+        "operations": [],
+        "codeExamples": 5,
+        "complexity": "intermediate",
+        "readingTime": "4 min",
+        "contentLength": 5438,
+        "relatedPages": []
+      },
+      "searchIndex": {
+        "fullText": "let ai specify tool parameters # let ai specify the tool parameters\n\nwhen configuring [tools](../../../glossary/#ai-tool) connected to the tools agent, many parameters can be filled in by the ai model itself. the ai model will use the context from the task and information from other connected tools to fill in the appropriate details.\n\nthere are two ways to do this, and you can switch between them.\n\n## let the model fill in the parameter\n\neach appropriate parameter field in the tool's editing dialog has an extra button at the end:\n\non activating this button, the [ai agent](../../../glossary/#ai-agent) will fill in the expression for you, with no need for any further user input. the field itself is filled in with a message indicating that the parameter has been defined automatically by the model.\n\nif you want to define the parameter yourself, click on the 'x' in this box to revert to user-defined values. note that the 'expression' field will now contain the expression generated by this feature, though you can now edit it further to add extra details as described in the following section.\n\nwarning\n\nactivating this feature will overwrite any manual definition you may have already added.\n\n## use the `$fromai()` function\n\nthe `$fromai()` function uses ai to dynamically fill in parameters for tools connected to the [tools ai agent](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/tools-agent/).\n\nonly for tools\n\nthe `$fromai()` function is only available for tools connected to the ai agent node. the `$fromai()` function doesn't work with the [code](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcode/) tool or with [other non-tool cluster sub-nodes](../../../integrations/builtin/cluster-nodes/sub-nodes/).\n\nto use the `$fromai()` function, call it with the required `key` parameter:\n\n```\n{{ $fromai('email') }}\n```\n\nthe `key` parameter and other arguments to the `$fromai()` function aren't references to existing values. instead, think of these arguments as hints that the ai model will use to populate the right data.\n\nfor instance, if you choose a key called `email`, the ai model will look for an email address in its context, other tools, and input data. in chat workflows, it may ask the user for an email address if it can't find one elsewhere. you can optionally pass other parameters like `description` to give extra context to the ai model.\n\n### parameters\n\nthe `$fromai()` function accepts the following parameters:\n\n| parameter      | type   | required? | description                                                                                                                                                                                             |\n| -------------- | ------ | --------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `key`          | string |           | a string representing the key or name of the argument. this must be between 1 and 64 characters in length and can only contain lowercase letters, uppercase letters, numbers, underscores, and hyphens. |\n| `description`  | string |           | a string describing the argument.                                                                                                                                                                       |\n| `type`         | string |           | a string specifying the data type. can be string, number, boolean, or json (defaults to string).                                                                                                        |\n| `defaultvalue` | any    |           | the default value to use for the argument.                                                                                                                                                              |\n\n### examples\n\nas an example, you could use the following `$fromai()` expression to dynamically populate a field with a name:\n\n```\n$fromai(\"name\", \"the commenter's name\", \"string\", \"jane doe\")\n```\n\nif you don't need the optional parameters, you could simplify this as:\n\n```\n$fromai(\"name\")\n```\n\nto dynamically populate the number of items you have in stock, you could use a `$fromai()` expression like this:\n\n```\n$fromai(\"numitemsinstock\", \"number of items in stock\", \"number\", 5)\n```\n\nif you only want to fill in parts of a field with a dynamic value from the model, you can use it in a normal expression as well. for example, if you want the model to fill out the `subject` parameter for an e-mail, but always pre-fix the generated value with the string 'generated by ai:', you could use the following expression:\n\n```\ngenerated by ai: {{ $fromai(\"subject\") }}\n```\n\n### templates\n\nyou can see the `$fromai()` function in action in the following [templates](../../../glossary/#template-n8n):\n\n- [angie, personal ai assistant with telegram voice and text](https://n8n.io/workflows/2462-angie-personal-ai-assistant-with-telegram-voice-and-text/)\n- [automate customer support issue resolution using ai text classifier](https://n8n.io/workflows/2468-automate-customer-support-issue-resolution-using-ai-text-classifier/)\n- [scale deal flow with a pitch deck ai vision, chatbot and qdrant vector store](https://n8n.io/workflows/2464-scale-deal-flow-with-a-pitch-deck-ai-vision-chatbot-and-qdrant-vector-store/)\n let ai specify the tool parameters",
+        "importantTerms": [
+          "fromai",
+          "with",
+          "string",
+          "parameters",
+          "tools",
+          "model",
+          "nodes",
+          "this",
+          "parameter",
+          "function",
+          "tool",
+          "agent",
+          "expression",
+          "will",
+          "fill",
+          "other",
+          "field",
+          "following",
+          "name",
+          "connected",
+          "generated",
+          "cluster",
+          "only",
+          "email",
+          "workflows",
+          "number",
+          "could",
+          "text",
+          "specify",
+          "glossary",
+          "context",
+          "from",
+          "extra",
+          "user",
+          "that",
+          "want",
+          "dynamically",
+          "integrations",
+          "builtin",
+          "populate",
+          "data",
+          "description",
+          "type",
+          "argument",
+          "value",
+          "https"
+        ]
+      }
+    },
+    {
+      "id": "page-0038",
       "title": "Populate a Pinecone vector database from a website",
       "url": "https://docs.n8n.io/advanced-ai/examples/vector-store-website/index.md",
       "urlPath": "advanced-ai/examples/vector-store-website/index.md",
@@ -4846,13 +4941,13 @@
       "nodeName": null,
       "nodeType": null,
       "content": {
-        "markdown": "# LangChain concepts in n8n\n\nThis page explains how LangChain concepts and features map to n8n nodes.\n\nThis page includes lists of the LangChain-focused nodes in n8n. You can use any n8n node in a workflow where you interact with LangChain, to link LangChain to other services. The LangChain features uses n8n's [Cluster nodes](../../../integrations/builtin/cluster-nodes/).\n\nn8n implements LangChain JS\n\nThis feature is n8n's implementation of [LangChain's JavaScript framework](https://js.langchain.com/docs/get_started/introduction).\n\n## Trigger nodes\n\n[Chat Trigger](../../../integrations/builtin/core-nodes/n8n-nodes-langchain.chattrigger/)\n\n## Cluster nodes\n\n[Cluster nodes](../../../glossary/#cluster-node-n8n) are node groups that work together to provide functionality in an n8n workflow. Instead of using a single node, you use a [root node](../../../glossary/#root-node-n8n) and one or more [sub-nodes](../../../glossary/#sub-node-n8n) that extend the functionality of the node.\n\n### Root nodes\n\nEach cluster starts with one [root node](../../../glossary/#root-node-n8n).\n\n#### Chains\n\nA [chain](../../../glossary/#ai-chain) is a series of LLMs, and related tools, linked together to support functionality that can't be provided by a single LLM alone.\n\nAvailable nodes:\n\n- [Basic LLM Chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm/)\n- [Retrieval Q&A Chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa/)\n- [Summarization Chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainsummarization/)\n- [Sentiment Analysis](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.sentimentanalysis/)\n- [Text Classifier](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.text-classifier/)\n\nLearn more about [chaining in LangChain](https://js.langchain.com/docs/concepts/lcel).\n\n#### Agents\n\n> An [agent](../../../glossary/#ai-agent) has access to a suite of tools, and determines which ones to use depending on the user input. Agents can use multiple tools, and use the output of one tool as the input to the next. [Source](https://github.com/langchain-ai/langchainjs/blob/def3a26c054575e1ed40b9062087e8c0a8899633/docs/core_docs/docs/modules/agents/index.mdx)\n\nAvailable nodes:\n\n- [Agent](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)\n\nLearn more about [Agents in LangChain](https://js.langchain.com/docs/concepts/agents).\n\n#### Vector stores\n\n[Vector stores](../../../glossary/#ai-vector-store) store embedded data, and perform vector searches on it.\n\n- [Simple Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreinmemory/)\n- [PGVector Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepgvector/)\n- [Pinecone Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/)\n- [Qdrant Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreqdrant/)\n- [Supabase Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/)\n- [Zep Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorezep/)\n\nLearn more about [Vector stores in LangChain](https://js.langchain.com/docs/concepts/vectorstores/).\n\n#### Miscellaneous\n\nUtility nodes.\n\n[LangChain Code](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.code/): import LangChain. This means if there is functionality you need that n8n hasn't created a node for, you can still use it.\n\n### Sub-nodes\n\nEach root node can have one or more [sub-nodes](../../../glossary/#sub-node-n8n) attached to it.\n\n#### Document loaders\n\nDocument loaders add data to your chain as documents. The data source can be a file or web service.\n\nAvailable nodes:\n\n- [Default Document Loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/)\n- [GitHub Document Loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentgithubloader/)\n\nLearn more about [Document loaders in LangChain](https://js.langchain.com/docs/concepts/document_loaders).\n\n#### Language models\n\n[LLMs (large language models)](../../../glossary/#large-language-model-llm) are programs that analyze datasets. They're the key element of working with AI.\n\nAvailable nodes:\n\n- [Anthropic Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatanthropic/)\n- [AWS Bedrock Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatawsbedrock/)\n- [Cohere Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmcohere/)\n- [Hugging Face Inference Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmopenhuggingfaceinference/)\n- [Mistral Cloud Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatmistralcloud/)\n- [Ollama Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatollama/)\n- [Ollama Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmollama/)\n- [OpenAI Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/)\n\nLearn more about [Language models in LangChain](https://js.langchain.com/docs/concepts/chat_models).\n\n#### Memory\n\n[Memory](../../../glossary/#ai-memory) retains information about previous queries in a series of queries. For example, when a user interacts with a chat model, it's useful if your application can remember and call on the full conversation, not just the most recent query entered by the user.\n\nAvailable nodes:\n\n- [Motorhead](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymotorhead/)\n- [Redis Chat Memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryredischat/)\n- [Postgres Chat Memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorypostgreschat/)\n- [Simple Memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/)\n- [Xata](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryxata/)\n- [Zep](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryzep/)\n\nLearn more about [Memory in LangChain](https://langchain-ai.github.io/langgraphjs/concepts/memory/).\n\n#### Output parsers\n\nOutput parsers take the text generated by an LLM and format it to match the structure you require.\n\nAvailable nodes:\n\n- [Auto-fixing Output Parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserautofixing/)\n- [Item List Output Parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparseritemlist/)\n- [Structured Output Parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserstructured/)\n\nLearn more about [Output parsers in LangChain](https://js.langchain.com/docs/concepts/output_parsers/).\n\n#### Retrievers\n\n- [Contextual Compression Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievercontextualcompression/)\n- [MultiQuery Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievermultiquery/)\n- [Vector Store Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievervectorstore/)\n- [Workflow Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrieverworkflow/)\n\n#### Text splitters\n\nText splitters break down data (documents), making it easier for the LLM to process the information and return accurate results.\n\nAvailable nodes:\n\n- [Character Text Splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittercharactertextsplitter/)\n- [Recursive Character Text Splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplitterrecursivecharactertextsplitter/)\n- [Token Splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittertokensplitter/)\n\nn8n's text splitter nodes implements parts of [LangChain's text_splitter API](https://js.langchain.com/docs/concepts/text_splitters/).\n\n#### Tools\n\nUtility [tools](../../../glossary/#ai-tool).\n\n- [Calculator](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcalculator/)\n- [Code Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcode/)\n- [SerpAPI](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolserpapi/)\n- [Think Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolthink/)\n- [Vector Store Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolvectorstore/)\n- [Wikipedia](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwikipedia/)\n- [Wolfram|Alpha](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwolframalpha/)\n- [Workflow Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolworkflow/)\n\n#### Embeddings\n\n> [Embeddings](../../../glossary/#ai-embedding) capture the \"relatedness\" of text, images, video, or other types of information. ([source](https://supabase.com/docs/guides/ai/concepts))\n\nAvailable nodes:\n\n- [Embeddings AWS Bedrock](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsawsbedrock/)\n- [Embeddings Cohere](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingscohere/)\n- [Embeddings Google PaLM](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsgooglepalm/)\n- [Embeddings Hugging Face Inference](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingshuggingfaceinference/)\n- [Embeddings Mistral Cloud](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsmistralcloud/)\n- [Embeddings Ollama](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsollama/)\n- [Embeddings OpenAI](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsopenai/)\n\nLearn more about [Text embeddings in LangChain](https://js.langchain.com/docs/concepts/embedding_models/).\n\n#### Miscellaneous\n\n- [Chat Memory Manager](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymanager/)\n",
-        "excerpt": "# LangChain concepts in n8n  This page explains how LangChain concepts and features map to n8n nodes.  This page includes lists of the LangChain-focused nodes in n8n. You can use any n8n node in a workflow where you interact with LangChain, to link LangChain to other services. The LangChain features uses n8n's [Cluster nodes](../../../integrations/builtin/cluster-nodes/).  n8n implements LangChain JS  This feature is n8n's implementation of [LangChain's JavaScript framework](https://js.langchain...",
+        "markdown": "# Populate a Pinecone vector database from a website\n\nUse n8n to scrape a website, load the data into Pinecone, then query it using a chat workflow. This workflow uses the [HTTP node](../../../integrations/builtin/core-nodes/n8n-nodes-base.httprequest/) to get website data, extracts the relevant content using the [HTML node](../../../integrations/builtin/core-nodes/n8n-nodes-base.html/), then uses the [Pinecone Vector Store node](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/) to send it to Pinecone.\n\n[View workflow file](/_workflows/advanced-ai/examples/populate_a_pinecone_vector_database_from_a_website.json)\n\n## Key features\n\nThis workflow uses:\n\n- [HTTP node](../../../integrations/builtin/core-nodes/n8n-nodes-base.httprequest/): fetches website data.\n- [HTML node](../../../integrations/builtin/core-nodes/n8n-nodes-base.html/): simplifies the data by extracting the main content from the page.\n- [Pinecone Vector Store node](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/) and [Embeddings OpenAI](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsopenai/): transform the data into vectors and store it in Pinecone.\n- [Chat Trigger](../../../integrations/builtin/core-nodes/n8n-nodes-langchain.chattrigger/) and [Question and Answer Chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa/) to query the vector database.\n\n## Using the example\n\nTo load the template into your n8n instance:\n\n1. Download the workflow JSON file.\n1. Open a new workflow in your n8n instance.\n1. Copy in the JSON, or select **Workflow menu** > **Import from file...**.\n\nThe example workflows use Sticky Notes to guide you:\n\n- Yellow: notes and information.\n- Green: instructions to run the workflow.\n- Orange: you need to change something to make the workflow work.\n- Blue: draws attention to a key feature of the example.\n",
+        "excerpt": "# Populate a Pinecone vector database from a website  Use n8n to scrape a website, load the data into Pinecone, then query it using a chat workflow. This workflow uses the [HTTP node](../../../integrations/builtin/core-nodes/n8n-nodes-base.httprequest/) to get website data, extracts the relevant content using the [HTML node](../../../integrations/builtin/core-nodes/n8n-nodes-base.html/), then uses the [Pinecone Vector Store node](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-l...",
         "sections": [
           {
-            "title": "LangChain concepts in n8n",
+            "title": "Populate a Pinecone vector database from a website",
             "level": 1,
-            "content": "This page explains how LangChain concepts and features map to n8n nodes.\n\nThis page includes lists of the LangChain-focused nodes in n8n. You can use any n8n node in a workflow where you interact with LangChain, to link LangChain to other services. The LangChain features uses n8n's [Cluster nodes](../../../integrations/builtin/cluster-nodes/).\n\nn8n implements LangChain JS\n\nThis feature is n8n's implementation of [LangChain's JavaScript framework](https://js.langchain.com/docs/get_started/introduction)."
+            "content": "Use n8n to scrape a website, load the data into Pinecone, then query it using a chat workflow. This workflow uses the [HTTP node](../../../integrations/builtin/core-nodes/n8n-nodes-base.httprequest/) to get website data, extracts the relevant content using the [HTML node](../../../integrations/builtin/core-nodes/n8n-nodes-base.html/), then uses the [Pinecone Vector Store node](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/) to send it to Pinecone.\n\n[View workflow file](/_workflows/advanced-ai/examples/populate_a_pinecone_vector_database_from_a_website.json)"
           }
         ]
       },
@@ -4871,13 +4966,148 @@
         "useCases": [],
         "operations": [],
         "codeExamples": 0,
+        "complexity": "beginner",
+        "readingTime": "2 min",
+        "contentLength": 1989,
+        "relatedPages": []
+      },
+      "searchIndex": {
+        "fullText": "populate a pinecone vector database from a website # populate a pinecone vector database from a website\n\nuse n8n to scrape a website, load the data into pinecone, then query it using a chat workflow. this workflow uses the [http node](../../../integrations/builtin/core-nodes/n8n-nodes-base.httprequest/) to get website data, extracts the relevant content using the [html node](../../../integrations/builtin/core-nodes/n8n-nodes-base.html/), then uses the [pinecone vector store node](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/) to send it to pinecone.\n\n[view workflow file](/_workflows/advanced-ai/examples/populate_a_pinecone_vector_database_from_a_website.json)\n\n## key features\n\nthis workflow uses:\n\n- [http node](../../../integrations/builtin/core-nodes/n8n-nodes-base.httprequest/): fetches website data.\n- [html node](../../../integrations/builtin/core-nodes/n8n-nodes-base.html/): simplifies the data by extracting the main content from the page.\n- [pinecone vector store node](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/) and [embeddings openai](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsopenai/): transform the data into vectors and store it in pinecone.\n- [chat trigger](../../../integrations/builtin/core-nodes/n8n-nodes-langchain.chattrigger/) and [question and answer chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa/) to query the vector database.\n\n## using the example\n\nto load the template into your n8n instance:\n\n1. download the workflow json file.\n1. open a new workflow in your n8n instance.\n1. copy in the json, or select **workflow menu** > **import from file...**.\n\nthe example workflows use sticky notes to guide you:\n\n- yellow: notes and information.\n- green: instructions to run the workflow.\n- orange: you need to change something to make the workflow work.\n- blue: draws attention to a key feature of the example.\n populate a pinecone vector database from a website",
+        "importantTerms": [
+          "nodes",
+          "workflow",
+          "integrations",
+          "builtin",
+          "pinecone",
+          "vector",
+          "website",
+          "node",
+          "from",
+          "data",
+          "core",
+          "langchain",
+          "database",
+          "base",
+          "html",
+          "cluster",
+          "populate",
+          "into",
+          "using",
+          "uses",
+          "store",
+          "root",
+          "file",
+          "json",
+          "example"
+        ]
+      }
+    },
+    {
+      "id": "page-0039",
+      "title": "LangChain learning resources",
+      "url": "https://docs.n8n.io/advanced-ai/langchain/langchain-learning-resources/index.md",
+      "urlPath": "advanced-ai/langchain/langchain-learning-resources/index.md",
+      "category": "advanced-ai",
+      "subcategory": "langchain",
+      "nodeName": null,
+      "nodeType": null,
+      "content": {
+        "markdown": "# LangChain learning resources\n\nYou don't need to know details about LangChain to use n8n, but it can be helpful to learn a few concepts. This pages lists some learning resources that people at n8n have found helpful.\n\nThe [LangChain documentation](https://docs.langchain.com/docs/) includes introductions to key concepts and possible use cases. Choose the [LangChain | Python](https://python.langchain.com/docs/get_started/introduction) or [LangChain | JavaScript](https://js.langchain.com/docs/get_started/introduction/) documentation for quickstarts, code examples, and API documentation. LangChain also provide [code templates](https://github.com/langchain-ai/langchain/tree/master/cookbook) (Python only), offering ideas for potential use cases and common patterns.\n\n[What Product People Need To Know About LangChain](https://www.commandbar.com/blog/langchain-guide) provides a list of terminology and concepts, explained with helpful metaphors. Aimed at a wide audience.\n\nIf you prefer video, this [YouTube series by Greg Kamradt](https://youtu.be/_v_fgW2SkkQ?si=8Z2tfAoXnN3lXU9s) works through the LangChain documentation, providing code examples as it goes.\n\nn8n offers space to discuss LangChain on the [Discord](https://discord.gg/bAt54txhHg). Join to share your projects and discuss ideas with the community.\n",
+        "excerpt": "# LangChain learning resources  You don't need to know details about LangChain to use n8n, but it can be helpful to learn a few concepts. This pages lists some learning resources that people at n8n have found helpful.  The [LangChain documentation](https://docs.langchain.com/docs/) includes introductions to key concepts and possible use cases. Choose the [LangChain | Python](https://python.langchain.com/docs/get_started/introduction) or [LangChain | JavaScript](https://js.langchain.com/docs/get_...",
+        "sections": [
+          {
+            "title": "LangChain learning resources",
+            "level": 1,
+            "content": "You don't need to know details about LangChain to use n8n, but it can be helpful to learn a few concepts. This pages lists some learning resources that people at n8n have found helpful.\n\nThe [LangChain documentation](https://docs.langchain.com/docs/) includes introductions to key concepts and possible use cases. Choose the [LangChain | Python](https://python.langchain.com/docs/get_started/introduction) or [LangChain | JavaScript](https://js.langchain.com/docs/get_started/introduction/) documentation for quickstarts, code examples, and API documentation. LangChain also provide [code templates](https://github.com/langchain-ai/langchain/tree/master/cookbook) (Python only), offering ideas for potential use cases and common patterns.\n\n[What Product People Need To Know About LangChain](https://www.commandbar.com/blog/langchain-guide) provides a list of terminology and concepts, explained with helpful metaphors. Aimed at a wide audience.\n\nIf you prefer video, this [YouTube series by Greg Kamr"
+          }
+        ]
+      },
+      "metadata": {
+        "keywords": [
+          "langchain",
+          "learning",
+          "resources"
+        ],
+        "useCases": [],
+        "operations": [],
+        "codeExamples": 0,
+        "complexity": "beginner",
+        "readingTime": "1 min",
+        "contentLength": 1320,
+        "relatedPages": []
+      },
+      "searchIndex": {
+        "fullText": "langchain learning resources # langchain learning resources\n\nyou don't need to know details about langchain to use n8n, but it can be helpful to learn a few concepts. this pages lists some learning resources that people at n8n have found helpful.\n\nthe [langchain documentation](https://docs.langchain.com/docs/) includes introductions to key concepts and possible use cases. choose the [langchain | python](https://python.langchain.com/docs/get_started/introduction) or [langchain | javascript](https://js.langchain.com/docs/get_started/introduction/) documentation for quickstarts, code examples, and api documentation. langchain also provide [code templates](https://github.com/langchain-ai/langchain/tree/master/cookbook) (python only), offering ideas for potential use cases and common patterns.\n\n[what product people need to know about langchain](https://www.commandbar.com/blog/langchain-guide) provides a list of terminology and concepts, explained with helpful metaphors. aimed at a wide audience.\n\nif you prefer video, this [youtube series by greg kamradt](https://youtu.be/_v_fgw2skkq?si=8z2tfaoxnn3lxu9s) works through the langchain documentation, providing code examples as it goes.\n\nn8n offers space to discuss langchain on the [discord](https://discord.gg/bat54txhhg). join to share your projects and discuss ideas with the community.\n langchain learning resources",
+        "importantTerms": [
+          "langchain",
+          "https",
+          "learning",
+          "resources",
+          "documentation",
+          "docs",
+          "helpful",
+          "concepts",
+          "python",
+          "code"
+        ]
+      }
+    },
+    {
+      "id": "page-0040",
+      "title": "Langchain concepts in n8n",
+      "url": "https://docs.n8n.io/advanced-ai/langchain/langchain-n8n/index.md",
+      "urlPath": "advanced-ai/langchain/langchain-n8n/index.md",
+      "category": "advanced-ai",
+      "subcategory": "langchain",
+      "nodeName": null,
+      "nodeType": null,
+      "content": {
+        "markdown": "# LangChain concepts in n8n\n\nThis page explains how LangChain concepts and features map to n8n nodes.\n\nThis page includes lists of the LangChain-focused nodes in n8n. You can use any n8n node in a workflow where you interact with LangChain, to link LangChain to other services. The LangChain features uses n8n's [Cluster nodes](../../../integrations/builtin/cluster-nodes/).\n\nn8n implements LangChain JS\n\nThis feature is n8n's implementation of [LangChain's JavaScript framework](https://js.langchain.com/docs/get_started/introduction).\n\n## Trigger nodes\n\n[Chat Trigger](../../../integrations/builtin/core-nodes/n8n-nodes-langchain.chattrigger/)\n\n## Cluster nodes\n\n[Cluster nodes](../../../glossary/#cluster-node-n8n) are node groups that work together to provide functionality in an n8n workflow. Instead of using a single node, you use a [root node](../../../glossary/#root-node-n8n) and one or more [sub-nodes](../../../glossary/#sub-node-n8n) that extend the functionality of the node.\n\n### Root nodes\n\nEach cluster starts with one [root node](../../../glossary/#root-node-n8n).\n\n#### Chains\n\nA [chain](../../../glossary/#ai-chain) is a series of LLMs, and related tools, linked together to support functionality that can't be provided by a single LLM alone.\n\nAvailable nodes:\n\n- [Basic LLM Chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm/)\n- [Retrieval Q&A Chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa/)\n- [Summarization Chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainsummarization/)\n- [Sentiment Analysis](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.sentimentanalysis/)\n- [Text Classifier](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.text-classifier/)\n\nLearn more about [chaining in LangChain](https://js.langchain.com/docs/concepts/lcel).\n\n#### Agents\n\n> An [agent](../../../glossary/#ai-agent) has access to a suite of tools, and determines which ones to use depending on the user input. Agents can use multiple tools, and use the output of one tool as the input to the next. [Source](https://github.com/langchain-ai/langchainjs/blob/def3a26c054575e1ed40b9062087e8c0a8899633/docs/core_docs/docs/modules/agents/index.mdx)\n\nAvailable nodes:\n\n- [Agent](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)\n\nLearn more about [Agents in LangChain](https://js.langchain.com/docs/concepts/agents).\n\n#### Vector stores\n\n[Vector stores](../../../glossary/#ai-vector-store) store embedded data, and perform vector searches on it.\n\n- [Simple Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreinmemory/)\n- [PGVector Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepgvector/)\n- [Pinecone Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/)\n- [Qdrant Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreqdrant/)\n- [Supabase Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/)\n- [Zep Vector Store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorezep/)\n\nLearn more about [Vector stores in LangChain](https://js.langchain.com/docs/concepts/vectorstores/).\n\n#### Miscellaneous\n\nUtility nodes.\n\n[LangChain Code](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.code/): import LangChain. This means if there is functionality you need that n8n hasn't created a node for, you can still use it.\n\n### Sub-nodes\n\nEach root node can have one or more [sub-nodes](../../../glossary/#sub-node-n8n) attached to it.\n\n#### Document loaders\n\nDocument loaders add data to your chain as documents. The data source can be a file or web service.\n\nAvailable nodes:\n\n- [Default Document Loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/)\n- [GitHub Document Loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentgithubloader/)\n\nLearn more about [Document loaders in LangChain](https://js.langchain.com/docs/concepts/document_loaders).\n\n#### Language models\n\n[LLMs (large language models)](../../../glossary/#large-language-model-llm) are programs that analyze datasets. They're the key element of working with AI.\n\nAvailable nodes:\n\n- [Anthropic Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatanthropic/)\n- [AWS Bedrock Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatawsbedrock/)\n- [Cohere Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmcohere/)\n- [Hugging Face Inference Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmopenhuggingfaceinference/)\n- [Mistral Cloud Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatmistralcloud/)\n- [Ollama Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatollama/)\n- [Ollama Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmollama/)\n- [OpenAI Chat Model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/)\n\nLearn more about [Language models in LangChain](https://js.langchain.com/docs/concepts/chat_models).\n\n#### Memory\n\n[Memory](../../../glossary/#ai-memory) retains information about previous queries in a series of queries. For example, when a user interacts with a chat model, it's useful if your application can remember and call on the full conversation, not just the most recent query entered by the user.\n\nAvailable nodes:\n\n- [Motorhead](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymotorhead/)\n- [Redis Chat Memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryredischat/)\n- [Postgres Chat Memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorypostgreschat/)\n- [Simple Memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/)\n- [Xata](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryxata/)\n- [Zep](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryzep/)\n\nLearn more about [Memory in LangChain](https://langchain-ai.github.io/langgraphjs/concepts/memory/).\n\n#### Output parsers\n\nOutput parsers take the text generated by an LLM and format it to match the structure you require.\n\nAvailable nodes:\n\n- [Auto-fixing Output Parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserautofixing/)\n- [Item List Output Parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparseritemlist/)\n- [Structured Output Parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserstructured/)\n\nLearn more about [Output parsers in LangChain](https://js.langchain.com/docs/concepts/output_parsers/).\n\n#### Retrievers\n\n- [Contextual Compression Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievercontextualcompression/)\n- [MultiQuery Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievermultiquery/)\n- [Vector Store Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievervectorstore/)\n- [Workflow Retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrieverworkflow/)\n\n#### Text splitters\n\nText splitters break down data (documents), making it easier for the LLM to process the information and return accurate results.\n\nAvailable nodes:\n\n- [Character Text Splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittercharactertextsplitter/)\n- [Recursive Character Text Splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplitterrecursivecharactertextsplitter/)\n- [Token Splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittertokensplitter/)\n\nn8n's text splitter nodes implements parts of [LangChain's text_splitter API](https://js.langchain.com/docs/concepts/text_splitters/).\n\n#### Tools\n\nUtility [tools](../../../glossary/#ai-tool).\n\n- [Calculator](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcalculator/)\n- [Code Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcode/)\n- [SerpAPI](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolserpapi/)\n- [Think Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolthink/)\n- [Vector Store Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolvectorstore/)\n- [Wikipedia](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwikipedia/)\n- [Wolfram|Alpha](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwolframalpha/)\n- [Workflow Tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolworkflow/)\n\n#### Embeddings\n\n> [Embeddings](../../../glossary/#ai-embedding) capture the \"relatedness\" of text, images, video, or other types of information. ([source](https://supabase.com/docs/guides/ai/concepts))\n\nAvailable nodes:\n\n- [Embeddings AWS Bedrock](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsawsbedrock/)\n- [Embeddings Cohere](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingscohere/)\n- [Embeddings Google PaLM](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsgooglepalm/)\n- [Embeddings Hugging Face Inference](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingshuggingfaceinference/)\n- [Embeddings Mistral Cloud](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsmistralcloud/)\n- [Embeddings Ollama](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsollama/)\n- [Embeddings OpenAI](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsopenai/)\n\nLearn more about [Text embeddings in LangChain](https://js.langchain.com/docs/concepts/embedding_models/).\n\n#### Miscellaneous\n\n- [Chat Memory Manager](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymanager/)\n",
+        "excerpt": "# LangChain concepts in n8n  This page explains how LangChain concepts and features map to n8n nodes.  This page includes lists of the LangChain-focused nodes in n8n. You can use any n8n node in a workflow where you interact with LangChain, to link LangChain to other services. The LangChain features uses n8n's [Cluster nodes](../../../integrations/builtin/cluster-nodes/).  n8n implements LangChain JS  This feature is n8n's implementation of [LangChain's JavaScript framework](https://js.langchain...",
+        "sections": [
+          {
+            "title": "LangChain concepts in n8n",
+            "level": 1,
+            "content": "This page explains how LangChain concepts and features map to n8n nodes.\n\nThis page includes lists of the LangChain-focused nodes in n8n. You can use any n8n node in a workflow where you interact with LangChain, to link LangChain to other services. The LangChain features uses n8n's [Cluster nodes](../../../integrations/builtin/cluster-nodes/).\n\nn8n implements LangChain JS\n\nThis feature is n8n's implementation of [LangChain's JavaScript framework](https://js.langchain.com/docs/get_started/introduction)."
+          }
+        ]
+      },
+      "metadata": {
+        "keywords": [
+          "langchain",
+          "concepts",
+          "trigger",
+          "nodes",
+          "cluster",
+          "root",
+          "chains",
+          "agents",
+          "vector",
+          "stores",
+          "miscellaneous",
+          "document",
+          "loaders",
+          "language",
+          "models",
+          "memory",
+          "output",
+          "parsers",
+          "retrievers",
+          "text",
+          "splitters",
+          "tools",
+          "embeddings"
+        ],
+        "useCases": [],
+        "operations": [],
+        "codeExamples": 0,
         "complexity": "intermediate",
         "readingTime": "4 min",
         "contentLength": 10758,
         "relatedPages": []
       },
       "searchIndex": {
-        "fullText": "populate a pinecone vector database from a website # langchain concepts in n8n\n\nthis page explains how langchain concepts and features map to n8n nodes.\n\nthis page includes lists of the langchain-focused nodes in n8n. you can use any n8n node in a workflow where you interact with langchain, to link langchain to other services. the langchain features uses n8n's [cluster nodes](../../../integrations/builtin/cluster-nodes/).\n\nn8n implements langchain js\n\nthis feature is n8n's implementation of [langchain's javascript framework](https://js.langchain.com/docs/get_started/introduction).\n\n## trigger nodes\n\n[chat trigger](../../../integrations/builtin/core-nodes/n8n-nodes-langchain.chattrigger/)\n\n## cluster nodes\n\n[cluster nodes](../../../glossary/#cluster-node-n8n) are node groups that work together to provide functionality in an n8n workflow. instead of using a single node, you use a [root node](../../../glossary/#root-node-n8n) and one or more [sub-nodes](../../../glossary/#sub-node-n8n) that extend the functionality of the node.\n\n### root nodes\n\neach cluster starts with one [root node](../../../glossary/#root-node-n8n).\n\n#### chains\n\na [chain](../../../glossary/#ai-chain) is a series of llms, and related tools, linked together to support functionality that can't be provided by a single llm alone.\n\navailable nodes:\n\n- [basic llm chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm/)\n- [retrieval q&a chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa/)\n- [summarization chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainsummarization/)\n- [sentiment analysis](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.sentimentanalysis/)\n- [text classifier](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.text-classifier/)\n\nlearn more about [chaining in langchain](https://js.langchain.com/docs/concepts/lcel).\n\n#### agents\n\n> an [agent](../../../glossary/#ai-agent) has access to a suite of tools, and determines which ones to use depending on the user input. agents can use multiple tools, and use the output of one tool as the input to the next. [source](https://github.com/langchain-ai/langchainjs/blob/def3a26c054575e1ed40b9062087e8c0a8899633/docs/core_docs/docs/modules/agents/index.mdx)\n\navailable nodes:\n\n- [agent](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)\n\nlearn more about [agents in langchain](https://js.langchain.com/docs/concepts/agents).\n\n#### vector stores\n\n[vector stores](../../../glossary/#ai-vector-store) store embedded data, and perform vector searches on it.\n\n- [simple vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreinmemory/)\n- [pgvector vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepgvector/)\n- [pinecone vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/)\n- [qdrant vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreqdrant/)\n- [supabase vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/)\n- [zep vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorezep/)\n\nlearn more about [vector stores in langchain](https://js.langchain.com/docs/concepts/vectorstores/).\n\n#### miscellaneous\n\nutility nodes.\n\n[langchain code](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.code/): import langchain. this means if there is functionality you need that n8n hasn't created a node for, you can still use it.\n\n### sub-nodes\n\neach root node can have one or more [sub-nodes](../../../glossary/#sub-node-n8n) attached to it.\n\n#### document loaders\n\ndocument loaders add data to your chain as documents. the data source can be a file or web service.\n\navailable nodes:\n\n- [default document loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/)\n- [github document loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentgithubloader/)\n\nlearn more about [document loaders in langchain](https://js.langchain.com/docs/concepts/document_loaders).\n\n#### language models\n\n[llms (large language models)](../../../glossary/#large-language-model-llm) are programs that analyze datasets. they're the key element of working with ai.\n\navailable nodes:\n\n- [anthropic chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatanthropic/)\n- [aws bedrock chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatawsbedrock/)\n- [cohere model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmcohere/)\n- [hugging face inference model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmopenhuggingfaceinference/)\n- [mistral cloud chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatmistralcloud/)\n- [ollama chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatollama/)\n- [ollama model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmollama/)\n- [openai chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/)\n\nlearn more about [language models in langchain](https://js.langchain.com/docs/concepts/chat_models).\n\n#### memory\n\n[memory](../../../glossary/#ai-memory) retains information about previous queries in a series of queries. for example, when a user interacts with a chat model, it's useful if your application can remember and call on the full conversation, not just the most recent query entered by the user.\n\navailable nodes:\n\n- [motorhead](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymotorhead/)\n- [redis chat memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryredischat/)\n- [postgres chat memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorypostgreschat/)\n- [simple memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/)\n- [xata](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryxata/)\n- [zep](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryzep/)\n\nlearn more about [memory in langchain](https://langchain-ai.github.io/langgraphjs/concepts/memory/).\n\n#### output parsers\n\noutput parsers take the text generated by an llm and format it to match the structure you require.\n\navailable nodes:\n\n- [auto-fixing output parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserautofixing/)\n- [item list output parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparseritemlist/)\n- [structured output parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserstructured/)\n\nlearn more about [output parsers in langchain](https://js.langchain.com/docs/concepts/output_parsers/).\n\n#### retrievers\n\n- [contextual compression retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievercontextualcompression/)\n- [multiquery retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievermultiquery/)\n- [vector store retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievervectorstore/)\n- [workflow retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrieverworkflow/)\n\n#### text splitters\n\ntext splitters break down data (documents), making it easier for the llm to process the information and return accurate results.\n\navailable nodes:\n\n- [character text splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittercharactertextsplitter/)\n- [recursive character text splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplitterrecursivecharactertextsplitter/)\n- [token splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittertokensplitter/)\n\nn8n's text splitter nodes implements parts of [langchain's text_splitter api](https://js.langchain.com/docs/concepts/text_splitters/).\n\n#### tools\n\nutility [tools](../../../glossary/#ai-tool).\n\n- [calculator](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcalculator/)\n- [code tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcode/)\n- [serpapi](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolserpapi/)\n- [think tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolthink/)\n- [vector store tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolvectorstore/)\n- [wikipedia](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwikipedia/)\n- [wolfram|alpha](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwolframalpha/)\n- [workflow tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolworkflow/)\n\n#### embeddings\n\n> [embeddings](../../../glossary/#ai-embedding) capture the \"relatedness\" of text, images, video, or other types of information. ([source](https://supabase.com/docs/guides/ai/concepts))\n\navailable nodes:\n\n- [embeddings aws bedrock](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsawsbedrock/)\n- [embeddings cohere](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingscohere/)\n- [embeddings google palm](../../../integrations/builtin/clus",
+        "fullText": "langchain concepts in n8n # langchain concepts in n8n\n\nthis page explains how langchain concepts and features map to n8n nodes.\n\nthis page includes lists of the langchain-focused nodes in n8n. you can use any n8n node in a workflow where you interact with langchain, to link langchain to other services. the langchain features uses n8n's [cluster nodes](../../../integrations/builtin/cluster-nodes/).\n\nn8n implements langchain js\n\nthis feature is n8n's implementation of [langchain's javascript framework](https://js.langchain.com/docs/get_started/introduction).\n\n## trigger nodes\n\n[chat trigger](../../../integrations/builtin/core-nodes/n8n-nodes-langchain.chattrigger/)\n\n## cluster nodes\n\n[cluster nodes](../../../glossary/#cluster-node-n8n) are node groups that work together to provide functionality in an n8n workflow. instead of using a single node, you use a [root node](../../../glossary/#root-node-n8n) and one or more [sub-nodes](../../../glossary/#sub-node-n8n) that extend the functionality of the node.\n\n### root nodes\n\neach cluster starts with one [root node](../../../glossary/#root-node-n8n).\n\n#### chains\n\na [chain](../../../glossary/#ai-chain) is a series of llms, and related tools, linked together to support functionality that can't be provided by a single llm alone.\n\navailable nodes:\n\n- [basic llm chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainllm/)\n- [retrieval q&a chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainretrievalqa/)\n- [summarization chain](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.chainsummarization/)\n- [sentiment analysis](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.sentimentanalysis/)\n- [text classifier](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.text-classifier/)\n\nlearn more about [chaining in langchain](https://js.langchain.com/docs/concepts/lcel).\n\n#### agents\n\n> an [agent](../../../glossary/#ai-agent) has access to a suite of tools, and determines which ones to use depending on the user input. agents can use multiple tools, and use the output of one tool as the input to the next. [source](https://github.com/langchain-ai/langchainjs/blob/def3a26c054575e1ed40b9062087e8c0a8899633/docs/core_docs/docs/modules/agents/index.mdx)\n\navailable nodes:\n\n- [agent](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent/)\n\nlearn more about [agents in langchain](https://js.langchain.com/docs/concepts/agents).\n\n#### vector stores\n\n[vector stores](../../../glossary/#ai-vector-store) store embedded data, and perform vector searches on it.\n\n- [simple vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreinmemory/)\n- [pgvector vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepgvector/)\n- [pinecone vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/)\n- [qdrant vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreqdrant/)\n- [supabase vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/)\n- [zep vector store](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorezep/)\n\nlearn more about [vector stores in langchain](https://js.langchain.com/docs/concepts/vectorstores/).\n\n#### miscellaneous\n\nutility nodes.\n\n[langchain code](../../../integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.code/): import langchain. this means if there is functionality you need that n8n hasn't created a node for, you can still use it.\n\n### sub-nodes\n\neach root node can have one or more [sub-nodes](../../../glossary/#sub-node-n8n) attached to it.\n\n#### document loaders\n\ndocument loaders add data to your chain as documents. the data source can be a file or web service.\n\navailable nodes:\n\n- [default document loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/)\n- [github document loader](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.documentgithubloader/)\n\nlearn more about [document loaders in langchain](https://js.langchain.com/docs/concepts/document_loaders).\n\n#### language models\n\n[llms (large language models)](../../../glossary/#large-language-model-llm) are programs that analyze datasets. they're the key element of working with ai.\n\navailable nodes:\n\n- [anthropic chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatanthropic/)\n- [aws bedrock chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatawsbedrock/)\n- [cohere model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmcohere/)\n- [hugging face inference model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmopenhuggingfaceinference/)\n- [mistral cloud chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatmistralcloud/)\n- [ollama chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatollama/)\n- [ollama model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmollama/)\n- [openai chat model](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.lmchatopenai/)\n\nlearn more about [language models in langchain](https://js.langchain.com/docs/concepts/chat_models).\n\n#### memory\n\n[memory](../../../glossary/#ai-memory) retains information about previous queries in a series of queries. for example, when a user interacts with a chat model, it's useful if your application can remember and call on the full conversation, not just the most recent query entered by the user.\n\navailable nodes:\n\n- [motorhead](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorymotorhead/)\n- [redis chat memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryredischat/)\n- [postgres chat memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorypostgreschat/)\n- [simple memory](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorybufferwindow/)\n- [xata](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryxata/)\n- [zep](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memoryzep/)\n\nlearn more about [memory in langchain](https://langchain-ai.github.io/langgraphjs/concepts/memory/).\n\n#### output parsers\n\noutput parsers take the text generated by an llm and format it to match the structure you require.\n\navailable nodes:\n\n- [auto-fixing output parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserautofixing/)\n- [item list output parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparseritemlist/)\n- [structured output parser](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.outputparserstructured/)\n\nlearn more about [output parsers in langchain](https://js.langchain.com/docs/concepts/output_parsers/).\n\n#### retrievers\n\n- [contextual compression retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievercontextualcompression/)\n- [multiquery retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievermultiquery/)\n- [vector store retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrievervectorstore/)\n- [workflow retriever](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.retrieverworkflow/)\n\n#### text splitters\n\ntext splitters break down data (documents), making it easier for the llm to process the information and return accurate results.\n\navailable nodes:\n\n- [character text splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittercharactertextsplitter/)\n- [recursive character text splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplitterrecursivecharactertextsplitter/)\n- [token splitter](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.textsplittertokensplitter/)\n\nn8n's text splitter nodes implements parts of [langchain's text_splitter api](https://js.langchain.com/docs/concepts/text_splitters/).\n\n#### tools\n\nutility [tools](../../../glossary/#ai-tool).\n\n- [calculator](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcalculator/)\n- [code tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolcode/)\n- [serpapi](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolserpapi/)\n- [think tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolthink/)\n- [vector store tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolvectorstore/)\n- [wikipedia](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwikipedia/)\n- [wolfram|alpha](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolwolframalpha/)\n- [workflow tool](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.toolworkflow/)\n\n#### embeddings\n\n> [embeddings](../../../glossary/#ai-embedding) capture the \"relatedness\" of text, images, video, or other types of information. ([source](https://supabase.com/docs/guides/ai/concepts))\n\navailable nodes:\n\n- [embeddings aws bedrock](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingsawsbedrock/)\n- [embeddings cohere](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.embeddingscohere/)\n- [embeddings google palm](../../../integrations/builtin/cluster-nodes/sub-nodes/n8n-n",
         "importantTerms": [
           "nodes",
           "langchain",
@@ -4885,9 +5115,9 @@
           "integrations",
           "builtin",
           "root",
-          "vector",
           "concepts",
           "node",
+          "vector",
           "https",
           "docs",
           "glossary",
@@ -18552,13 +18782,13 @@
       "nodeName": null,
       "nodeType": null,
       "content": {
-        "markdown": "# OpenTelemetry tracing\n\nThis feature is still under development - Initially available from 2.19.0\n\nAgent telemetry and open telemetry formatted metrics will be coming soon\n\nn8n can emit [OpenTelemetry](https://opentelemetry.io/) traces for workflow and node executions. Use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.\n\nFeature availability\n\nOpenTelemetry workflow tracing requires environment variables to be set, so it's available on self-hosted n8n only.\n\n## What you get\n\nWhen you turn on tracing, n8n exports two kinds of spans for each execution:\n\n- **`workflow.execute`**: One span per workflow execution. It records the workflow ID, name, version, node count, execution mode, status, and any error type.\n- **`node.execute`**: One span per node execution, nested inside its workflow span. It records the node ID, name, type, version, and the number of input and output items.\n\nEach span includes resource attributes that identify the n8n instance:\n\n- `service.name` (default `n8n`)\n- `service.version` (the n8n version)\n- `n8n.instance.id`\n- `n8n.instance.role` (for example, `main`, `worker`, or `webhook`)\n\nn8n also handles trace context propagation:\n\n- **Inbound**: If a webhook request includes a [W3C `traceparent` header](https://www.w3.org/TR/trace-context/), n8n uses it as the parent for the workflow span. This links the n8n workflow trace to the upstream caller.\n- **Outbound**: HTTP Request nodes (and other nodes that use the n8n HTTP helpers) can inject a `traceparent` header into outbound requests. Downstream services that support W3C trace context can therefore continue the trace.\n- **Sub-workflows**: A sub-workflow's span uses the parent workflow's span as its parent.\n- **Resumed workflows**: When a workflow resumes after a wait, the new span links back to the previous span using a span link.\n\n## Enable tracing\n\nSet the following environment variables on each n8n instance you want workflow tracing enabled (main, workers, and webhook processors):\n\n```\nexport N8N_OTEL_ENABLED=true\nexport N8N_OTEL_EXPORTER_OTLP_ENDPOINT=http://<your-collector-host>:4318\n```\n\nRestart n8n. The instance starts exporting spans over OTLP HTTP using the Protobuf encoding.\n\nn8n appends `/v1/traces` to the endpoint by default. Point `N8N_OTEL_EXPORTER_OTLP_ENDPOINT` at the base URL of your collector, not the traces path.\n\nIf your collector needs authentication, set `N8N_OTEL_EXPORTER_OTLP_HEADERS` to a comma-separated list of `key=value` pairs:\n\n```\nexport N8N_OTEL_EXPORTER_OTLP_HEADERS=\"authorization=Bearer <your-token>,x-tenant=acme\"\n\n// For added protection - It is recommended to use the `_FILE` postfix if you are putting a token in here:\nexport N8N_OTEL_EXPORTER_OTLP_HEADERS_FILE=/mnt/otel-headers\n```\n\nFor the full list of supported variables, refer to [OpenTelemetry environment variables](../../configuration/environment-variables/opentelemetry/).\n\nQueue mode\n\nIn [queue mode](../../scaling/queue-mode/), set the OpenTelemetry variables on the main, worker, and webhook instances. Trace context is propagated between main, worker and webhook instances.\n\n## Sampling\n\nBy default, n8n exports every trace. To reduce volume in busy instances, set `N8N_OTEL_TRACES_SAMPLE_RATE` to a value between `0` and `1`:\n\n```\n# Export 10% of traces\nexport N8N_OTEL_TRACES_SAMPLE_RATE=0.1\n```\n\nn8n uses a trace ID ratio sampler, so the same trace ID is either fully sampled or fully dropped across all spans in the trace.\n\nn8n will output a trace for every workflow execution - this includes published workflows, unpublished workflows and test executions - In a future release a toggle will be available to track only published workflows\n\n## Reduce span volume\n\nEach node in a workflow produces its own span. For workflows with lots of nodes, this can produce more data than you need. To export only workflow-level spans, set:\n\n```\nexport N8N_OTEL_TRACES_INCLUDE_NODE_SPANS=false\n```\n\nTo stop n8n from injecting `traceparent` headers into outbound HTTP requests, set:\n\n```\nexport N8N_OTEL_TRACES_INJECT_OUTBOUND=false\n```\n\n## Add custom attributes to node spans\n\nIf you're [building a custom node](../../../integrations/creating-nodes/overview/), you can attach custom key-value pairs to the node's span. Call `setMetadata` from the node's `execute` method:\n\n```\nasync execute(this: IExecuteFunctions): Promise<INodeExecutionData[][]> {\n\tthis.setMetadata({\n\t\ttracing: {\n\t\t\t'llm.model': 'gpt-4o',\n\t\t\t'llm.token.input': 1500,\n\t\t\t'llm.token.output': 340,\n\t\t},\n\t});\n\n\treturn [this.getInputData()];\n}\n```\n\nn8n prefixes each key with `n8n.node.custom.` on the exported span. Values must be strings, numbers, or boolean.\n\nThis API isn't available from the Code node. It's intended for node authors who want to enrich spans with domain-specific data.\n\n## Try it out with Jaeger\n\nYou can send traces to a local [Jaeger](https://www.jaegertracing.io/) instance to see them in action.\n\n1. Save the following as `docker-compose.yml`:\n\n```\nservices:\n  jaeger:\n    image: jaegertracing/jaeger:latest\n    ports:\n      - \"16686:16686\" # UI\n      - \"4317:4317\"   # OTLP gRPC\n      - \"4318:4318\"   # OTLP HTTP\n```\n\n2. Start Jaeger:\n\n```\ndocker compose up -d\n```\n\n3. Start n8n with tracing turned on and pointed at Jaeger. Information about [starting n8n](https://github.com/n8n-io/n8n/blob/master/CONTRIBUTING.md) can be found elsewhere in this documentation:\n\n```\nN8N_OTEL_ENABLED=true N8N_OTEL_EXPORTER_OTLP_ENDPOINT=http://127.0.0.1:4318 n8n start\n```\n\n5. Run a workflow, then open the Jaeger UI at <http://localhost:16686> - Select \"n8n\" as service\" and click \"Find traces\" to see the OpenTelemetry traces emitted by n8n.\n\n## Span attributes\n\nWorkflow and node spans include the following n8n-specific attributes.\n\n### Workflow span (`workflow.execute`)\n\n| Attribute                  | Description                                                            |\n| -------------------------- | ---------------------------------------------------------------------- |\n| `n8n.workflow.id`          | Workflow ID.                                                           |\n| `n8n.workflow.name`        | Workflow name.                                                         |\n| `n8n.workflow.version_id`  | Workflow version ID.                                                   |\n| `n8n.workflow.node_count`  | Number of nodes in the workflow.                                       |\n| `n8n.execution.id`         | Execution ID.                                                          |\n| `n8n.execution.mode`       | Execution mode (for example, `manual`, `webhook`, `trigger`, `retry`). |\n| `n8n.execution.status`     | Final execution status.                                                |\n| `n8n.execution.is_retry`   | `true` if the execution is a retry.                                    |\n| `n8n.execution.retry_of`   | The original execution ID, when the execution is a retry.              |\n| `n8n.execution.error_type` | Error class name, set when the execution fails.                        |\n| `n8n.continuation.reason`  | Set on a span link when the workflow resumes after a wait.             |\n\n### Node span (`node.execute`)\n\n| Attribute                     | Description                                                                            |\n| ----------------------------- | -------------------------------------------------------------------------------------- |\n| `n8n.node.id`                 | Node ID.                                                                               |\n| `n8n.node.name`               | Node name.                                                                             |\n| `n8n.node.type`               | Node type (for example, `n8n-nodes-base.httpRequest`).                                 |\n| `n8n.node.type_version`       | Node type version.                                                                     |\n| `n8n.node.items.input`        | Number of input items the node received.                                               |\n| `n8n.node.items.output`       | Number of output items the node produced.                                              |\n| `n8n.node.termination_reason` | Why a node span ended without a normal completion (for example, `workflow_cancelled`). |\n| `n8n.node.custom.<key>`       | Custom attributes set through `metadata.tracing` in the node output.                   |\n\nWhen a node fails, n8n records an `exception` event on the span with the standard OpenTelemetry exception attributes (`exception.type`, `exception.message`, `exception.stacktrace`).\n\n## Troubleshooting\n\n### No traces appear in your backend\n\nIf n8n can't reach the OTLP endpoint at startup, it logs an error:\n\n```\nFailed to connect to OpenTelemetry OTLP endpoint during startup\n```\n\nCheck that:\n\n- `N8N_OTEL_ENABLED` is set to `true`.\n- `N8N_OTEL_EXPORTER_OTLP_ENDPOINT` points at the base URL of the collector (not the `/v1/traces` path).\n- The collector is reachable from the n8n container or host.\n- Any required `N8N_OTEL_EXPORTER_OTLP_HEADERS` (such as authentication tokens) are set.\n\nn8n logs OpenTelemetry diagnostics at `warn` level by default. Set `N8N_LOG_LEVEL=debug` to see more detail.\n\n### Worker traces are missing parent context\n\nIn queue mode, workers read the parent trace context from the database. If you only set the OpenTelemetry environment variables on the main instance, worker spans won't link to the parent workflow trace. Set the same variables on every instance type.\n\n## Related resources\n\n- [OpenTelemetry environment variables](../../configuration/environment-variables/opentelemetry/)\n- [W3C Trace Context specification](https://www.w3.org/TR/trace-context/)\n- [OpenTelemetry Collector documentation](https://opentelemetry.io/docs/collector/)\n- [Logging in n8n](../logging/)\n- [Monitoring](../monitoring/)\n",
-        "excerpt": "# OpenTelemetry tracing  This feature is still under development - Initially available from 2.19.0  Agent telemetry and open telemetry formatted metrics will be coming soon  n8n can emit [OpenTelemetry](https://opentelemetry.io/) traces for workflow and node executions. Use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.  Feature availability  OpenTelemetry workflow tracing requires environment variables to be set, so it'...",
+        "markdown": "# OpenTelemetry tracing\n\nThis feature is still under development\n\n- Initially available from 2.19.0\n- Open telemetry formatted metrics will be coming soon\n\nn8n can emit [OpenTelemetry](https://opentelemetry.io/) traces for workflow and node executions. Use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.\n\nFeature availability\n\nOpenTelemetry workflow tracing is only available on self-hosted n8n.\n\n## What you get\n\nWhen you turn on tracing, n8n exports two kinds of spans for each execution:\n\n- **`workflow.execute`**: One span per workflow execution. It records the workflow ID, name, version, node count, execution mode, status, and any error type.\n- **`node.execute`**: One span per node execution, nested inside its workflow span. It records the node ID, name, type, version, and the number of input and output items.\n\nEach span includes resource attributes that identify the n8n instance:\n\n- `service.name` (default `n8n`)\n- `service.version` (the n8n version)\n- `n8n.instance.id`\n- `n8n.instance.role` (for example, `main`, `worker`, or `webhook`)\n\nn8n also handles trace context propagation:\n\n- **Inbound**: If a webhook request includes a [W3C `traceparent` header](https://www.w3.org/TR/trace-context/), n8n uses it as the parent for the workflow span. This links the n8n workflow trace to the upstream caller.\n- **Outbound**: HTTP Request nodes (and other nodes that use the n8n HTTP helpers) can inject a `traceparent` header into outbound requests. Downstream services that support W3C trace context can therefore continue the trace.\n- **Sub-workflows**: A sub-workflow's span uses the parent workflow's span as its parent.\n- **Resumed workflows**: When a workflow resumes after a wait, the new span links back to the previous span using a span link.\n\n## Enable tracing\n\nSet the following environment variables on each n8n instance you want workflow tracing enabled (main, workers, and webhook processors):\n\n```\nexport N8N_OTEL_ENABLED=true\nexport N8N_OTEL_EXPORTER_OTLP_ENDPOINT=http://<your-collector-host>:4318\n```\n\nRestart n8n. The instance starts exporting spans over OTLP HTTP using the Protobuf encoding.\n\nn8n appends `/v1/traces` to the endpoint by default. Point `N8N_OTEL_EXPORTER_OTLP_ENDPOINT` at the base URL of your collector, not the traces path.\n\nIf your collector needs authentication, set `N8N_OTEL_EXPORTER_OTLP_HEADERS` to a comma-separated list of `key=value` pairs:\n\n```\nexport N8N_OTEL_EXPORTER_OTLP_HEADERS=\"authorization=Bearer <your-token>,x-tenant=acme\"\n\n// For added protection - It is recommended to use the `_FILE` postfix if you are putting a token in here:\nexport N8N_OTEL_EXPORTER_OTLP_HEADERS_FILE=/mnt/otel-headers\n```\n\nFor the full list of supported variables, refer to [OpenTelemetry environment variables](../../configuration/environment-variables/opentelemetry/).\n\nQueue mode\n\nIn [queue mode](../../scaling/queue-mode/), the OpenTelemetry variables must be set on all instances. Trace context is propagated between instances.\n\n## Sampling\n\nBy default, n8n exports every trace. To reduce volume in busy instances, set `N8N_OTEL_TRACES_SAMPLE_RATE` to a value between `0` and `1`:\n\n```\n# Export 10% of traces\nexport N8N_OTEL_TRACES_SAMPLE_RATE=0.1\n```\n\nn8n uses a trace ID ratio sampler, so the same trace ID is either fully sampled or fully dropped across all spans in the trace.\n\nn8n will output a trace for every workflow execution - this includes published workflows, unpublished workflows and test executions - In a future release a toggle will be available to track only published workflows\n\n## Reduce span volume\n\nEach node in a workflow produces its own span. For workflows with lots of nodes, this can produce more data than you need. To export only workflow-level spans, set:\n\n```\nexport N8N_OTEL_TRACES_INCLUDE_NODE_SPANS=false\n```\n\nTo stop n8n from injecting `traceparent` headers into outbound HTTP requests, set:\n\n```\nexport N8N_OTEL_TRACES_INJECT_OUTBOUND=false\n```\n\n## Add custom attributes to node spans\n\nIf you're [building a custom node](../../../integrations/creating-nodes/overview/), you can attach custom key-value pairs to the node's span. Call `setMetadata` from the node's `execute` method:\n\n```\nasync execute(this: IExecuteFunctions): Promise<INodeExecutionData[][]> {\n\tthis.setMetadata({\n\t\ttracing: {\n\t\t\t'llm.model': 'gpt-4o',\n\t\t\t'llm.token.input': 1500,\n\t\t\t'llm.token.output': 340,\n\t\t},\n\t});\n\n\treturn [this.getInputData()];\n}\n```\n\nn8n prefixes each key with `n8n.node.custom.` on the exported span. Values must be strings, numbers, or boolean.\n\nThis API isn't available from the Code node. It's intended for node authors who want to enrich spans with domain-specific data.\n\n## Try it out with Jaeger\n\nYou can send traces to a local [Jaeger](https://www.jaegertracing.io/) instance to see them in action.\n\n1. Save the following as `docker-compose.yml`:\n\n```\nservices:\n  jaeger:\n    image: jaegertracing/jaeger:latest\n    ports:\n      - \"16686:16686\" # UI\n      - \"4317:4317\"   # OTLP gRPC\n      - \"4318:4318\"   # OTLP HTTP\n```\n\n2. Start Jaeger:\n\n```\ndocker compose up -d\n```\n\n3. Start n8n with tracing turned on and pointed at Jaeger. Information about [starting n8n](https://github.com/n8n-io/n8n/blob/master/CONTRIBUTING.md) can be found elsewhere in this documentation:\n\n```\nN8N_OTEL_ENABLED=true N8N_OTEL_EXPORTER_OTLP_ENDPOINT=http://127.0.0.1:4318 n8n start\n```\n\n5. Run a workflow, then open the Jaeger UI at <http://localhost:16686> - Select \"n8n\" as service\" and click \"Find traces\" to see the OpenTelemetry traces emitted by n8n.\n\n## Span attributes\n\nWorkflow and node spans include the following n8n-specific attributes.\n\n### Workflow span (`workflow.execute`)\n\n| Attribute                  | Description                                                            |\n| -------------------------- | ---------------------------------------------------------------------- |\n| `n8n.workflow.id`          | Workflow ID.                                                           |\n| `n8n.workflow.name`        | Workflow name.                                                         |\n| `n8n.workflow.version_id`  | Workflow version ID.                                                   |\n| `n8n.workflow.node_count`  | Number of nodes in the workflow.                                       |\n| `n8n.execution.id`         | Execution ID.                                                          |\n| `n8n.execution.mode`       | Execution mode (for example, `manual`, `webhook`, `trigger`, `retry`). |\n| `n8n.execution.status`     | Final execution status.                                                |\n| `n8n.execution.is_retry`   | `true` if the execution is a retry.                                    |\n| `n8n.execution.retry_of`   | The original execution ID, when the execution is a retry.              |\n| `n8n.execution.error_type` | Error class name, set when the execution fails.                        |\n| `n8n.continuation.reason`  | Set on a span link when the workflow resumes after a wait.             |\n\n### Node span (`node.execute`)\n\n| Attribute                     | Description                                                                            |\n| ----------------------------- | -------------------------------------------------------------------------------------- |\n| `n8n.node.id`                 | Node ID.                                                                               |\n| `n8n.node.name`               | Node name.                                                                             |\n| `n8n.node.type`               | Node type (for example, `n8n-nodes-base.httpRequest`).                                 |\n| `n8n.node.type_version`       | Node type version.                                                                     |\n| `n8n.node.items.input`        | Number of input items the node received.                                               |\n| `n8n.node.items.output`       | Number of output items the node produced.                                              |\n| `n8n.node.termination_reason` | Why a node span ended without a normal completion (for example, `workflow_cancelled`). |\n| `n8n.node.custom.<key>`       | Custom attributes set through `metadata.tracing` in the node output.                   |\n\nWhen a node fails, n8n records an `exception` event on the span with the standard OpenTelemetry exception attributes (`exception.type`, `exception.message`, `exception.stacktrace`).\n\n## Troubleshooting\n\n### No traces appear in your backend\n\nIf n8n can't reach the OTLP endpoint at startup, it logs an error:\n\n```\nFailed to connect to OpenTelemetry OTLP endpoint during startup\n```\n\nCheck that:\n\n- `N8N_OTEL_ENABLED` is set to `true`.\n- `N8N_OTEL_EXPORTER_OTLP_ENDPOINT` points at the base URL of the collector (not the `/v1/traces` path).\n- The collector is reachable from the n8n container or host.\n- Any required `N8N_OTEL_EXPORTER_OTLP_HEADERS` (such as authentication tokens) are set.\n\nn8n logs OpenTelemetry diagnostics at `warn` level by default. Set `N8N_LOG_LEVEL=debug` to see more detail.\n\n### Worker traces are missing parent context\n\nIn queue mode, workers read the parent trace context from the database. If you only set the OpenTelemetry environment variables on the main instance, worker spans won't link to the parent workflow trace. Set the same variables on every instance type.\n\n## Related resources\n\n- [OpenTelemetry environment variables](../../configuration/environment-variables/opentelemetry/)\n- [W3C Trace Context specification](https://www.w3.org/TR/trace-context/)\n- [OpenTelemetry Collector documentation](https://opentelemetry.io/docs/collector/)\n- [Logging in n8n](../logging/)\n- [Monitoring](../monitoring/)\n",
+        "excerpt": "# OpenTelemetry tracing  This feature is still under development  - Initially available from 2.19.0 - Open telemetry formatted metrics will be coming soon  n8n can emit [OpenTelemetry](https://opentelemetry.io/) traces for workflow and node executions. Use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.  Feature availability  OpenTelemetry workflow tracing is only available on self-hosted n8n.  ## What you get  When you t...",
         "sections": [
           {
             "title": "OpenTelemetry tracing",
             "level": 1,
-            "content": "This feature is still under development - Initially available from 2.19.0\n\nAgent telemetry and open telemetry formatted metrics will be coming soon\n\nn8n can emit [OpenTelemetry](https://opentelemetry.io/) traces for workflow and node executions. Use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.\n\nFeature availability\n\nOpenTelemetry workflow tracing requires environment variables to be set, so it's available on self-hosted n8n only."
+            "content": "This feature is still under development\n\n- Initially available from 2.19.0\n- Open telemetry formatted metrics will be coming soon\n\nn8n can emit [OpenTelemetry](https://opentelemetry.io/) traces for workflow and node executions. Use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.\n\nFeature availability\n\nOpenTelemetry workflow tracing is only available on self-hosted n8n."
           },
           {
             "title": "Export 10% of traces",
@@ -18605,11 +18835,11 @@
         "codeExamples": 10,
         "complexity": "intermediate",
         "readingTime": "6 min",
-        "contentLength": 9887,
+        "contentLength": 9779,
         "relatedPages": []
       },
       "searchIndex": {
-        "fullText": "opentelemetry tracing # opentelemetry tracing\n\nthis feature is still under development - initially available from 2.19.0\n\nagent telemetry and open telemetry formatted metrics will be coming soon\n\nn8n can emit [opentelemetry](https://opentelemetry.io/) traces for workflow and node executions. use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.\n\nfeature availability\n\nopentelemetry workflow tracing requires environment variables to be set, so it's available on self-hosted n8n only.\n\n## what you get\n\nwhen you turn on tracing, n8n exports two kinds of spans for each execution:\n\n- **`workflow.execute`**: one span per workflow execution. it records the workflow id, name, version, node count, execution mode, status, and any error type.\n- **`node.execute`**: one span per node execution, nested inside its workflow span. it records the node id, name, type, version, and the number of input and output items.\n\neach span includes resource attributes that identify the n8n instance:\n\n- `service.name` (default `n8n`)\n- `service.version` (the n8n version)\n- `n8n.instance.id`\n- `n8n.instance.role` (for example, `main`, `worker`, or `webhook`)\n\nn8n also handles trace context propagation:\n\n- **inbound**: if a webhook request includes a [w3c `traceparent` header](https://www.w3.org/tr/trace-context/), n8n uses it as the parent for the workflow span. this links the n8n workflow trace to the upstream caller.\n- **outbound**: http request nodes (and other nodes that use the n8n http helpers) can inject a `traceparent` header into outbound requests. downstream services that support w3c trace context can therefore continue the trace.\n- **sub-workflows**: a sub-workflow's span uses the parent workflow's span as its parent.\n- **resumed workflows**: when a workflow resumes after a wait, the new span links back to the previous span using a span link.\n\n## enable tracing\n\nset the following environment variables on each n8n instance you want workflow tracing enabled (main, workers, and webhook processors):\n\n```\nexport n8n_otel_enabled=true\nexport n8n_otel_exporter_otlp_endpoint=http://<your-collector-host>:4318\n```\n\nrestart n8n. the instance starts exporting spans over otlp http using the protobuf encoding.\n\nn8n appends `/v1/traces` to the endpoint by default. point `n8n_otel_exporter_otlp_endpoint` at the base url of your collector, not the traces path.\n\nif your collector needs authentication, set `n8n_otel_exporter_otlp_headers` to a comma-separated list of `key=value` pairs:\n\n```\nexport n8n_otel_exporter_otlp_headers=\"authorization=bearer <your-token>,x-tenant=acme\"\n\n// for added protection - it is recommended to use the `_file` postfix if you are putting a token in here:\nexport n8n_otel_exporter_otlp_headers_file=/mnt/otel-headers\n```\n\nfor the full list of supported variables, refer to [opentelemetry environment variables](../../configuration/environment-variables/opentelemetry/).\n\nqueue mode\n\nin [queue mode](../../scaling/queue-mode/), set the opentelemetry variables on the main, worker, and webhook instances. trace context is propagated between main, worker and webhook instances.\n\n## sampling\n\nby default, n8n exports every trace. to reduce volume in busy instances, set `n8n_otel_traces_sample_rate` to a value between `0` and `1`:\n\n```\n# export 10% of traces\nexport n8n_otel_traces_sample_rate=0.1\n```\n\nn8n uses a trace id ratio sampler, so the same trace id is either fully sampled or fully dropped across all spans in the trace.\n\nn8n will output a trace for every workflow execution - this includes published workflows, unpublished workflows and test executions - in a future release a toggle will be available to track only published workflows\n\n## reduce span volume\n\neach node in a workflow produces its own span. for workflows with lots of nodes, this can produce more data than you need. to export only workflow-level spans, set:\n\n```\nexport n8n_otel_traces_include_node_spans=false\n```\n\nto stop n8n from injecting `traceparent` headers into outbound http requests, set:\n\n```\nexport n8n_otel_traces_inject_outbound=false\n```\n\n## add custom attributes to node spans\n\nif you're [building a custom node](../../../integrations/creating-nodes/overview/), you can attach custom key-value pairs to the node's span. call `setmetadata` from the node's `execute` method:\n\n```\nasync execute(this: iexecutefunctions): promise<inodeexecutiondata[][]> {\n\tthis.setmetadata({\n\t\ttracing: {\n\t\t\t'llm.model': 'gpt-4o',\n\t\t\t'llm.token.input': 1500,\n\t\t\t'llm.token.output': 340,\n\t\t},\n\t});\n\n\treturn [this.getinputdata()];\n}\n```\n\nn8n prefixes each key with `n8n.node.custom.` on the exported span. values must be strings, numbers, or boolean.\n\nthis api isn't available from the code node. it's intended for node authors who want to enrich spans with domain-specific data.\n\n## try it out with jaeger\n\nyou can send traces to a local [jaeger](https://www.jaegertracing.io/) instance to see them in action.\n\n1. save the following as `docker-compose.yml`:\n\n```\nservices:\n  jaeger:\n    image: jaegertracing/jaeger:latest\n    ports:\n      - \"16686:16686\" # ui\n      - \"4317:4317\"   # otlp grpc\n      - \"4318:4318\"   # otlp http\n```\n\n2. start jaeger:\n\n```\ndocker compose up -d\n```\n\n3. start n8n with tracing turned on and pointed at jaeger. information about [starting n8n](https://github.com/n8n-io/n8n/blob/master/contributing.md) can be found elsewhere in this documentation:\n\n```\nn8n_otel_enabled=true n8n_otel_exporter_otlp_endpoint=http://127.0.0.1:4318 n8n start\n```\n\n5. run a workflow, then open the jaeger ui at <http://localhost:16686> - select \"n8n\" as service\" and click \"find traces\" to see the opentelemetry traces emitted by n8n.\n\n## span attributes\n\nworkflow and node spans include the following n8n-specific attributes.\n\n### workflow span (`workflow.execute`)\n\n| attribute                  | description                                                            |\n| -------------------------- | ---------------------------------------------------------------------- |\n| `n8n.workflow.id`          | workflow id.                                                           |\n| `n8n.workflow.name`        | workflow name.                                                         |\n| `n8n.workflow.version_id`  | workflow version id.                                                   |\n| `n8n.workflow.node_count`  | number of nodes in the workflow.                                       |\n| `n8n.execution.id`         | execution id.                                                          |\n| `n8n.execution.mode`       | execution mode (for example, `manual`, `webhook`, `trigger`, `retry`). |\n| `n8n.execution.status`     | final execution status.                                                |\n| `n8n.execution.is_retry`   | `true` if the execution is a retry.                                    |\n| `n8n.execution.retry_of`   | the original execution id, when the execution is a retry.              |\n| `n8n.execution.error_type` | error class name, set when the execution fails.                        |\n| `n8n.continuation.reason`  | set on a span link when the workflow resumes after a wait.             |\n\n### node span (`node.execute`)\n\n| attribute                     | description                                                                            |\n| ----------------------------- | -------------------------------------------------------------------------------------- |\n| `n8n.node.id`                 | node id.                                                                               |\n| `n8n.node.name`               | node name.                                                                             |\n| `n8n.node.type`               | node type (for example, `n8n-nodes-base.httprequest`).                                 |\n| `n8n.node.type_version`       | node type version.                                                                     |\n| `n8n.node.items.input`        | number of input items the node received.                                               |\n| `n8n.node.items.output`       | number of output items the node produced.                                              |\n| `n8n.node.termination_reason` | why a node span ended without a normal completion (for example, `workflow_cancelled`). |\n| `n8n.node.custom.<key>`       | custom attributes set through `metadata.tracing` in the node output.                   |\n\nwhen a node fails, n8n records an `exception` event on the span with the standard opentelemetry exception attributes (`exception.type`, `exception.message`, `exception.stacktrace`).\n\n## troubleshooting\n\n### no traces appear in your backend\n\nif n8n can't reach the otlp endpoint at startup, it logs an error:\n\n```\nfailed to connect to opentelemetry otlp endpoint during startup\n```\n\ncheck that:\n\n- `n8n_otel_enabled` is set to `true`.\n- `n8n_otel_exporter_otlp_endpoint` points at the base url of the collector (not the `/v1/traces` path).\n- the collector is reachable from the n8n container or host.\n- any required `n8n_otel_exporter_otlp_headers` (such as authentication tokens) are set.\n\nn8n logs opentelemetry diagnostics at `warn` level by default. set `n8n_log_level=debug` to see more detail.\n\n### worker traces are missing parent context\n\nin queue mode, workers read the parent trace context from the database. if you only set the opentelemetry environment variables on the main instance, worker spans won't link to the parent workflow trace. set the same variables on every instance type.\n\n## related resources\n\n- [opentelemetry environment variables](../../configuration/environment-variables/opentelemetry/)\n- [w3c trace context specification](https://www.w3.org/tr/trace-context/)\n- [opentelemetry collector documentation](https://opentelemetry.io/docs/collector/)\n- [logging in n8n](../logging/)\n- [monitoring](../monitoring/)\n opentelemetry tracing export 10% of traces",
+        "fullText": "opentelemetry tracing # opentelemetry tracing\n\nthis feature is still under development\n\n- initially available from 2.19.0\n- open telemetry formatted metrics will be coming soon\n\nn8n can emit [opentelemetry](https://opentelemetry.io/) traces for workflow and node executions. use these traces to monitor execution latency, debug failures, and track requests across services in your observability stack.\n\nfeature availability\n\nopentelemetry workflow tracing is only available on self-hosted n8n.\n\n## what you get\n\nwhen you turn on tracing, n8n exports two kinds of spans for each execution:\n\n- **`workflow.execute`**: one span per workflow execution. it records the workflow id, name, version, node count, execution mode, status, and any error type.\n- **`node.execute`**: one span per node execution, nested inside its workflow span. it records the node id, name, type, version, and the number of input and output items.\n\neach span includes resource attributes that identify the n8n instance:\n\n- `service.name` (default `n8n`)\n- `service.version` (the n8n version)\n- `n8n.instance.id`\n- `n8n.instance.role` (for example, `main`, `worker`, or `webhook`)\n\nn8n also handles trace context propagation:\n\n- **inbound**: if a webhook request includes a [w3c `traceparent` header](https://www.w3.org/tr/trace-context/), n8n uses it as the parent for the workflow span. this links the n8n workflow trace to the upstream caller.\n- **outbound**: http request nodes (and other nodes that use the n8n http helpers) can inject a `traceparent` header into outbound requests. downstream services that support w3c trace context can therefore continue the trace.\n- **sub-workflows**: a sub-workflow's span uses the parent workflow's span as its parent.\n- **resumed workflows**: when a workflow resumes after a wait, the new span links back to the previous span using a span link.\n\n## enable tracing\n\nset the following environment variables on each n8n instance you want workflow tracing enabled (main, workers, and webhook processors):\n\n```\nexport n8n_otel_enabled=true\nexport n8n_otel_exporter_otlp_endpoint=http://<your-collector-host>:4318\n```\n\nrestart n8n. the instance starts exporting spans over otlp http using the protobuf encoding.\n\nn8n appends `/v1/traces` to the endpoint by default. point `n8n_otel_exporter_otlp_endpoint` at the base url of your collector, not the traces path.\n\nif your collector needs authentication, set `n8n_otel_exporter_otlp_headers` to a comma-separated list of `key=value` pairs:\n\n```\nexport n8n_otel_exporter_otlp_headers=\"authorization=bearer <your-token>,x-tenant=acme\"\n\n// for added protection - it is recommended to use the `_file` postfix if you are putting a token in here:\nexport n8n_otel_exporter_otlp_headers_file=/mnt/otel-headers\n```\n\nfor the full list of supported variables, refer to [opentelemetry environment variables](../../configuration/environment-variables/opentelemetry/).\n\nqueue mode\n\nin [queue mode](../../scaling/queue-mode/), the opentelemetry variables must be set on all instances. trace context is propagated between instances.\n\n## sampling\n\nby default, n8n exports every trace. to reduce volume in busy instances, set `n8n_otel_traces_sample_rate` to a value between `0` and `1`:\n\n```\n# export 10% of traces\nexport n8n_otel_traces_sample_rate=0.1\n```\n\nn8n uses a trace id ratio sampler, so the same trace id is either fully sampled or fully dropped across all spans in the trace.\n\nn8n will output a trace for every workflow execution - this includes published workflows, unpublished workflows and test executions - in a future release a toggle will be available to track only published workflows\n\n## reduce span volume\n\neach node in a workflow produces its own span. for workflows with lots of nodes, this can produce more data than you need. to export only workflow-level spans, set:\n\n```\nexport n8n_otel_traces_include_node_spans=false\n```\n\nto stop n8n from injecting `traceparent` headers into outbound http requests, set:\n\n```\nexport n8n_otel_traces_inject_outbound=false\n```\n\n## add custom attributes to node spans\n\nif you're [building a custom node](../../../integrations/creating-nodes/overview/), you can attach custom key-value pairs to the node's span. call `setmetadata` from the node's `execute` method:\n\n```\nasync execute(this: iexecutefunctions): promise<inodeexecutiondata[][]> {\n\tthis.setmetadata({\n\t\ttracing: {\n\t\t\t'llm.model': 'gpt-4o',\n\t\t\t'llm.token.input': 1500,\n\t\t\t'llm.token.output': 340,\n\t\t},\n\t});\n\n\treturn [this.getinputdata()];\n}\n```\n\nn8n prefixes each key with `n8n.node.custom.` on the exported span. values must be strings, numbers, or boolean.\n\nthis api isn't available from the code node. it's intended for node authors who want to enrich spans with domain-specific data.\n\n## try it out with jaeger\n\nyou can send traces to a local [jaeger](https://www.jaegertracing.io/) instance to see them in action.\n\n1. save the following as `docker-compose.yml`:\n\n```\nservices:\n  jaeger:\n    image: jaegertracing/jaeger:latest\n    ports:\n      - \"16686:16686\" # ui\n      - \"4317:4317\"   # otlp grpc\n      - \"4318:4318\"   # otlp http\n```\n\n2. start jaeger:\n\n```\ndocker compose up -d\n```\n\n3. start n8n with tracing turned on and pointed at jaeger. information about [starting n8n](https://github.com/n8n-io/n8n/blob/master/contributing.md) can be found elsewhere in this documentation:\n\n```\nn8n_otel_enabled=true n8n_otel_exporter_otlp_endpoint=http://127.0.0.1:4318 n8n start\n```\n\n5. run a workflow, then open the jaeger ui at <http://localhost:16686> - select \"n8n\" as service\" and click \"find traces\" to see the opentelemetry traces emitted by n8n.\n\n## span attributes\n\nworkflow and node spans include the following n8n-specific attributes.\n\n### workflow span (`workflow.execute`)\n\n| attribute                  | description                                                            |\n| -------------------------- | ---------------------------------------------------------------------- |\n| `n8n.workflow.id`          | workflow id.                                                           |\n| `n8n.workflow.name`        | workflow name.                                                         |\n| `n8n.workflow.version_id`  | workflow version id.                                                   |\n| `n8n.workflow.node_count`  | number of nodes in the workflow.                                       |\n| `n8n.execution.id`         | execution id.                                                          |\n| `n8n.execution.mode`       | execution mode (for example, `manual`, `webhook`, `trigger`, `retry`). |\n| `n8n.execution.status`     | final execution status.                                                |\n| `n8n.execution.is_retry`   | `true` if the execution is a retry.                                    |\n| `n8n.execution.retry_of`   | the original execution id, when the execution is a retry.              |\n| `n8n.execution.error_type` | error class name, set when the execution fails.                        |\n| `n8n.continuation.reason`  | set on a span link when the workflow resumes after a wait.             |\n\n### node span (`node.execute`)\n\n| attribute                     | description                                                                            |\n| ----------------------------- | -------------------------------------------------------------------------------------- |\n| `n8n.node.id`                 | node id.                                                                               |\n| `n8n.node.name`               | node name.                                                                             |\n| `n8n.node.type`               | node type (for example, `n8n-nodes-base.httprequest`).                                 |\n| `n8n.node.type_version`       | node type version.                                                                     |\n| `n8n.node.items.input`        | number of input items the node received.                                               |\n| `n8n.node.items.output`       | number of output items the node produced.                                              |\n| `n8n.node.termination_reason` | why a node span ended without a normal completion (for example, `workflow_cancelled`). |\n| `n8n.node.custom.<key>`       | custom attributes set through `metadata.tracing` in the node output.                   |\n\nwhen a node fails, n8n records an `exception` event on the span with the standard opentelemetry exception attributes (`exception.type`, `exception.message`, `exception.stacktrace`).\n\n## troubleshooting\n\n### no traces appear in your backend\n\nif n8n can't reach the otlp endpoint at startup, it logs an error:\n\n```\nfailed to connect to opentelemetry otlp endpoint during startup\n```\n\ncheck that:\n\n- `n8n_otel_enabled` is set to `true`.\n- `n8n_otel_exporter_otlp_endpoint` points at the base url of the collector (not the `/v1/traces` path).\n- the collector is reachable from the n8n container or host.\n- any required `n8n_otel_exporter_otlp_headers` (such as authentication tokens) are set.\n\nn8n logs opentelemetry diagnostics at `warn` level by default. set `n8n_log_level=debug` to see more detail.\n\n### worker traces are missing parent context\n\nin queue mode, workers read the parent trace context from the database. if you only set the opentelemetry environment variables on the main instance, worker spans won't link to the parent workflow trace. set the same variables on every instance type.\n\n## related resources\n\n- [opentelemetry environment variables](../../configuration/environment-variables/opentelemetry/)\n- [w3c trace context specification](https://www.w3.org/tr/trace-context/)\n- [opentelemetry collector documentation](https://opentelemetry.io/docs/collector/)\n- [logging in n8n](../logging/)\n- [monitoring](../monitoring/)\n opentelemetry tracing export 10% of traces",
         "importantTerms": [
           "node",
           "workflow",
@@ -18619,15 +18849,14 @@
           "trace",
           "traces",
           "tracing",
-          "variables",
           "export",
           "this",
+          "variables",
           "spans",
           "name",
           "instance",
           "context",
           "http",
-          "environment",
           "mode",
           "type",
           "collector",
@@ -18640,16 +18869,14 @@
           "version",
           "output",
           "attributes",
-          "webhook",
           "parent",
           "nodes",
           "workflows",
+          "environment",
           "with",
           "custom",
           "each",
           "items",
-          "main",
-          "worker",
           "otlp",
           "exception",
           "available",
@@ -18659,8 +18886,11 @@
           "that",
           "default",
           "example",
+          "webhook",
           "true",
-          "token"
+          "token",
+          "queue",
+          "will"
         ]
       }
     },
@@ -20532,13 +20762,13 @@
       "nodeName": null,
       "nodeType": null,
       "content": {
-        "markdown": "# Built-in integrations\n\nThis section contains the [node](../../../glossary/#node-n8n) library: reference documentation for every built-in node in n8n, and their credentials.\n\n## Node operations: Triggers and Actions\n\nWhen you add a node to a workflow, n8n displays a list of available operations. An operation is something a node does, such as getting or sending data.\n\nThere are two types of operation:\n\n- Triggers start a workflow in response to specific events or conditions in your services. When you select a Trigger, n8n adds a trigger node to your workflow, with the Trigger operation you chose pre-selected. When you search for a node in n8n, Trigger operations have a bolt icon .\n- Actions are operations that represent specific tasks within a workflow, which you can use to manipulate data, perform operations on external systems, and trigger events in other systems as part of your workflows. When you select an Action, n8n adds a node to your workflow, with the Action operation you chose pre-selected.\n\n## Core nodes\n\nCore nodes can be actions or [triggers](../../../glossary/#trigger-node-n8n). Whereas most nodes connect to a specific external service, core nodes provide functionality such as logic, scheduling, or generic API calls.\n\n## Cluster nodes\n\n[Cluster nodes](../../../glossary/#cluster-node-n8n) are node groups that work together to provide functionality in an n8n workflow. Instead of using a single node, you use a [root node](../../../glossary/#root-node-n8n) and one or more [sub-nodes](../../../glossary/#sub-node-n8n) that extend the functionality of the node.\n\n## Credentials\n\nExternal services need a way to identify and authenticate users. This data can range from an API key over an email/password combination to a long multi-line private key. You can save these in n8n as [credentials](../../../glossary/#credential-n8n).\n\nNodes in n8n can then request that credential information. As another layer of security, only node types with specific access rights can access the credentials.\n\nTo make sure that the data is secure, it gets saved to the database encrypted. n8n uses a random personal encryption key, which it automatically generates on the first run of n8n and then saved under `~/.n8n/config`.\n\nTo learn more about creating, managing, and sharing credentials, refer to [Manage credentials](../../../credentials/).\n\n## Community nodes\n\nn8n supports custom nodes built by the community. Refer to [Community nodes](../../community-nodes/installation/) for guidance on installing and using these nodes.\n\nFor help building your own custom nodes, and publish them to [npm](https://www.npmjs.com/), refer to [Creating nodes](../../creating-nodes/overview/) for more information.\n",
-        "excerpt": "# Built-in integrations  This section contains the [node](../../../glossary/#node-n8n) library: reference documentation for every built-in node in n8n, and their credentials.  ## Node operations: Triggers and Actions  When you add a node to a workflow, n8n displays a list of available operations. An operation is something a node does, such as getting or sending data.  There are two types of operation:  - Triggers start a workflow in response to specific events or conditions in your services. Whe...",
+        "markdown": "# Handling API rate limits\n\n[API](../../../glossary/#api) rate limits are restrictions on request frequency. For example, an API may limit the number of requests you can make per minute, or per day.\n\nAPIs can also limits how much data you can send in one request, or how much data the API sends in a single response.\n\n## Identify rate limit issues\n\nWhen an n8n node hits a rate limit, it errors. n8n displays the error message in the node output panel. This includes the error message from the service.\n\nIf n8n received error 429 (too many requests) from the service, the error message is **The service is receiving too many requests from you**.\n\nTo check the rate limits for the service you're using, refer to the API documentation for the service.\n\n## Handle rate limits for integrations\n\nThere are two ways to handle rate limits in n8n's integrations: using the Retry On Fail setting, or using a combination of the [Loop Over Items](../core-nodes/n8n-nodes-base.splitinbatches/) and [Wait](../core-nodes/n8n-nodes-base.wait/) nodes:\n\n- Retry On Fail adds a pause between API request attempts.\n- With Loop Over Items and Wait you can break you request data into smaller chunks, as well as pausing between requests.\n\n### Enable Retry On Fail\n\nWhen you enable Retry On Fail, the node automatically tries the request again if it fails the first time.\n\n1. Open the node.\n1. Select **Settings**.\n1. Enable the **Retry On Fail** toggle.\n1. Configure the retry settings: if using this to work around rate limits, set **Wait Between Tries (ms)** to more than the rate limit. For example, if the API you're using allows one request per second, set **Wait Between Tries (ms)** to `1000` to allow a 1 second wait.\n\n### Use Loop Over Items and Wait\n\nUse the Loop Over Items node to batch the input items, and the Wait node to introduce a pause between each request.\n\n1. Add the Loop Over Items node before the node that calls the API. Refer to [Loop Over Items](../core-nodes/n8n-nodes-base.splitinbatches/) for information on how to configure the node.\n1. Add the Wait node after the node that calls the API, and connect it back to the Loop Over Items node. Refer to [Wait](../core-nodes/n8n-nodes-base.wait/) for information on how to configure the node.\n\nFor example, to handle rate limits when using OpenAI:\n\n## Handle rate limits in the HTTP Request node\n\nThe HTTP Request node has built-in settings for handling rate limits and large amounts of data.\n\n### Batch requests\n\nUse the Batching option to send more than one request, reducing the request size, and introducing a pause between requests. This is the equivalent of using Loop Over Items and Wait.\n\n1. In the HTTP Request node, select **Add Option** > **Batching**.\n1. Set **Items per Batch**: this is the number of input items to include in each request.\n1. Set **Batch Interval (ms)** to introduce a delay between requests. For example, if the API you're using allows one request per second, set **Wait Between Tries (ms)** to `1000` to allow a 1 second wait.\n\n### Paginate results\n\nAPIs paginate their results when they need to send more data than they can handle in a single response. For more information on pagination in the HTTP Request node, refer to [HTTP Request node | Pagination](../core-nodes/n8n-nodes-base.httprequest/#pagination).\n",
+        "excerpt": "# Handling API rate limits  [API](../../../glossary/#api) rate limits are restrictions on request frequency. For example, an API may limit the number of requests you can make per minute, or per day.  APIs can also limits how much data you can send in one request, or how much data the API sends in a single response.  ## Identify rate limit issues  When an n8n node hits a rate limit, it errors. n8n displays the error message in the node output panel. This includes the error message from the servic...",
         "sections": [
           {
-            "title": "Built-in integrations",
+            "title": "Handling API rate limits",
             "level": 1,
-            "content": "This section contains the [node](../../../glossary/#node-n8n) library: reference documentation for every built-in node in n8n, and their credentials."
+            "content": "[API](../../../glossary/#api) rate limits are restrictions on request frequency. For example, an API may limit the number of requests you can make per minute, or per day.\n\nAPIs can also limits how much data you can send in one request, or how much data the API sends in a single response."
           }
         ]
       },
@@ -20558,97 +20788,6 @@
           "community"
         ],
         "useCases": [],
-        "operations": [
-          "triggers",
-          "actions",
-          "n8n adds a trigger node to your workflow",
-          "trigger operations have a bolt icon .",
-          "node : triggers and"
-        ],
-        "codeExamples": 0,
-        "complexity": "beginner",
-        "readingTime": "2 min",
-        "contentLength": 2719,
-        "relatedPages": []
-      },
-      "searchIndex": {
-        "fullText": "node types # built-in integrations\n\nthis section contains the [node](../../../glossary/#node-n8n) library: reference documentation for every built-in node in n8n, and their credentials.\n\n## node operations: triggers and actions\n\nwhen you add a node to a workflow, n8n displays a list of available operations. an operation is something a node does, such as getting or sending data.\n\nthere are two types of operation:\n\n- triggers start a workflow in response to specific events or conditions in your services. when you select a trigger, n8n adds a trigger node to your workflow, with the trigger operation you chose pre-selected. when you search for a node in n8n, trigger operations have a bolt icon .\n- actions are operations that represent specific tasks within a workflow, which you can use to manipulate data, perform operations on external systems, and trigger events in other systems as part of your workflows. when you select an action, n8n adds a node to your workflow, with the action operation you chose pre-selected.\n\n## core nodes\n\ncore nodes can be actions or [triggers](../../../glossary/#trigger-node-n8n). whereas most nodes connect to a specific external service, core nodes provide functionality such as logic, scheduling, or generic api calls.\n\n## cluster nodes\n\n[cluster nodes](../../../glossary/#cluster-node-n8n) are node groups that work together to provide functionality in an n8n workflow. instead of using a single node, you use a [root node](../../../glossary/#root-node-n8n) and one or more [sub-nodes](../../../glossary/#sub-node-n8n) that extend the functionality of the node.\n\n## credentials\n\nexternal services need a way to identify and authenticate users. this data can range from an api key over an email/password combination to a long multi-line private key. you can save these in n8n as [credentials](../../../glossary/#credential-n8n).\n\nnodes in n8n can then request that credential information. as another layer of security, only node types with specific access rights can access the credentials.\n\nto make sure that the data is secure, it gets saved to the database encrypted. n8n uses a random personal encryption key, which it automatically generates on the first run of n8n and then saved under `~/.n8n/config`.\n\nto learn more about creating, managing, and sharing credentials, refer to [manage credentials](../../../credentials/).\n\n## community nodes\n\nn8n supports custom nodes built by the community. refer to [community nodes](../../community-nodes/installation/) for guidance on installing and using these nodes.\n\nfor help building your own custom nodes, and publish them to [npm](https://www.npmjs.com/), refer to [creating nodes](../../creating-nodes/overview/) for more information.\n built-in integrations",
-        "importantTerms": [
-          "node",
-          "nodes",
-          "credentials",
-          "glossary",
-          "workflow",
-          "trigger",
-          "operations",
-          "your",
-          "that",
-          "built",
-          "when",
-          "operation",
-          "data",
-          "specific",
-          "community",
-          "types",
-          "triggers",
-          "actions",
-          "with",
-          "external",
-          "core",
-          "functionality",
-          "cluster",
-          "more",
-          "creating",
-          "refer"
-        ]
-      }
-    },
-    {
-      "id": "page-0240",
-      "title": "Handle rate limits",
-      "url": "https://docs.n8n.io/integrations/builtin/rate-limits/index.md",
-      "urlPath": "integrations/builtin/rate-limits/index.md",
-      "category": "other",
-      "subcategory": null,
-      "nodeName": null,
-      "nodeType": null,
-      "content": {
-        "markdown": "# Handling API rate limits\n\n[API](../../../glossary/#api) rate limits are restrictions on request frequency. For example, an API may limit the number of requests you can make per minute, or per day.\n\nAPIs can also limits how much data you can send in one request, or how much data the API sends in a single response.\n\n## Identify rate limit issues\n\nWhen an n8n node hits a rate limit, it errors. n8n displays the error message in the node output panel. This includes the error message from the service.\n\nIf n8n received error 429 (too many requests) from the service, the error message is **The service is receiving too many requests from you**.\n\nTo check the rate limits for the service you're using, refer to the API documentation for the service.\n\n## Handle rate limits for integrations\n\nThere are two ways to handle rate limits in n8n's integrations: using the Retry On Fail setting, or using a combination of the [Loop Over Items](../core-nodes/n8n-nodes-base.splitinbatches/) and [Wait](../core-nodes/n8n-nodes-base.wait/) nodes:\n\n- Retry On Fail adds a pause between API request attempts.\n- With Loop Over Items and Wait you can break you request data into smaller chunks, as well as pausing between requests.\n\n### Enable Retry On Fail\n\nWhen you enable Retry On Fail, the node automatically tries the request again if it fails the first time.\n\n1. Open the node.\n1. Select **Settings**.\n1. Enable the **Retry On Fail** toggle.\n1. Configure the retry settings: if using this to work around rate limits, set **Wait Between Tries (ms)** to more than the rate limit. For example, if the API you're using allows one request per second, set **Wait Between Tries (ms)** to `1000` to allow a 1 second wait.\n\n### Use Loop Over Items and Wait\n\nUse the Loop Over Items node to batch the input items, and the Wait node to introduce a pause between each request.\n\n1. Add the Loop Over Items node before the node that calls the API. Refer to [Loop Over Items](../core-nodes/n8n-nodes-base.splitinbatches/) for information on how to configure the node.\n1. Add the Wait node after the node that calls the API, and connect it back to the Loop Over Items node. Refer to [Wait](../core-nodes/n8n-nodes-base.wait/) for information on how to configure the node.\n\nFor example, to handle rate limits when using OpenAI:\n\n## Handle rate limits in the HTTP Request node\n\nThe HTTP Request node has built-in settings for handling rate limits and large amounts of data.\n\n### Batch requests\n\nUse the Batching option to send more than one request, reducing the request size, and introducing a pause between requests. This is the equivalent of using Loop Over Items and Wait.\n\n1. In the HTTP Request node, select **Add Option** > **Batching**.\n1. Set **Items per Batch**: this is the number of input items to include in each request.\n1. Set **Batch Interval (ms)** to introduce a delay between requests. For example, if the API you're using allows one request per second, set **Wait Between Tries (ms)** to `1000` to allow a 1 second wait.\n\n### Paginate results\n\nAPIs paginate their results when they need to send more data than they can handle in a single response. For more information on pagination in the HTTP Request node, refer to [HTTP Request node | Pagination](../core-nodes/n8n-nodes-base.httprequest/#pagination).\n",
-        "excerpt": "# Handling API rate limits  [API](../../../glossary/#api) rate limits are restrictions on request frequency. For example, an API may limit the number of requests you can make per minute, or per day.  APIs can also limits how much data you can send in one request, or how much data the API sends in a single response.  ## Identify rate limit issues  When an n8n node hits a rate limit, it errors. n8n displays the error message in the node output panel. This includes the error message from the servic...",
-        "sections": [
-          {
-            "title": "Handling API rate limits",
-            "level": 1,
-            "content": "[API](../../../glossary/#api) rate limits are restrictions on request frequency. For example, an API may limit the number of requests you can make per minute, or per day.\n\nAPIs can also limits how much data you can send in one request, or how much data the API sends in a single response."
-          }
-        ]
-      },
-      "metadata": {
-        "keywords": [
-          "handle",
-          "rate",
-          "limits",
-          "handling",
-          "identify",
-          "limit",
-          "issues",
-          "integrations",
-          "enable",
-          "retry",
-          "fail",
-          "loop",
-          "over",
-          "items",
-          "wait",
-          "http",
-          "request",
-          "node",
-          "batch",
-          "requests",
-          "paginate",
-          "results"
-        ],
-        "useCases": [],
         "operations": [],
         "codeExamples": 0,
         "complexity": "beginner",
@@ -20657,12 +20796,12 @@
         "relatedPages": []
       },
       "searchIndex": {
-        "fullText": "handle rate limits # handling api rate limits\n\n[api](../../../glossary/#api) rate limits are restrictions on request frequency. for example, an api may limit the number of requests you can make per minute, or per day.\n\napis can also limits how much data you can send in one request, or how much data the api sends in a single response.\n\n## identify rate limit issues\n\nwhen an n8n node hits a rate limit, it errors. n8n displays the error message in the node output panel. this includes the error message from the service.\n\nif n8n received error 429 (too many requests) from the service, the error message is **the service is receiving too many requests from you**.\n\nto check the rate limits for the service you're using, refer to the api documentation for the service.\n\n## handle rate limits for integrations\n\nthere are two ways to handle rate limits in n8n's integrations: using the retry on fail setting, or using a combination of the [loop over items](../core-nodes/n8n-nodes-base.splitinbatches/) and [wait](../core-nodes/n8n-nodes-base.wait/) nodes:\n\n- retry on fail adds a pause between api request attempts.\n- with loop over items and wait you can break you request data into smaller chunks, as well as pausing between requests.\n\n### enable retry on fail\n\nwhen you enable retry on fail, the node automatically tries the request again if it fails the first time.\n\n1. open the node.\n1. select **settings**.\n1. enable the **retry on fail** toggle.\n1. configure the retry settings: if using this to work around rate limits, set **wait between tries (ms)** to more than the rate limit. for example, if the api you're using allows one request per second, set **wait between tries (ms)** to `1000` to allow a 1 second wait.\n\n### use loop over items and wait\n\nuse the loop over items node to batch the input items, and the wait node to introduce a pause between each request.\n\n1. add the loop over items node before the node that calls the api. refer to [loop over items](../core-nodes/n8n-nodes-base.splitinbatches/) for information on how to configure the node.\n1. add the wait node after the node that calls the api, and connect it back to the loop over items node. refer to [wait](../core-nodes/n8n-nodes-base.wait/) for information on how to configure the node.\n\nfor example, to handle rate limits when using openai:\n\n## handle rate limits in the http request node\n\nthe http request node has built-in settings for handling rate limits and large amounts of data.\n\n### batch requests\n\nuse the batching option to send more than one request, reducing the request size, and introducing a pause between requests. this is the equivalent of using loop over items and wait.\n\n1. in the http request node, select **add option** > **batching**.\n1. set **items per batch**: this is the number of input items to include in each request.\n1. set **batch interval (ms)** to introduce a delay between requests. for example, if the api you're using allows one request per second, set **wait between tries (ms)** to `1000` to allow a 1 second wait.\n\n### paginate results\n\napis paginate their results when they need to send more data than they can handle in a single response. for more information on pagination in the http request node, refer to [http request node | pagination](../core-nodes/n8n-nodes-base.httprequest/#pagination).\n handling api rate limits",
+        "fullText": "node types # handling api rate limits\n\n[api](../../../glossary/#api) rate limits are restrictions on request frequency. for example, an api may limit the number of requests you can make per minute, or per day.\n\napis can also limits how much data you can send in one request, or how much data the api sends in a single response.\n\n## identify rate limit issues\n\nwhen an n8n node hits a rate limit, it errors. n8n displays the error message in the node output panel. this includes the error message from the service.\n\nif n8n received error 429 (too many requests) from the service, the error message is **the service is receiving too many requests from you**.\n\nto check the rate limits for the service you're using, refer to the api documentation for the service.\n\n## handle rate limits for integrations\n\nthere are two ways to handle rate limits in n8n's integrations: using the retry on fail setting, or using a combination of the [loop over items](../core-nodes/n8n-nodes-base.splitinbatches/) and [wait](../core-nodes/n8n-nodes-base.wait/) nodes:\n\n- retry on fail adds a pause between api request attempts.\n- with loop over items and wait you can break you request data into smaller chunks, as well as pausing between requests.\n\n### enable retry on fail\n\nwhen you enable retry on fail, the node automatically tries the request again if it fails the first time.\n\n1. open the node.\n1. select **settings**.\n1. enable the **retry on fail** toggle.\n1. configure the retry settings: if using this to work around rate limits, set **wait between tries (ms)** to more than the rate limit. for example, if the api you're using allows one request per second, set **wait between tries (ms)** to `1000` to allow a 1 second wait.\n\n### use loop over items and wait\n\nuse the loop over items node to batch the input items, and the wait node to introduce a pause between each request.\n\n1. add the loop over items node before the node that calls the api. refer to [loop over items](../core-nodes/n8n-nodes-base.splitinbatches/) for information on how to configure the node.\n1. add the wait node after the node that calls the api, and connect it back to the loop over items node. refer to [wait](../core-nodes/n8n-nodes-base.wait/) for information on how to configure the node.\n\nfor example, to handle rate limits when using openai:\n\n## handle rate limits in the http request node\n\nthe http request node has built-in settings for handling rate limits and large amounts of data.\n\n### batch requests\n\nuse the batching option to send more than one request, reducing the request size, and introducing a pause between requests. this is the equivalent of using loop over items and wait.\n\n1. in the http request node, select **add option** > **batching**.\n1. set **items per batch**: this is the number of input items to include in each request.\n1. set **batch interval (ms)** to introduce a delay between requests. for example, if the api you're using allows one request per second, set **wait between tries (ms)** to `1000` to allow a 1 second wait.\n\n### paginate results\n\napis paginate their results when they need to send more data than they can handle in a single response. for more information on pagination in the http request node, refer to [http request node | pagination](../core-nodes/n8n-nodes-base.httprequest/#pagination).\n handling api rate limits",
         "importantTerms": [
           "node",
           "request",
-          "rate",
           "wait",
+          "rate",
           "limits",
           "items",
           "nodes",
@@ -20671,10 +20810,10 @@
           "over",
           "between",
           "requests",
-          "handle",
           "retry",
           "data",
           "service",
+          "handle",
           "fail",
           "core",
           "base",
@@ -94034,7 +94173,7 @@
         "page-0028",
         "page-0029",
         "page-0030",
-        "page-0037",
+        "page-0038",
         "page-0053",
         "page-0147",
         "page-0558",
@@ -94151,7 +94290,6 @@
         "page-0218",
         "page-0230",
         "page-0239",
-        "page-0240",
         "page-0242",
         "page-0243",
         "page-0244",
@@ -95137,6 +95275,7 @@
         "page-0003",
         "page-0008",
         "page-0013",
+        "page-0040",
         "page-0044",
         "page-0051",
         "page-0073",
@@ -95341,7 +95480,6 @@
         "page-0070",
         "page-0079",
         "page-0080",
-        "page-0240",
         "page-0506",
         "page-0540",
         "page-0544",
@@ -95427,7 +95565,6 @@
         "page-0012",
         "page-0026",
         "page-0102",
-        "page-0240",
         "page-0355",
         "page-0381",
         "page-0501",
@@ -95580,7 +95717,7 @@
       "from": [
         "page-0003",
         "page-0015",
-        "page-0037",
+        "page-0038",
         "page-0043",
         "page-0044",
         "page-0050",
@@ -95964,7 +96101,6 @@
         "page-0224",
         "page-0226",
         "page-0233",
-        "page-0240",
         "page-0577",
         "page-0580",
         "page-0883",
@@ -96024,6 +96160,7 @@
         "page-0020",
         "page-0026",
         "page-0035",
+        "page-0037",
         "page-0541",
         "page-0558",
         "page-0559",
@@ -96484,6 +96621,7 @@
         "page-0003",
         "page-0006",
         "page-0034",
+        "page-0040",
         "page-0209",
         "page-0215",
         "page-0220",
@@ -97500,7 +97638,7 @@
         "page-0028",
         "page-0029",
         "page-0030",
-        "page-0037",
+        "page-0038",
         "page-0043",
         "page-0047",
         "page-0049",
@@ -98064,7 +98202,8 @@
         "page-0006",
         "page-0022",
         "page-0036",
-        "page-0037",
+        "page-0038",
+        "page-0040",
         "page-0528",
         "page-0558",
         "page-0559",
@@ -98093,6 +98232,7 @@
       ],
       "cluster": [
         "page-0006",
+        "page-0040",
         "page-0165",
         "page-0201",
         "page-0202",
@@ -98162,6 +98302,8 @@
       ],
       "langchain": [
         "page-0006",
+        "page-0039",
+        "page-0040",
         "page-0042",
         "page-0057",
         "page-0554",
@@ -98174,6 +98316,7 @@
       ],
       "language": [
         "page-0006",
+        "page-0040",
         "page-0327",
         "page-0556",
         "page-0634",
@@ -98183,6 +98326,7 @@
       "model": [
         "page-0006",
         "page-0018",
+        "page-0037",
         "page-0495",
         "page-0498",
         "page-0499",
@@ -98226,6 +98370,7 @@
       ],
       "root": [
         "page-0006",
+        "page-0040",
         "page-0114",
         "page-0129",
         "page-0204",
@@ -98249,6 +98394,7 @@
         "page-0017",
         "page-0021",
         "page-0023",
+        "page-0040",
         "page-0043",
         "page-0074",
         "page-0085",
@@ -98641,7 +98787,8 @@
         "page-1221"
       ],
       "learning": [
-        "page-0009"
+        "page-0009",
+        "page-0039"
       ],
       "path": [
         "page-0009",
@@ -98704,6 +98851,7 @@
         "page-0009",
         "page-0022",
         "page-0036",
+        "page-0040",
         "page-0071",
         "page-0325",
         "page-0385",
@@ -99251,7 +99399,7 @@
         "page-0029",
         "page-0030",
         "page-0036",
-        "page-0037",
+        "page-0038",
         "page-0052",
         "page-0110",
         "page-0111",
@@ -99834,7 +99982,6 @@
         "page-0013",
         "page-0020",
         "page-0138",
-        "page-0240",
         "page-0699"
       ],
       "calls": [
@@ -101193,6 +101340,7 @@
       "resources": [
         "page-0017",
         "page-0020",
+        "page-0039",
         "page-0043",
         "page-0051",
         "page-0052",
@@ -101758,6 +101906,7 @@
       ],
       "templates": [
         "page-0017",
+        "page-0037",
         "page-0063",
         "page-0161",
         "page-0242",
@@ -102223,7 +102372,6 @@
         "page-0018",
         "page-0066",
         "page-0136",
-        "page-0240",
         "page-0687",
         "page-1156",
         "page-1179",
@@ -102272,6 +102420,7 @@
         "page-0022",
         "page-0027",
         "page-0032",
+        "page-0040",
         "page-0653"
       ],
       "managing": [
@@ -102374,6 +102523,7 @@
       "tools": [
         "page-0020",
         "page-0035",
+        "page-0040",
         "page-0043",
         "page-0044",
         "page-0205",
@@ -102521,6 +102671,7 @@
       "concepts": [
         "page-0021",
         "page-0031",
+        "page-0040",
         "page-0053",
         "page-0209",
         "page-0714"
@@ -102730,7 +102881,6 @@
       "results": [
         "page-0024",
         "page-0026",
-        "page-0240",
         "page-0558",
         "page-0559",
         "page-0560",
@@ -102802,7 +102952,8 @@
       ],
       "chains": [
         "page-0027",
-        "page-0033"
+        "page-0033",
+        "page-0040"
       ],
       "demonstration": [
         "page-0027"
@@ -102923,6 +103074,7 @@
       ],
       "examples": [
         "page-0031",
+        "page-0037",
         "page-0043",
         "page-0050",
         "page-0060",
@@ -103416,25 +103568,211 @@
       ],
       "document": [
         "page-0036",
+        "page-0040",
         "page-0522",
         "page-0523",
         "page-0538",
         "page-0583"
       ],
       "loaders": [
-        "page-0036"
+        "page-0036",
+        "page-0040"
       ],
-      "populate": [
+      "specify": [
+        "page-0037",
+        "page-0160",
+        "page-0169",
+        "page-0292",
+        "page-0428",
+        "page-0465"
+      ],
+      "parameters": [
+        "page-0037",
+        "page-0044",
+        "page-0070",
+        "page-0074",
+        "page-0161",
+        "page-0309",
+        "page-0364",
+        "page-0392",
+        "page-0483",
+        "page-0506",
+        "page-0524",
+        "page-0528",
+        "page-0529",
+        "page-0530",
+        "page-0538",
+        "page-0540",
+        "page-0544",
+        "page-0552",
+        "page-0553",
+        "page-0554",
+        "page-0555",
+        "page-0556",
+        "page-0557",
+        "page-0558",
+        "page-0559",
+        "page-0560",
+        "page-0561",
+        "page-0562",
+        "page-0563",
+        "page-0564",
+        "page-0565",
+        "page-0566",
+        "page-0567",
+        "page-0568",
+        "page-0569",
+        "page-0572",
+        "page-0573",
+        "page-0574",
+        "page-0575",
+        "page-0576",
+        "page-0577",
+        "page-0578",
+        "page-0582",
+        "page-0583",
+        "page-0584",
+        "page-0586",
+        "page-0587",
+        "page-0588",
+        "page-0589",
+        "page-0590",
+        "page-0591",
+        "page-0592",
+        "page-0593",
+        "page-0596",
+        "page-0597",
+        "page-0598",
+        "page-0599",
+        "page-0600",
+        "page-0601",
+        "page-0602",
+        "page-0603",
+        "page-0604",
+        "page-0605",
+        "page-0606",
+        "page-0608",
+        "page-0609",
+        "page-0610",
+        "page-0612",
+        "page-0613",
+        "page-0614",
+        "page-0615",
+        "page-0616",
+        "page-0617",
+        "page-0618",
+        "page-0619",
+        "page-0620",
+        "page-0621",
+        "page-0624",
+        "page-0627",
+        "page-0628",
+        "page-0629",
+        "page-0630",
+        "page-0631",
+        "page-0632",
+        "page-0634",
+        "page-0636",
+        "page-0640",
+        "page-0643",
+        "page-0644",
+        "page-0645",
+        "page-0646",
+        "page-0647",
+        "page-0648",
+        "page-0649",
+        "page-0650",
+        "page-0652",
+        "page-0653",
+        "page-0655",
+        "page-0656",
+        "page-0657",
+        "page-0658",
+        "page-0659",
+        "page-0661",
+        "page-0663",
+        "page-0664",
+        "page-0665",
+        "page-0668",
+        "page-0669",
+        "page-0672",
+        "page-0673",
+        "page-0674",
+        "page-0675",
+        "page-0678",
+        "page-0681",
+        "page-0683",
+        "page-0684",
+        "page-0686",
+        "page-0687",
+        "page-0689",
+        "page-0692",
+        "page-0693",
+        "page-0694",
+        "page-0695",
+        "page-0696",
+        "page-0697",
+        "page-0698",
+        "page-0699",
+        "page-0700",
+        "page-0701",
+        "page-0703",
+        "page-0704",
+        "page-0705",
+        "page-0706",
+        "page-0708",
+        "page-0709",
+        "page-0710",
+        "page-0711",
+        "page-0712",
+        "page-0713",
+        "page-0720",
+        "page-0722",
+        "page-0723",
+        "page-0724",
+        "page-0726",
+        "page-0728",
+        "page-0731",
+        "page-0750",
+        "page-1058",
+        "page-1121",
+        "page-1152",
+        "page-1178",
+        "page-1189",
+        "page-1191",
+        "page-1192",
+        "page-1266"
+      ],
+      "fill": [
+        "page-0037"
+      ],
+      "parameter": [
+        "page-0037",
+        "page-0723",
+        "page-1177",
+        "page-1185",
+        "page-1186",
+        "page-1245"
+      ],
+      "`$fromai()`": [
         "page-0037",
+        "page-0577",
+        "page-0632"
+      ],
+      "function": [
+        "page-0037"
+      ],
+      "populate": [
+        "page-0038",
         "page-0530"
       ],
       "pinecone": [
-        "page-0037",
+        "page-0038",
         "page-0564",
         "page-0934"
       ],
       "database": [
-        "page-0037",
+        "page-0038",
         "page-0148",
         "page-0154",
         "page-0175",
@@ -103457,9 +103795,73 @@
         "page-0996"
       ],
       "website": [
-        "page-0037",
+        "page-0038",
         "page-0732"
       ],
+      "stores": [
+        "page-0040",
+        "page-0209"
+      ],
+      "miscellaneous": [
+        "page-0040"
+      ],
+      "models": [
+        "page-0040"
+      ],
+      "output": [
+        "page-0040",
+        "page-0044",
+        "page-0050",
+        "page-0061",
+        "page-0066",
+        "page-0099",
+        "page-0108",
+        "page-0210",
+        "page-0552",
+        "page-0572",
+        "page-0573",
+        "page-0574",
+        "page-0575",
+        "page-0577",
+        "page-0622",
+        "page-0623",
+        "page-0646",
+        "page-0652",
+        "page-0653",
+        "page-0658",
+        "page-0672",
+        "page-0693",
+        "page-0697",
+        "page-0704",
+        "page-1186",
+        "page-1221",
+        "page-1235"
+      ],
+      "parsers": [
+        "page-0040",
+        "page-0686"
+      ],
+      "retrievers": [
+        "page-0040"
+      ],
+      "splitters": [
+        "page-0040"
+      ],
+      "embeddings": [
+        "page-0040",
+        "page-0584",
+        "page-0585",
+        "page-0586",
+        "page-0587",
+        "page-0588",
+        "page-0589",
+        "page-0590",
+        "page-0591",
+        "page-0592",
+        "page-0593",
+        "page-0594",
+        "page-1221"
+      ],
       "langsmith": [
         "page-0041"
       ],
@@ -103767,190 +104169,6 @@
         "page-1238",
         "page-1239"
       ],
-      "parameters": [
-        "page-0044",
-        "page-0070",
-        "page-0074",
-        "page-0161",
-        "page-0309",
-        "page-0364",
-        "page-0392",
-        "page-0483",
-        "page-0506",
-        "page-0524",
-        "page-0528",
-        "page-0529",
-        "page-0530",
-        "page-0538",
-        "page-0540",
-        "page-0544",
-        "page-0552",
-        "page-0553",
-        "page-0554",
-        "page-0555",
-        "page-0556",
-        "page-0557",
-        "page-0558",
-        "page-0559",
-        "page-0560",
-        "page-0561",
-        "page-0562",
-        "page-0563",
-        "page-0564",
-        "page-0565",
-        "page-0566",
-        "page-0567",
-        "page-0568",
-        "page-0569",
-        "page-0572",
-        "page-0573",
-        "page-0574",
-        "page-0575",
-        "page-0576",
-        "page-0577",
-        "page-0578",
-        "page-0582",
-        "page-0583",
-        "page-0584",
-        "page-0586",
-        "page-0587",
-        "page-0588",
-        "page-0589",
-        "page-0590",
-        "page-0591",
-        "page-0592",
-        "page-0593",
-        "page-0596",
-        "page-0597",
-        "page-0598",
-        "page-0599",
-        "page-0600",
-        "page-0601",
-        "page-0602",
-        "page-0603",
-        "page-0604",
-        "page-0605",
-        "page-0606",
-        "page-0608",
-        "page-0609",
-        "page-0610",
-        "page-0612",
-        "page-0613",
-        "page-0614",
-        "page-0615",
-        "page-0616",
-        "page-0617",
-        "page-0618",
-        "page-0619",
-        "page-0620",
-        "page-0621",
-        "page-0624",
-        "page-0627",
-        "page-0628",
-        "page-0629",
-        "page-0630",
-        "page-0631",
-        "page-0632",
-        "page-0634",
-        "page-0636",
-        "page-0640",
-        "page-0643",
-        "page-0644",
-        "page-0645",
-        "page-0646",
-        "page-0647",
-        "page-0648",
-        "page-0649",
-        "page-0650",
-        "page-0652",
-        "page-0653",
-        "page-0655",
-        "page-0656",
-        "page-0657",
-        "page-0658",
-        "page-0659",
-        "page-0661",
-        "page-0663",
-        "page-0664",
-        "page-0665",
-        "page-0668",
-        "page-0669",
-        "page-0672",
-        "page-0673",
-        "page-0674",
-        "page-0675",
-        "page-0678",
-        "page-0681",
-        "page-0683",
-        "page-0684",
-        "page-0686",
-        "page-0687",
-        "page-0689",
-        "page-0692",
-        "page-0693",
-        "page-0694",
-        "page-0695",
-        "page-0696",
-        "page-0697",
-        "page-0698",
-        "page-0699",
-        "page-0700",
-        "page-0701",
-        "page-0703",
-        "page-0704",
-        "page-0705",
-        "page-0706",
-        "page-0708",
-        "page-0709",
-        "page-0710",
-        "page-0711",
-        "page-0712",
-        "page-0713",
-        "page-0720",
-        "page-0722",
-        "page-0723",
-        "page-0724",
-        "page-0726",
-        "page-0728",
-        "page-0731",
-        "page-0750",
-        "page-1058",
-        "page-1121",
-        "page-1152",
-        "page-1178",
-        "page-1189",
-        "page-1191",
-        "page-1192",
-        "page-1266"
-      ],
-      "output": [
-        "page-0044",
-        "page-0050",
-        "page-0061",
-        "page-0066",
-        "page-0099",
-        "page-0108",
-        "page-0210",
-        "page-0552",
-        "page-0572",
-        "page-0573",
-        "page-0574",
-        "page-0575",
-        "page-0577",
-        "page-0622",
-        "page-0623",
-        "page-0646",
-        "page-0652",
-        "page-0653",
-        "page-0658",
-        "page-0672",
-        "page-0693",
-        "page-0697",
-        "page-0704",
-        "page-1186",
-        "page-1221",
-        "page-1235"
-      ],
       "details": [
         "page-0044",
         "page-0144",
@@ -104320,7 +104538,6 @@
       ],
       "limits": [
         "page-0052",
-        "page-0240",
         "page-1006",
         "page-1208",
         "page-1211"
@@ -105212,7 +105429,6 @@
         "page-0070",
         "page-0079",
         "page-0080",
-        "page-0240",
         "page-0635",
         "page-0678",
         "page-0707",
@@ -105227,7 +105443,6 @@
       ],
       "requests": [
         "page-0053",
-        "page-0240",
         "page-0422",
         "page-0502",
         "page-0544",
@@ -105312,7 +105527,6 @@
         "page-0111",
         "page-0112",
         "page-0138",
-        "page-0240",
         "page-0683",
         "page-0687",
         "page-0699",
@@ -107934,13 +108148,6 @@
       "trust": [
         "page-0159"
       ],
-      "specify": [
-        "page-0160",
-        "page-0169",
-        "page-0292",
-        "page-0428",
-        "page-0465"
-      ],
       "location": [
         "page-0160",
         "page-0210",
@@ -108705,9 +108912,6 @@
       "database,": [
         "page-0209"
       ],
-      "stores": [
-        "page-0209"
-      ],
       "openshift:": [
         "page-0209"
       ],
@@ -109409,7 +109613,6 @@
       "integrations": [
         "page-0236",
         "page-0239",
-        "page-0240",
         "page-0891",
         "page-0914"
       ],
@@ -109766,54 +109969,6 @@
         "page-0239",
         "page-1270"
       ],
-      "handle": [
-        "page-0240",
-        "page-0527"
-      ],
-      "rate": [
-        "page-0240",
-        "page-1006"
-      ],
-      "identify": [
-        "page-0240"
-      ],
-      "limit": [
-        "page-0240",
-        "page-0568",
-        "page-0576",
-        "page-0640",
-        "page-0683",
-        "page-0707",
-        "page-0813",
-        "page-1221"
-      ],
-      "retry": [
-        "page-0240",
-        "page-0723",
-        "page-1273",
-        "page-1279"
-      ],
-      "fail": [
-        "page-0240",
-        "page-0723"
-      ],
-      "over": [
-        "page-0240",
-        "page-0699"
-      ],
-      "wait": [
-        "page-0240",
-        "page-0509",
-        "page-0538",
-        "page-0707"
-      ],
-      "batch": [
-        "page-0240",
-        "page-0699"
-      ],
-      "paginate": [
-        "page-0240"
-      ],
       "action": [
         "page-0242",
         "page-0538",
@@ -111291,6 +111446,11 @@
         "page-0538",
         "page-0696"
       ],
+      "wait": [
+        "page-0509",
+        "page-0538",
+        "page-0707"
+      ],
       "thread": [
         "page-0510"
       ],
@@ -111425,6 +111585,9 @@
         "page-0527",
         "page-1271"
       ],
+      "handle": [
+        "page-0527"
+      ],
       "null": [
         "page-0527"
       ],
@@ -111967,6 +112130,15 @@
       "fusion": [
         "page-0568"
       ],
+      "limit": [
+        "page-0568",
+        "page-0576",
+        "page-0640",
+        "page-0683",
+        "page-0707",
+        "page-0813",
+        "page-1221"
+      ],
       "alpha": [
         "page-0568",
         "page-1221"
@@ -112064,10 +112236,6 @@
         "page-0577",
         "page-1271"
       ],
-      "`$fromai()`": [
-        "page-0577",
-        "page-0632"
-      ],
       "produce": [
         "page-0579"
       ],
@@ -112087,20 +112255,6 @@
         "page-0582",
         "page-0583"
       ],
-      "embeddings": [
-        "page-0584",
-        "page-0585",
-        "page-0586",
-        "page-0587",
-        "page-0588",
-        "page-0589",
-        "page-0590",
-        "page-0591",
-        "page-0592",
-        "page-0593",
-        "page-0594",
-        "page-1221"
-      ],
       "bedrock": [
         "page-0584",
         "page-0597"
@@ -112594,9 +112748,6 @@
         "page-1220",
         "page-1271"
       ],
-      "parsers": [
-        "page-0686"
-      ],
       "position": [
         "page-0687"
       ],
@@ -112687,12 +112838,18 @@
       "arrays": [
         "page-0697"
       ],
+      "over": [
+        "page-0699"
+      ],
       "(split": [
         "page-0699"
       ],
       "batches)": [
         "page-0699"
       ],
+      "batch": [
+        "page-0699"
+      ],
       "reset": [
         "page-0699"
       ],
@@ -112845,12 +113002,13 @@
       "could": [
         "page-0723"
       ],
-      "parameter": [
+      "retry": [
         "page-0723",
-        "page-1177",
-        "page-1185",
-        "page-1186",
-        "page-1245"
+        "page-1273",
+        "page-1279"
+      ],
+      "fail": [
+        "page-0723"
       ],
       "duplicates": [
         "page-0724",
@@ -113295,6 +113453,9 @@
       "trellix": [
         "page-1001"
       ],
+      "rate": [
+        "page-1006"
+      ],
       "typeform": [
         "page-1007",
         "page-1131"
@@ -114429,7 +114590,6 @@
         "page-0237",
         "page-0238",
         "page-0239",
-        "page-0240",
         "page-0654",
         "page-0655",
         "page-0656",
@@ -114974,6 +115134,9 @@
         "page-0035",
         "page-0036",
         "page-0037",
+        "page-0038",
+        "page-0039",
+        "page-0040",
         "page-0041",
         "page-0042",
         "page-0043",