@n8n-as-code/skills 2.1.0-next.47 → 2.1.0-next.49
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/assets/n8n-credentials-ontology.json +1 -1
- package/dist/assets/n8n-docs-complete.json +245 -527
- package/dist/assets/n8n-knowledge-index.json +45 -323
- package/dist/assets/n8n-nodes-index.json +5 -5
- package/dist/assets/n8n-nodes-technical.json +5 -5
- package/dist/assets/workflows-index.json +1 -1
- package/package.json +1 -1
|
@@ -1,13 +1,13 @@
|
|
|
1
1
|
{
|
|
2
|
-
"generatedAt": "2026-05-
|
|
2
|
+
"generatedAt": "2026-05-11T11:30:58.451Z",
|
|
3
3
|
"version": "1.0.0",
|
|
4
4
|
"sourceUrl": "https://docs.n8n.io/llms.txt",
|
|
5
|
-
"totalPages":
|
|
5
|
+
"totalPages": 1276,
|
|
6
6
|
"statistics": {
|
|
7
7
|
"byCategory": {
|
|
8
8
|
"other": 514,
|
|
9
9
|
"tutorials": 27,
|
|
10
|
-
"advanced-ai":
|
|
10
|
+
"advanced-ai": 25,
|
|
11
11
|
"api": 6,
|
|
12
12
|
"code": 20,
|
|
13
13
|
"data": 38,
|
|
@@ -21,7 +21,7 @@
|
|
|
21
21
|
},
|
|
22
22
|
"withNodeNames": 471,
|
|
23
23
|
"withUseCases": 40,
|
|
24
|
-
"withCodeExamples":
|
|
24
|
+
"withCodeExamples": 185
|
|
25
25
|
},
|
|
26
26
|
"categories": {
|
|
27
27
|
"other": {
|
|
@@ -579,7 +579,7 @@
|
|
|
579
579
|
},
|
|
580
580
|
"advanced-ai": {
|
|
581
581
|
"description": "AI agents, chains, RAG, memory, and LangChain integration",
|
|
582
|
-
"totalPages":
|
|
582
|
+
"totalPages": 25,
|
|
583
583
|
"pages": [
|
|
584
584
|
"page-0017",
|
|
585
585
|
"page-0018",
|
|
@@ -602,9 +602,6 @@
|
|
|
602
602
|
"page-0035",
|
|
603
603
|
"page-0036",
|
|
604
604
|
"page-0037",
|
|
605
|
-
"page-0038",
|
|
606
|
-
"page-0039",
|
|
607
|
-
"page-0040",
|
|
608
605
|
"page-0041",
|
|
609
606
|
"page-0042",
|
|
610
607
|
"page-0043",
|
|
@@ -4841,99 +4838,6 @@
|
|
|
4841
4838
|
},
|
|
4842
4839
|
{
|
|
4843
4840
|
"id": "page-0037",
|
|
4844
|
-
"title": "Let AI specify tool parameters",
|
|
4845
|
-
"url": "https://docs.n8n.io/advanced-ai/examples/using-the-fromai-function/index.md",
|
|
4846
|
-
"urlPath": "advanced-ai/examples/using-the-fromai-function/index.md",
|
|
4847
|
-
"category": "advanced-ai",
|
|
4848
|
-
"subcategory": "examples",
|
|
4849
|
-
"nodeName": null,
|
|
4850
|
-
"nodeType": null,
|
|
4851
|
-
"content": {
|
|
4852
|
-
"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",
|
|
4853
|
-
"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...",
|
|
4854
|
-
"sections": [
|
|
4855
|
-
{
|
|
4856
|
-
"title": "Let AI specify the tool parameters",
|
|
4857
|
-
"level": 1,
|
|
4858
|
-
"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."
|
|
4859
|
-
}
|
|
4860
|
-
]
|
|
4861
|
-
},
|
|
4862
|
-
"metadata": {
|
|
4863
|
-
"keywords": [
|
|
4864
|
-
"specify",
|
|
4865
|
-
"tool",
|
|
4866
|
-
"parameters",
|
|
4867
|
-
"model",
|
|
4868
|
-
"fill",
|
|
4869
|
-
"parameter",
|
|
4870
|
-
"`$fromai()`",
|
|
4871
|
-
"function",
|
|
4872
|
-
"examples",
|
|
4873
|
-
"templates"
|
|
4874
|
-
],
|
|
4875
|
-
"useCases": [],
|
|
4876
|
-
"operations": [],
|
|
4877
|
-
"codeExamples": 5,
|
|
4878
|
-
"complexity": "intermediate",
|
|
4879
|
-
"readingTime": "4 min",
|
|
4880
|
-
"contentLength": 5438,
|
|
4881
|
-
"relatedPages": []
|
|
4882
|
-
},
|
|
4883
|
-
"searchIndex": {
|
|
4884
|
-
"fullText": "let ai specify tool parameters # let ai specify the tool parameters\n\nwhen configuring [tools](../../../glossary/#ai-tool) connected to the tools agent, many parameters can be filled in by the ai model itself. the ai model will use the context from the task and information from other connected tools to fill in the appropriate details.\n\nthere are two ways to do this, and you can switch between them.\n\n## let the model fill in the parameter\n\neach appropriate parameter field in the tool's editing dialog has an extra button at the end:\n\non activating this button, the [ai agent](../../../glossary/#ai-agent) will fill in the expression for you, with no need for any further user input. the field itself is filled in with a message indicating that the parameter has been defined automatically by the model.\n\nif you want to define the parameter yourself, click on the 'x' in this box to revert to user-defined values. note that the 'expression' field will now contain the expression generated by this feature, though you can now edit it further to add extra details as described in the following section.\n\nwarning\n\nactivating this feature will overwrite any manual definition you may have already added.\n\n## use the `$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",
|
|
4885
|
-
"importantTerms": [
|
|
4886
|
-
"fromai",
|
|
4887
|
-
"with",
|
|
4888
|
-
"string",
|
|
4889
|
-
"parameters",
|
|
4890
|
-
"tools",
|
|
4891
|
-
"model",
|
|
4892
|
-
"nodes",
|
|
4893
|
-
"this",
|
|
4894
|
-
"parameter",
|
|
4895
|
-
"function",
|
|
4896
|
-
"tool",
|
|
4897
|
-
"agent",
|
|
4898
|
-
"expression",
|
|
4899
|
-
"will",
|
|
4900
|
-
"fill",
|
|
4901
|
-
"other",
|
|
4902
|
-
"field",
|
|
4903
|
-
"following",
|
|
4904
|
-
"name",
|
|
4905
|
-
"connected",
|
|
4906
|
-
"generated",
|
|
4907
|
-
"cluster",
|
|
4908
|
-
"only",
|
|
4909
|
-
"email",
|
|
4910
|
-
"workflows",
|
|
4911
|
-
"number",
|
|
4912
|
-
"could",
|
|
4913
|
-
"text",
|
|
4914
|
-
"specify",
|
|
4915
|
-
"glossary",
|
|
4916
|
-
"context",
|
|
4917
|
-
"from",
|
|
4918
|
-
"extra",
|
|
4919
|
-
"user",
|
|
4920
|
-
"that",
|
|
4921
|
-
"want",
|
|
4922
|
-
"dynamically",
|
|
4923
|
-
"integrations",
|
|
4924
|
-
"builtin",
|
|
4925
|
-
"populate",
|
|
4926
|
-
"data",
|
|
4927
|
-
"description",
|
|
4928
|
-
"type",
|
|
4929
|
-
"argument",
|
|
4930
|
-
"value",
|
|
4931
|
-
"https"
|
|
4932
|
-
]
|
|
4933
|
-
}
|
|
4934
|
-
},
|
|
4935
|
-
{
|
|
4936
|
-
"id": "page-0038",
|
|
4937
4841
|
"title": "Populate a Pinecone vector database from a website",
|
|
4938
4842
|
"url": "https://docs.n8n.io/advanced-ai/examples/vector-store-website/index.md",
|
|
4939
4843
|
"urlPath": "advanced-ai/examples/vector-store-website/index.md",
|
|
@@ -4942,13 +4846,13 @@
|
|
|
4942
4846
|
"nodeName": null,
|
|
4943
4847
|
"nodeType": null,
|
|
4944
4848
|
"content": {
|
|
4945
|
-
"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",
|
|
4946
|
-
"excerpt": "#
|
|
4849
|
+
"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",
|
|
4850
|
+
"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...",
|
|
4947
4851
|
"sections": [
|
|
4948
4852
|
{
|
|
4949
|
-
"title": "
|
|
4853
|
+
"title": "LangChain concepts in n8n",
|
|
4950
4854
|
"level": 1,
|
|
4951
|
-
"content": "
|
|
4855
|
+
"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)."
|
|
4952
4856
|
}
|
|
4953
4857
|
]
|
|
4954
4858
|
},
|
|
@@ -4967,148 +4871,13 @@
|
|
|
4967
4871
|
"useCases": [],
|
|
4968
4872
|
"operations": [],
|
|
4969
4873
|
"codeExamples": 0,
|
|
4970
|
-
"complexity": "beginner",
|
|
4971
|
-
"readingTime": "2 min",
|
|
4972
|
-
"contentLength": 1989,
|
|
4973
|
-
"relatedPages": []
|
|
4974
|
-
},
|
|
4975
|
-
"searchIndex": {
|
|
4976
|
-
"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",
|
|
4977
|
-
"importantTerms": [
|
|
4978
|
-
"nodes",
|
|
4979
|
-
"workflow",
|
|
4980
|
-
"integrations",
|
|
4981
|
-
"builtin",
|
|
4982
|
-
"pinecone",
|
|
4983
|
-
"vector",
|
|
4984
|
-
"website",
|
|
4985
|
-
"node",
|
|
4986
|
-
"from",
|
|
4987
|
-
"data",
|
|
4988
|
-
"core",
|
|
4989
|
-
"langchain",
|
|
4990
|
-
"database",
|
|
4991
|
-
"base",
|
|
4992
|
-
"html",
|
|
4993
|
-
"cluster",
|
|
4994
|
-
"populate",
|
|
4995
|
-
"into",
|
|
4996
|
-
"using",
|
|
4997
|
-
"uses",
|
|
4998
|
-
"store",
|
|
4999
|
-
"root",
|
|
5000
|
-
"file",
|
|
5001
|
-
"json",
|
|
5002
|
-
"example"
|
|
5003
|
-
]
|
|
5004
|
-
}
|
|
5005
|
-
},
|
|
5006
|
-
{
|
|
5007
|
-
"id": "page-0039",
|
|
5008
|
-
"title": "LangChain learning resources",
|
|
5009
|
-
"url": "https://docs.n8n.io/advanced-ai/langchain/langchain-learning-resources/index.md",
|
|
5010
|
-
"urlPath": "advanced-ai/langchain/langchain-learning-resources/index.md",
|
|
5011
|
-
"category": "advanced-ai",
|
|
5012
|
-
"subcategory": "langchain",
|
|
5013
|
-
"nodeName": null,
|
|
5014
|
-
"nodeType": null,
|
|
5015
|
-
"content": {
|
|
5016
|
-
"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",
|
|
5017
|
-
"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_...",
|
|
5018
|
-
"sections": [
|
|
5019
|
-
{
|
|
5020
|
-
"title": "LangChain learning resources",
|
|
5021
|
-
"level": 1,
|
|
5022
|
-
"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"
|
|
5023
|
-
}
|
|
5024
|
-
]
|
|
5025
|
-
},
|
|
5026
|
-
"metadata": {
|
|
5027
|
-
"keywords": [
|
|
5028
|
-
"langchain",
|
|
5029
|
-
"learning",
|
|
5030
|
-
"resources"
|
|
5031
|
-
],
|
|
5032
|
-
"useCases": [],
|
|
5033
|
-
"operations": [],
|
|
5034
|
-
"codeExamples": 0,
|
|
5035
|
-
"complexity": "beginner",
|
|
5036
|
-
"readingTime": "1 min",
|
|
5037
|
-
"contentLength": 1320,
|
|
5038
|
-
"relatedPages": []
|
|
5039
|
-
},
|
|
5040
|
-
"searchIndex": {
|
|
5041
|
-
"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",
|
|
5042
|
-
"importantTerms": [
|
|
5043
|
-
"langchain",
|
|
5044
|
-
"https",
|
|
5045
|
-
"learning",
|
|
5046
|
-
"resources",
|
|
5047
|
-
"documentation",
|
|
5048
|
-
"docs",
|
|
5049
|
-
"helpful",
|
|
5050
|
-
"concepts",
|
|
5051
|
-
"python",
|
|
5052
|
-
"code"
|
|
5053
|
-
]
|
|
5054
|
-
}
|
|
5055
|
-
},
|
|
5056
|
-
{
|
|
5057
|
-
"id": "page-0040",
|
|
5058
|
-
"title": "Langchain concepts in n8n",
|
|
5059
|
-
"url": "https://docs.n8n.io/advanced-ai/langchain/langchain-n8n/index.md",
|
|
5060
|
-
"urlPath": "advanced-ai/langchain/langchain-n8n/index.md",
|
|
5061
|
-
"category": "advanced-ai",
|
|
5062
|
-
"subcategory": "langchain",
|
|
5063
|
-
"nodeName": null,
|
|
5064
|
-
"nodeType": null,
|
|
5065
|
-
"content": {
|
|
5066
|
-
"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",
|
|
5067
|
-
"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...",
|
|
5068
|
-
"sections": [
|
|
5069
|
-
{
|
|
5070
|
-
"title": "LangChain concepts in n8n",
|
|
5071
|
-
"level": 1,
|
|
5072
|
-
"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)."
|
|
5073
|
-
}
|
|
5074
|
-
]
|
|
5075
|
-
},
|
|
5076
|
-
"metadata": {
|
|
5077
|
-
"keywords": [
|
|
5078
|
-
"langchain",
|
|
5079
|
-
"concepts",
|
|
5080
|
-
"trigger",
|
|
5081
|
-
"nodes",
|
|
5082
|
-
"cluster",
|
|
5083
|
-
"root",
|
|
5084
|
-
"chains",
|
|
5085
|
-
"agents",
|
|
5086
|
-
"vector",
|
|
5087
|
-
"stores",
|
|
5088
|
-
"miscellaneous",
|
|
5089
|
-
"document",
|
|
5090
|
-
"loaders",
|
|
5091
|
-
"language",
|
|
5092
|
-
"models",
|
|
5093
|
-
"memory",
|
|
5094
|
-
"output",
|
|
5095
|
-
"parsers",
|
|
5096
|
-
"retrievers",
|
|
5097
|
-
"text",
|
|
5098
|
-
"splitters",
|
|
5099
|
-
"tools",
|
|
5100
|
-
"embeddings"
|
|
5101
|
-
],
|
|
5102
|
-
"useCases": [],
|
|
5103
|
-
"operations": [],
|
|
5104
|
-
"codeExamples": 0,
|
|
5105
4874
|
"complexity": "intermediate",
|
|
5106
4875
|
"readingTime": "4 min",
|
|
5107
4876
|
"contentLength": 10758,
|
|
5108
4877
|
"relatedPages": []
|
|
5109
4878
|
},
|
|
5110
4879
|
"searchIndex": {
|
|
5111
|
-
"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",
|
|
4880
|
+
"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",
|
|
5112
4881
|
"importantTerms": [
|
|
5113
4882
|
"nodes",
|
|
5114
4883
|
"langchain",
|
|
@@ -5116,9 +4885,9 @@
|
|
|
5116
4885
|
"integrations",
|
|
5117
4886
|
"builtin",
|
|
5118
4887
|
"root",
|
|
4888
|
+
"vector",
|
|
5119
4889
|
"concepts",
|
|
5120
4890
|
"node",
|
|
5121
|
-
"vector",
|
|
5122
4891
|
"https",
|
|
5123
4892
|
"docs",
|
|
5124
4893
|
"glossary",
|
|
@@ -94265,7 +94034,7 @@
|
|
|
94265
94034
|
"page-0028",
|
|
94266
94035
|
"page-0029",
|
|
94267
94036
|
"page-0030",
|
|
94268
|
-
"page-
|
|
94037
|
+
"page-0037",
|
|
94269
94038
|
"page-0053",
|
|
94270
94039
|
"page-0147",
|
|
94271
94040
|
"page-0558",
|
|
@@ -95368,7 +95137,6 @@
|
|
|
95368
95137
|
"page-0003",
|
|
95369
95138
|
"page-0008",
|
|
95370
95139
|
"page-0013",
|
|
95371
|
-
"page-0040",
|
|
95372
95140
|
"page-0044",
|
|
95373
95141
|
"page-0051",
|
|
95374
95142
|
"page-0073",
|
|
@@ -95812,7 +95580,7 @@
|
|
|
95812
95580
|
"from": [
|
|
95813
95581
|
"page-0003",
|
|
95814
95582
|
"page-0015",
|
|
95815
|
-
"page-
|
|
95583
|
+
"page-0037",
|
|
95816
95584
|
"page-0043",
|
|
95817
95585
|
"page-0044",
|
|
95818
95586
|
"page-0050",
|
|
@@ -96256,7 +96024,6 @@
|
|
|
96256
96024
|
"page-0020",
|
|
96257
96025
|
"page-0026",
|
|
96258
96026
|
"page-0035",
|
|
96259
|
-
"page-0037",
|
|
96260
96027
|
"page-0541",
|
|
96261
96028
|
"page-0558",
|
|
96262
96029
|
"page-0559",
|
|
@@ -96717,7 +96484,6 @@
|
|
|
96717
96484
|
"page-0003",
|
|
96718
96485
|
"page-0006",
|
|
96719
96486
|
"page-0034",
|
|
96720
|
-
"page-0040",
|
|
96721
96487
|
"page-0209",
|
|
96722
96488
|
"page-0215",
|
|
96723
96489
|
"page-0220",
|
|
@@ -97734,7 +97500,7 @@
|
|
|
97734
97500
|
"page-0028",
|
|
97735
97501
|
"page-0029",
|
|
97736
97502
|
"page-0030",
|
|
97737
|
-
"page-
|
|
97503
|
+
"page-0037",
|
|
97738
97504
|
"page-0043",
|
|
97739
97505
|
"page-0047",
|
|
97740
97506
|
"page-0049",
|
|
@@ -98298,8 +98064,7 @@
|
|
|
98298
98064
|
"page-0006",
|
|
98299
98065
|
"page-0022",
|
|
98300
98066
|
"page-0036",
|
|
98301
|
-
"page-
|
|
98302
|
-
"page-0040",
|
|
98067
|
+
"page-0037",
|
|
98303
98068
|
"page-0528",
|
|
98304
98069
|
"page-0558",
|
|
98305
98070
|
"page-0559",
|
|
@@ -98328,7 +98093,6 @@
|
|
|
98328
98093
|
],
|
|
98329
98094
|
"cluster": [
|
|
98330
98095
|
"page-0006",
|
|
98331
|
-
"page-0040",
|
|
98332
98096
|
"page-0165",
|
|
98333
98097
|
"page-0201",
|
|
98334
98098
|
"page-0202",
|
|
@@ -98398,8 +98162,6 @@
|
|
|
98398
98162
|
],
|
|
98399
98163
|
"langchain": [
|
|
98400
98164
|
"page-0006",
|
|
98401
|
-
"page-0039",
|
|
98402
|
-
"page-0040",
|
|
98403
98165
|
"page-0042",
|
|
98404
98166
|
"page-0057",
|
|
98405
98167
|
"page-0554",
|
|
@@ -98412,7 +98174,6 @@
|
|
|
98412
98174
|
],
|
|
98413
98175
|
"language": [
|
|
98414
98176
|
"page-0006",
|
|
98415
|
-
"page-0040",
|
|
98416
98177
|
"page-0327",
|
|
98417
98178
|
"page-0556",
|
|
98418
98179
|
"page-0634",
|
|
@@ -98422,7 +98183,6 @@
|
|
|
98422
98183
|
"model": [
|
|
98423
98184
|
"page-0006",
|
|
98424
98185
|
"page-0018",
|
|
98425
|
-
"page-0037",
|
|
98426
98186
|
"page-0495",
|
|
98427
98187
|
"page-0498",
|
|
98428
98188
|
"page-0499",
|
|
@@ -98466,7 +98226,6 @@
|
|
|
98466
98226
|
],
|
|
98467
98227
|
"root": [
|
|
98468
98228
|
"page-0006",
|
|
98469
|
-
"page-0040",
|
|
98470
98229
|
"page-0114",
|
|
98471
98230
|
"page-0129",
|
|
98472
98231
|
"page-0204",
|
|
@@ -98490,7 +98249,6 @@
|
|
|
98490
98249
|
"page-0017",
|
|
98491
98250
|
"page-0021",
|
|
98492
98251
|
"page-0023",
|
|
98493
|
-
"page-0040",
|
|
98494
98252
|
"page-0043",
|
|
98495
98253
|
"page-0074",
|
|
98496
98254
|
"page-0085",
|
|
@@ -98883,8 +98641,7 @@
|
|
|
98883
98641
|
"page-1221"
|
|
98884
98642
|
],
|
|
98885
98643
|
"learning": [
|
|
98886
|
-
"page-0009"
|
|
98887
|
-
"page-0039"
|
|
98644
|
+
"page-0009"
|
|
98888
98645
|
],
|
|
98889
98646
|
"path": [
|
|
98890
98647
|
"page-0009",
|
|
@@ -98947,7 +98704,6 @@
|
|
|
98947
98704
|
"page-0009",
|
|
98948
98705
|
"page-0022",
|
|
98949
98706
|
"page-0036",
|
|
98950
|
-
"page-0040",
|
|
98951
98707
|
"page-0071",
|
|
98952
98708
|
"page-0325",
|
|
98953
98709
|
"page-0385",
|
|
@@ -99495,7 +99251,7 @@
|
|
|
99495
99251
|
"page-0029",
|
|
99496
99252
|
"page-0030",
|
|
99497
99253
|
"page-0036",
|
|
99498
|
-
"page-
|
|
99254
|
+
"page-0037",
|
|
99499
99255
|
"page-0052",
|
|
99500
99256
|
"page-0110",
|
|
99501
99257
|
"page-0111",
|
|
@@ -101437,7 +101193,6 @@
|
|
|
101437
101193
|
"resources": [
|
|
101438
101194
|
"page-0017",
|
|
101439
101195
|
"page-0020",
|
|
101440
|
-
"page-0039",
|
|
101441
101196
|
"page-0043",
|
|
101442
101197
|
"page-0051",
|
|
101443
101198
|
"page-0052",
|
|
@@ -102003,7 +101758,6 @@
|
|
|
102003
101758
|
],
|
|
102004
101759
|
"templates": [
|
|
102005
101760
|
"page-0017",
|
|
102006
|
-
"page-0037",
|
|
102007
101761
|
"page-0063",
|
|
102008
101762
|
"page-0161",
|
|
102009
101763
|
"page-0242",
|
|
@@ -102518,7 +102272,6 @@
|
|
|
102518
102272
|
"page-0022",
|
|
102519
102273
|
"page-0027",
|
|
102520
102274
|
"page-0032",
|
|
102521
|
-
"page-0040",
|
|
102522
102275
|
"page-0653"
|
|
102523
102276
|
],
|
|
102524
102277
|
"managing": [
|
|
@@ -102621,7 +102374,6 @@
|
|
|
102621
102374
|
"tools": [
|
|
102622
102375
|
"page-0020",
|
|
102623
102376
|
"page-0035",
|
|
102624
|
-
"page-0040",
|
|
102625
102377
|
"page-0043",
|
|
102626
102378
|
"page-0044",
|
|
102627
102379
|
"page-0205",
|
|
@@ -102769,7 +102521,6 @@
|
|
|
102769
102521
|
"concepts": [
|
|
102770
102522
|
"page-0021",
|
|
102771
102523
|
"page-0031",
|
|
102772
|
-
"page-0040",
|
|
102773
102524
|
"page-0053",
|
|
102774
102525
|
"page-0209",
|
|
102775
102526
|
"page-0714"
|
|
@@ -103051,8 +102802,7 @@
|
|
|
103051
102802
|
],
|
|
103052
102803
|
"chains": [
|
|
103053
102804
|
"page-0027",
|
|
103054
|
-
"page-0033"
|
|
103055
|
-
"page-0040"
|
|
102805
|
+
"page-0033"
|
|
103056
102806
|
],
|
|
103057
102807
|
"demonstration": [
|
|
103058
102808
|
"page-0027"
|
|
@@ -103173,7 +102923,6 @@
|
|
|
103173
102923
|
],
|
|
103174
102924
|
"examples": [
|
|
103175
102925
|
"page-0031",
|
|
103176
|
-
"page-0037",
|
|
103177
102926
|
"page-0043",
|
|
103178
102927
|
"page-0050",
|
|
103179
102928
|
"page-0060",
|
|
@@ -103667,211 +103416,25 @@
|
|
|
103667
103416
|
],
|
|
103668
103417
|
"document": [
|
|
103669
103418
|
"page-0036",
|
|
103670
|
-
"page-0040",
|
|
103671
103419
|
"page-0522",
|
|
103672
103420
|
"page-0523",
|
|
103673
103421
|
"page-0538",
|
|
103674
103422
|
"page-0583"
|
|
103675
103423
|
],
|
|
103676
103424
|
"loaders": [
|
|
103677
|
-
"page-0036"
|
|
103678
|
-
"page-0040"
|
|
103679
|
-
],
|
|
103680
|
-
"specify": [
|
|
103681
|
-
"page-0037",
|
|
103682
|
-
"page-0160",
|
|
103683
|
-
"page-0169",
|
|
103684
|
-
"page-0292",
|
|
103685
|
-
"page-0428",
|
|
103686
|
-
"page-0465"
|
|
103687
|
-
],
|
|
103688
|
-
"parameters": [
|
|
103689
|
-
"page-0037",
|
|
103690
|
-
"page-0044",
|
|
103691
|
-
"page-0070",
|
|
103692
|
-
"page-0074",
|
|
103693
|
-
"page-0161",
|
|
103694
|
-
"page-0309",
|
|
103695
|
-
"page-0364",
|
|
103696
|
-
"page-0392",
|
|
103697
|
-
"page-0483",
|
|
103698
|
-
"page-0506",
|
|
103699
|
-
"page-0524",
|
|
103700
|
-
"page-0528",
|
|
103701
|
-
"page-0529",
|
|
103702
|
-
"page-0530",
|
|
103703
|
-
"page-0538",
|
|
103704
|
-
"page-0540",
|
|
103705
|
-
"page-0544",
|
|
103706
|
-
"page-0552",
|
|
103707
|
-
"page-0553",
|
|
103708
|
-
"page-0554",
|
|
103709
|
-
"page-0555",
|
|
103710
|
-
"page-0556",
|
|
103711
|
-
"page-0557",
|
|
103712
|
-
"page-0558",
|
|
103713
|
-
"page-0559",
|
|
103714
|
-
"page-0560",
|
|
103715
|
-
"page-0561",
|
|
103716
|
-
"page-0562",
|
|
103717
|
-
"page-0563",
|
|
103718
|
-
"page-0564",
|
|
103719
|
-
"page-0565",
|
|
103720
|
-
"page-0566",
|
|
103721
|
-
"page-0567",
|
|
103722
|
-
"page-0568",
|
|
103723
|
-
"page-0569",
|
|
103724
|
-
"page-0572",
|
|
103725
|
-
"page-0573",
|
|
103726
|
-
"page-0574",
|
|
103727
|
-
"page-0575",
|
|
103728
|
-
"page-0576",
|
|
103729
|
-
"page-0577",
|
|
103730
|
-
"page-0578",
|
|
103731
|
-
"page-0582",
|
|
103732
|
-
"page-0583",
|
|
103733
|
-
"page-0584",
|
|
103734
|
-
"page-0586",
|
|
103735
|
-
"page-0587",
|
|
103736
|
-
"page-0588",
|
|
103737
|
-
"page-0589",
|
|
103738
|
-
"page-0590",
|
|
103739
|
-
"page-0591",
|
|
103740
|
-
"page-0592",
|
|
103741
|
-
"page-0593",
|
|
103742
|
-
"page-0596",
|
|
103743
|
-
"page-0597",
|
|
103744
|
-
"page-0598",
|
|
103745
|
-
"page-0599",
|
|
103746
|
-
"page-0600",
|
|
103747
|
-
"page-0601",
|
|
103748
|
-
"page-0602",
|
|
103749
|
-
"page-0603",
|
|
103750
|
-
"page-0604",
|
|
103751
|
-
"page-0605",
|
|
103752
|
-
"page-0606",
|
|
103753
|
-
"page-0608",
|
|
103754
|
-
"page-0609",
|
|
103755
|
-
"page-0610",
|
|
103756
|
-
"page-0612",
|
|
103757
|
-
"page-0613",
|
|
103758
|
-
"page-0614",
|
|
103759
|
-
"page-0615",
|
|
103760
|
-
"page-0616",
|
|
103761
|
-
"page-0617",
|
|
103762
|
-
"page-0618",
|
|
103763
|
-
"page-0619",
|
|
103764
|
-
"page-0620",
|
|
103765
|
-
"page-0621",
|
|
103766
|
-
"page-0624",
|
|
103767
|
-
"page-0627",
|
|
103768
|
-
"page-0628",
|
|
103769
|
-
"page-0629",
|
|
103770
|
-
"page-0630",
|
|
103771
|
-
"page-0631",
|
|
103772
|
-
"page-0632",
|
|
103773
|
-
"page-0634",
|
|
103774
|
-
"page-0636",
|
|
103775
|
-
"page-0640",
|
|
103776
|
-
"page-0643",
|
|
103777
|
-
"page-0644",
|
|
103778
|
-
"page-0645",
|
|
103779
|
-
"page-0646",
|
|
103780
|
-
"page-0647",
|
|
103781
|
-
"page-0648",
|
|
103782
|
-
"page-0649",
|
|
103783
|
-
"page-0650",
|
|
103784
|
-
"page-0652",
|
|
103785
|
-
"page-0653",
|
|
103786
|
-
"page-0655",
|
|
103787
|
-
"page-0656",
|
|
103788
|
-
"page-0657",
|
|
103789
|
-
"page-0658",
|
|
103790
|
-
"page-0659",
|
|
103791
|
-
"page-0661",
|
|
103792
|
-
"page-0663",
|
|
103793
|
-
"page-0664",
|
|
103794
|
-
"page-0665",
|
|
103795
|
-
"page-0668",
|
|
103796
|
-
"page-0669",
|
|
103797
|
-
"page-0672",
|
|
103798
|
-
"page-0673",
|
|
103799
|
-
"page-0674",
|
|
103800
|
-
"page-0675",
|
|
103801
|
-
"page-0678",
|
|
103802
|
-
"page-0681",
|
|
103803
|
-
"page-0683",
|
|
103804
|
-
"page-0684",
|
|
103805
|
-
"page-0686",
|
|
103806
|
-
"page-0687",
|
|
103807
|
-
"page-0689",
|
|
103808
|
-
"page-0692",
|
|
103809
|
-
"page-0693",
|
|
103810
|
-
"page-0694",
|
|
103811
|
-
"page-0695",
|
|
103812
|
-
"page-0696",
|
|
103813
|
-
"page-0697",
|
|
103814
|
-
"page-0698",
|
|
103815
|
-
"page-0699",
|
|
103816
|
-
"page-0700",
|
|
103817
|
-
"page-0701",
|
|
103818
|
-
"page-0703",
|
|
103819
|
-
"page-0704",
|
|
103820
|
-
"page-0705",
|
|
103821
|
-
"page-0706",
|
|
103822
|
-
"page-0708",
|
|
103823
|
-
"page-0709",
|
|
103824
|
-
"page-0710",
|
|
103825
|
-
"page-0711",
|
|
103826
|
-
"page-0712",
|
|
103827
|
-
"page-0713",
|
|
103828
|
-
"page-0720",
|
|
103829
|
-
"page-0722",
|
|
103830
|
-
"page-0723",
|
|
103831
|
-
"page-0724",
|
|
103832
|
-
"page-0726",
|
|
103833
|
-
"page-0728",
|
|
103834
|
-
"page-0731",
|
|
103835
|
-
"page-0750",
|
|
103836
|
-
"page-1058",
|
|
103837
|
-
"page-1121",
|
|
103838
|
-
"page-1152",
|
|
103839
|
-
"page-1178",
|
|
103840
|
-
"page-1189",
|
|
103841
|
-
"page-1191",
|
|
103842
|
-
"page-1192",
|
|
103843
|
-
"page-1266"
|
|
103844
|
-
],
|
|
103845
|
-
"fill": [
|
|
103846
|
-
"page-0037"
|
|
103847
|
-
],
|
|
103848
|
-
"parameter": [
|
|
103849
|
-
"page-0037",
|
|
103850
|
-
"page-0723",
|
|
103851
|
-
"page-1177",
|
|
103852
|
-
"page-1185",
|
|
103853
|
-
"page-1186",
|
|
103854
|
-
"page-1245"
|
|
103855
|
-
],
|
|
103856
|
-
"`$fromai()`": [
|
|
103857
|
-
"page-0037",
|
|
103858
|
-
"page-0577",
|
|
103859
|
-
"page-0632"
|
|
103860
|
-
],
|
|
103861
|
-
"function": [
|
|
103862
|
-
"page-0037"
|
|
103425
|
+
"page-0036"
|
|
103863
103426
|
],
|
|
103864
103427
|
"populate": [
|
|
103865
|
-
"page-
|
|
103428
|
+
"page-0037",
|
|
103866
103429
|
"page-0530"
|
|
103867
103430
|
],
|
|
103868
103431
|
"pinecone": [
|
|
103869
|
-
"page-
|
|
103432
|
+
"page-0037",
|
|
103870
103433
|
"page-0564",
|
|
103871
103434
|
"page-0934"
|
|
103872
103435
|
],
|
|
103873
103436
|
"database": [
|
|
103874
|
-
"page-
|
|
103437
|
+
"page-0037",
|
|
103875
103438
|
"page-0148",
|
|
103876
103439
|
"page-0154",
|
|
103877
103440
|
"page-0175",
|
|
@@ -103894,73 +103457,9 @@
|
|
|
103894
103457
|
"page-0996"
|
|
103895
103458
|
],
|
|
103896
103459
|
"website": [
|
|
103897
|
-
"page-
|
|
103460
|
+
"page-0037",
|
|
103898
103461
|
"page-0732"
|
|
103899
103462
|
],
|
|
103900
|
-
"stores": [
|
|
103901
|
-
"page-0040",
|
|
103902
|
-
"page-0209"
|
|
103903
|
-
],
|
|
103904
|
-
"miscellaneous": [
|
|
103905
|
-
"page-0040"
|
|
103906
|
-
],
|
|
103907
|
-
"models": [
|
|
103908
|
-
"page-0040"
|
|
103909
|
-
],
|
|
103910
|
-
"output": [
|
|
103911
|
-
"page-0040",
|
|
103912
|
-
"page-0044",
|
|
103913
|
-
"page-0050",
|
|
103914
|
-
"page-0061",
|
|
103915
|
-
"page-0066",
|
|
103916
|
-
"page-0099",
|
|
103917
|
-
"page-0108",
|
|
103918
|
-
"page-0210",
|
|
103919
|
-
"page-0552",
|
|
103920
|
-
"page-0572",
|
|
103921
|
-
"page-0573",
|
|
103922
|
-
"page-0574",
|
|
103923
|
-
"page-0575",
|
|
103924
|
-
"page-0577",
|
|
103925
|
-
"page-0622",
|
|
103926
|
-
"page-0623",
|
|
103927
|
-
"page-0646",
|
|
103928
|
-
"page-0652",
|
|
103929
|
-
"page-0653",
|
|
103930
|
-
"page-0658",
|
|
103931
|
-
"page-0672",
|
|
103932
|
-
"page-0693",
|
|
103933
|
-
"page-0697",
|
|
103934
|
-
"page-0704",
|
|
103935
|
-
"page-1186",
|
|
103936
|
-
"page-1221",
|
|
103937
|
-
"page-1235"
|
|
103938
|
-
],
|
|
103939
|
-
"parsers": [
|
|
103940
|
-
"page-0040",
|
|
103941
|
-
"page-0686"
|
|
103942
|
-
],
|
|
103943
|
-
"retrievers": [
|
|
103944
|
-
"page-0040"
|
|
103945
|
-
],
|
|
103946
|
-
"splitters": [
|
|
103947
|
-
"page-0040"
|
|
103948
|
-
],
|
|
103949
|
-
"embeddings": [
|
|
103950
|
-
"page-0040",
|
|
103951
|
-
"page-0584",
|
|
103952
|
-
"page-0585",
|
|
103953
|
-
"page-0586",
|
|
103954
|
-
"page-0587",
|
|
103955
|
-
"page-0588",
|
|
103956
|
-
"page-0589",
|
|
103957
|
-
"page-0590",
|
|
103958
|
-
"page-0591",
|
|
103959
|
-
"page-0592",
|
|
103960
|
-
"page-0593",
|
|
103961
|
-
"page-0594",
|
|
103962
|
-
"page-1221"
|
|
103963
|
-
],
|
|
103964
103463
|
"langsmith": [
|
|
103965
103464
|
"page-0041"
|
|
103966
103465
|
],
|
|
@@ -104268,6 +103767,190 @@
|
|
|
104268
103767
|
"page-1238",
|
|
104269
103768
|
"page-1239"
|
|
104270
103769
|
],
|
|
103770
|
+
"parameters": [
|
|
103771
|
+
"page-0044",
|
|
103772
|
+
"page-0070",
|
|
103773
|
+
"page-0074",
|
|
103774
|
+
"page-0161",
|
|
103775
|
+
"page-0309",
|
|
103776
|
+
"page-0364",
|
|
103777
|
+
"page-0392",
|
|
103778
|
+
"page-0483",
|
|
103779
|
+
"page-0506",
|
|
103780
|
+
"page-0524",
|
|
103781
|
+
"page-0528",
|
|
103782
|
+
"page-0529",
|
|
103783
|
+
"page-0530",
|
|
103784
|
+
"page-0538",
|
|
103785
|
+
"page-0540",
|
|
103786
|
+
"page-0544",
|
|
103787
|
+
"page-0552",
|
|
103788
|
+
"page-0553",
|
|
103789
|
+
"page-0554",
|
|
103790
|
+
"page-0555",
|
|
103791
|
+
"page-0556",
|
|
103792
|
+
"page-0557",
|
|
103793
|
+
"page-0558",
|
|
103794
|
+
"page-0559",
|
|
103795
|
+
"page-0560",
|
|
103796
|
+
"page-0561",
|
|
103797
|
+
"page-0562",
|
|
103798
|
+
"page-0563",
|
|
103799
|
+
"page-0564",
|
|
103800
|
+
"page-0565",
|
|
103801
|
+
"page-0566",
|
|
103802
|
+
"page-0567",
|
|
103803
|
+
"page-0568",
|
|
103804
|
+
"page-0569",
|
|
103805
|
+
"page-0572",
|
|
103806
|
+
"page-0573",
|
|
103807
|
+
"page-0574",
|
|
103808
|
+
"page-0575",
|
|
103809
|
+
"page-0576",
|
|
103810
|
+
"page-0577",
|
|
103811
|
+
"page-0578",
|
|
103812
|
+
"page-0582",
|
|
103813
|
+
"page-0583",
|
|
103814
|
+
"page-0584",
|
|
103815
|
+
"page-0586",
|
|
103816
|
+
"page-0587",
|
|
103817
|
+
"page-0588",
|
|
103818
|
+
"page-0589",
|
|
103819
|
+
"page-0590",
|
|
103820
|
+
"page-0591",
|
|
103821
|
+
"page-0592",
|
|
103822
|
+
"page-0593",
|
|
103823
|
+
"page-0596",
|
|
103824
|
+
"page-0597",
|
|
103825
|
+
"page-0598",
|
|
103826
|
+
"page-0599",
|
|
103827
|
+
"page-0600",
|
|
103828
|
+
"page-0601",
|
|
103829
|
+
"page-0602",
|
|
103830
|
+
"page-0603",
|
|
103831
|
+
"page-0604",
|
|
103832
|
+
"page-0605",
|
|
103833
|
+
"page-0606",
|
|
103834
|
+
"page-0608",
|
|
103835
|
+
"page-0609",
|
|
103836
|
+
"page-0610",
|
|
103837
|
+
"page-0612",
|
|
103838
|
+
"page-0613",
|
|
103839
|
+
"page-0614",
|
|
103840
|
+
"page-0615",
|
|
103841
|
+
"page-0616",
|
|
103842
|
+
"page-0617",
|
|
103843
|
+
"page-0618",
|
|
103844
|
+
"page-0619",
|
|
103845
|
+
"page-0620",
|
|
103846
|
+
"page-0621",
|
|
103847
|
+
"page-0624",
|
|
103848
|
+
"page-0627",
|
|
103849
|
+
"page-0628",
|
|
103850
|
+
"page-0629",
|
|
103851
|
+
"page-0630",
|
|
103852
|
+
"page-0631",
|
|
103853
|
+
"page-0632",
|
|
103854
|
+
"page-0634",
|
|
103855
|
+
"page-0636",
|
|
103856
|
+
"page-0640",
|
|
103857
|
+
"page-0643",
|
|
103858
|
+
"page-0644",
|
|
103859
|
+
"page-0645",
|
|
103860
|
+
"page-0646",
|
|
103861
|
+
"page-0647",
|
|
103862
|
+
"page-0648",
|
|
103863
|
+
"page-0649",
|
|
103864
|
+
"page-0650",
|
|
103865
|
+
"page-0652",
|
|
103866
|
+
"page-0653",
|
|
103867
|
+
"page-0655",
|
|
103868
|
+
"page-0656",
|
|
103869
|
+
"page-0657",
|
|
103870
|
+
"page-0658",
|
|
103871
|
+
"page-0659",
|
|
103872
|
+
"page-0661",
|
|
103873
|
+
"page-0663",
|
|
103874
|
+
"page-0664",
|
|
103875
|
+
"page-0665",
|
|
103876
|
+
"page-0668",
|
|
103877
|
+
"page-0669",
|
|
103878
|
+
"page-0672",
|
|
103879
|
+
"page-0673",
|
|
103880
|
+
"page-0674",
|
|
103881
|
+
"page-0675",
|
|
103882
|
+
"page-0678",
|
|
103883
|
+
"page-0681",
|
|
103884
|
+
"page-0683",
|
|
103885
|
+
"page-0684",
|
|
103886
|
+
"page-0686",
|
|
103887
|
+
"page-0687",
|
|
103888
|
+
"page-0689",
|
|
103889
|
+
"page-0692",
|
|
103890
|
+
"page-0693",
|
|
103891
|
+
"page-0694",
|
|
103892
|
+
"page-0695",
|
|
103893
|
+
"page-0696",
|
|
103894
|
+
"page-0697",
|
|
103895
|
+
"page-0698",
|
|
103896
|
+
"page-0699",
|
|
103897
|
+
"page-0700",
|
|
103898
|
+
"page-0701",
|
|
103899
|
+
"page-0703",
|
|
103900
|
+
"page-0704",
|
|
103901
|
+
"page-0705",
|
|
103902
|
+
"page-0706",
|
|
103903
|
+
"page-0708",
|
|
103904
|
+
"page-0709",
|
|
103905
|
+
"page-0710",
|
|
103906
|
+
"page-0711",
|
|
103907
|
+
"page-0712",
|
|
103908
|
+
"page-0713",
|
|
103909
|
+
"page-0720",
|
|
103910
|
+
"page-0722",
|
|
103911
|
+
"page-0723",
|
|
103912
|
+
"page-0724",
|
|
103913
|
+
"page-0726",
|
|
103914
|
+
"page-0728",
|
|
103915
|
+
"page-0731",
|
|
103916
|
+
"page-0750",
|
|
103917
|
+
"page-1058",
|
|
103918
|
+
"page-1121",
|
|
103919
|
+
"page-1152",
|
|
103920
|
+
"page-1178",
|
|
103921
|
+
"page-1189",
|
|
103922
|
+
"page-1191",
|
|
103923
|
+
"page-1192",
|
|
103924
|
+
"page-1266"
|
|
103925
|
+
],
|
|
103926
|
+
"output": [
|
|
103927
|
+
"page-0044",
|
|
103928
|
+
"page-0050",
|
|
103929
|
+
"page-0061",
|
|
103930
|
+
"page-0066",
|
|
103931
|
+
"page-0099",
|
|
103932
|
+
"page-0108",
|
|
103933
|
+
"page-0210",
|
|
103934
|
+
"page-0552",
|
|
103935
|
+
"page-0572",
|
|
103936
|
+
"page-0573",
|
|
103937
|
+
"page-0574",
|
|
103938
|
+
"page-0575",
|
|
103939
|
+
"page-0577",
|
|
103940
|
+
"page-0622",
|
|
103941
|
+
"page-0623",
|
|
103942
|
+
"page-0646",
|
|
103943
|
+
"page-0652",
|
|
103944
|
+
"page-0653",
|
|
103945
|
+
"page-0658",
|
|
103946
|
+
"page-0672",
|
|
103947
|
+
"page-0693",
|
|
103948
|
+
"page-0697",
|
|
103949
|
+
"page-0704",
|
|
103950
|
+
"page-1186",
|
|
103951
|
+
"page-1221",
|
|
103952
|
+
"page-1235"
|
|
103953
|
+
],
|
|
104271
103954
|
"details": [
|
|
104272
103955
|
"page-0044",
|
|
104273
103956
|
"page-0144",
|
|
@@ -108251,6 +107934,13 @@
|
|
|
108251
107934
|
"trust": [
|
|
108252
107935
|
"page-0159"
|
|
108253
107936
|
],
|
|
107937
|
+
"specify": [
|
|
107938
|
+
"page-0160",
|
|
107939
|
+
"page-0169",
|
|
107940
|
+
"page-0292",
|
|
107941
|
+
"page-0428",
|
|
107942
|
+
"page-0465"
|
|
107943
|
+
],
|
|
108254
107944
|
"location": [
|
|
108255
107945
|
"page-0160",
|
|
108256
107946
|
"page-0210",
|
|
@@ -109015,6 +108705,9 @@
|
|
|
109015
108705
|
"database,": [
|
|
109016
108706
|
"page-0209"
|
|
109017
108707
|
],
|
|
108708
|
+
"stores": [
|
|
108709
|
+
"page-0209"
|
|
108710
|
+
],
|
|
109018
108711
|
"openshift:": [
|
|
109019
108712
|
"page-0209"
|
|
109020
108713
|
],
|
|
@@ -112371,6 +112064,10 @@
|
|
|
112371
112064
|
"page-0577",
|
|
112372
112065
|
"page-1271"
|
|
112373
112066
|
],
|
|
112067
|
+
"`$fromai()`": [
|
|
112068
|
+
"page-0577",
|
|
112069
|
+
"page-0632"
|
|
112070
|
+
],
|
|
112374
112071
|
"produce": [
|
|
112375
112072
|
"page-0579"
|
|
112376
112073
|
],
|
|
@@ -112390,6 +112087,20 @@
|
|
|
112390
112087
|
"page-0582",
|
|
112391
112088
|
"page-0583"
|
|
112392
112089
|
],
|
|
112090
|
+
"embeddings": [
|
|
112091
|
+
"page-0584",
|
|
112092
|
+
"page-0585",
|
|
112093
|
+
"page-0586",
|
|
112094
|
+
"page-0587",
|
|
112095
|
+
"page-0588",
|
|
112096
|
+
"page-0589",
|
|
112097
|
+
"page-0590",
|
|
112098
|
+
"page-0591",
|
|
112099
|
+
"page-0592",
|
|
112100
|
+
"page-0593",
|
|
112101
|
+
"page-0594",
|
|
112102
|
+
"page-1221"
|
|
112103
|
+
],
|
|
112393
112104
|
"bedrock": [
|
|
112394
112105
|
"page-0584",
|
|
112395
112106
|
"page-0597"
|
|
@@ -112883,6 +112594,9 @@
|
|
|
112883
112594
|
"page-1220",
|
|
112884
112595
|
"page-1271"
|
|
112885
112596
|
],
|
|
112597
|
+
"parsers": [
|
|
112598
|
+
"page-0686"
|
|
112599
|
+
],
|
|
112886
112600
|
"position": [
|
|
112887
112601
|
"page-0687"
|
|
112888
112602
|
],
|
|
@@ -113131,6 +112845,13 @@
|
|
|
113131
112845
|
"could": [
|
|
113132
112846
|
"page-0723"
|
|
113133
112847
|
],
|
|
112848
|
+
"parameter": [
|
|
112849
|
+
"page-0723",
|
|
112850
|
+
"page-1177",
|
|
112851
|
+
"page-1185",
|
|
112852
|
+
"page-1186",
|
|
112853
|
+
"page-1245"
|
|
112854
|
+
],
|
|
113134
112855
|
"duplicates": [
|
|
113135
112856
|
"page-0724",
|
|
113136
112857
|
"page-0725",
|
|
@@ -115253,9 +114974,6 @@
|
|
|
115253
114974
|
"page-0035",
|
|
115254
114975
|
"page-0036",
|
|
115255
114976
|
"page-0037",
|
|
115256
|
-
"page-0038",
|
|
115257
|
-
"page-0039",
|
|
115258
|
-
"page-0040",
|
|
115259
114977
|
"page-0041",
|
|
115260
114978
|
"page-0042",
|
|
115261
114979
|
"page-0043",
|