@n8n-as-code/skills 1.8.0 → 1.8.1

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

@@ -1,5 +1,5 @@
 {
-  "generatedAt": "2026-04-09T13:50:19.318Z",
+  "generatedAt": "2026-04-09T19:44:57.386Z",
   "version": "1.0.0",
   "sourceUrl": "https://docs.n8n.io/llms.txt",
   "totalPages": 1262,
@@ -43619,34 +43619,35 @@
     },
     {
       "id": "page-0556",
-      "title": "Weaviate Vector Store",
-      "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreweaviate/index.md",
-      "urlPath": "integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreweaviate/index.md",
+      "title": "Supabase Vector Store",
+      "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/index.md",
+      "urlPath": "integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/index.md",
       "category": "cluster-nodes",
       "subcategory": null,
       "nodeName": null,
       "nodeType": null,
       "content": {
-        "markdown": "# Weaviate Vector Store node\n\nUse the Weaviate node to interact with your Weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into or retrieve documents from a vector database. You can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). On this page, you'll find the node parameters for the Weaviate node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/weaviate/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## Node usage patterns\n\nYou can use the Weaviate Vector Store node in the following patterns.\n\n### Use as a regular node to insert and retrieve documents\n\nYou can use the Weaviate Vector Store as a regular node to insert or get documents. This pattern places the Weaviate Vector Store in the regular connection flow without using an agent.\n\n### Connect directly to an AI agent as a tool\n\nYou can connect the Weaviate Vector Store node directly to the tool connector of an [AI agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nHere, the connection would be: AI agent (tools connector) -> Weaviate Vector Store node.\n\n### Use a retriever to fetch documents\n\nYou can use the [Vector Store Retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the Weaviate Vector Store node to fetch documents from the Weaviate Vector Store node. This is often used with the [Question and Answer Chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\n### Use the Vector Store Question Answer Tool to answer questions\n\nAnother pattern uses the [Vector Store Question Answer Tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the Weaviate Vector Store node. Rather than connecting the Weaviate Vector Store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\n## Node parameters\n\nMultitenancy\n\nYou can separate your data into isolated tenants for the same collection (for example, for different customers). For that, you must always provide a [Tenant Name](#tenant-name) both when inserting and retrieving objects. [Read more about multi tenancy in Weaviate docs](https://docs.weaviate.io/weaviate/manage-collections/multi-tenancy).\n\n### Operation Mode\n\nThis Vector Store node has four modes: **Get Many**, **Insert Documents**, **Retrieve Documents (As Vector Store for Chain/Tool)**, and **Retrieve Documents (As Tool for AI Agent)**. The mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### Get Many\n\nIn this mode, you can retrieve multiple documents from your vector database by providing a prompt. The prompt is embedded and used for similarity search. The node returns the documents that are most similar to the prompt with their similarity score. This is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### Insert Documents\n\nUse insert documents mode to insert new documents into your vector database.\n\n#### Retrieve Documents (as Vector Store for Chain/Tool)\n\nUse Retrieve Documents (As Vector Store for Chain/Tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. In this mode you must connect the node to a retriever node or root node.\n\n#### Retrieve Documents (as Tool for AI Agent)\n\nUse Retrieve Documents (As Tool for AI Agent) mode to use the vector store as a tool resource when answering queries. When formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n### Get Many parameters\n\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n- **Prompt**: Enter the search query.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Insert Documents parameters\n\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n- **Embedding Batch Size**: The number of documents to embed in a single batch. The default is 200 documents.\n\n### Retrieve Documents (As Vector Store for Chain/Tool) parameters\n\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n\n### Retrieve Documents (As Tool for AI Agent) parameters\n\n- **Weaviate Collection**: The name of the vector store.\n- **Description**: Explain to the LLM what this tool does. A good, specific description allows LLMs to produce expected results more often.\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Include Metadata\n\nWhether to include document metadata.\n\nYou can use this with the [Get Many](#get-many) and [Retrieve Documents (As Tool for AI Agent)](#retrieve-documents-as-tool-for-ai-agent-parameters) modes.\n\n### Rerank Results\n\nEnables [reranking](../../../../../glossary/#ai-reranking). If you enable this option, you must connect a reranking node to the vector store. That node will then rerank the results for queries. You can use this option with the `Get Many`, `Retrieve Documents (As Vector Store for Chain/Tool)` and `Retrieve Documents (As Tool for AI Agent)` modes.\n\n## Node options\n\n### Search Filters\n\nAvailable for the [Get Many](#get-many), [Retrieve Documents (As Vector Store for Chain/Tool)](#retrieve-documents-as-vector-store-for-chaintool), and [Retrieve Documents (As Tool for AI Agent)](#retrieve-documents-as-tool-for-ai-agent) operation modes.\n\nWhen searching for data, use this to match metadata associated with documents. You can learn more about the operators and query structure in [Weaviate's conditional filters documentation](https://docs.weaviate.io/weaviate/api/graphql/filters).\n\nYou can use both `AND` and `OR` with different operators. Operators are case insensitive:\n\n```\n{\n  \"OR\": [\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"Equal\",\n        \"valueString\": \"source1\"\n    },\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"Equal\",\n        \"valueString\": \"source1\"\n    }\n  ]\n}\n```\n\nSupported operators:\n\n| Operator           | Required Field(s)                                    | Description                                                                                                                                                                       |\n| ------------------ | ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `'equal'`          | `valueString` or `valueNumber`                       | Checks if the property is equal to the given string or number.                                                                                                                    |\n| `'like'`           | `valueString`                                        | Checks if the string property matches a pattern (for example, sub-string match).                                                                                                  |\n| `'containsAny'`    | `valueTextArray` (string[])                          | Checks if the property contains **any** of the given values.                                                                                                                      |\n| `'containsAll'`    | `valueTextArray` (string[])                          | Checks if the property contains **all** of the given values.                                                                                                                      |\n| `'greaterThan'`    | `valueNumber`                                        | Checks if the property value is greater than the given number.                                                                                                                    |\n| `'lessThan'`       | `valueNumber`                                        | Checks if the property value is less than the given number.                                                                                                                       |\n| `'isNull'`         | `valueBoolean` (true/false)                          | Checks if the property is null or not. ([must enable before ingestion](https://docs.weaviate.io/weaviate/manage-collections/collection-operations#set-inverted-index-parameters)) |\n| `'withinGeoRange'` | `valueGeoCoordinates` (object with geolocation data) | Filters by proximity to geographic coordinates.                                                                                                                                   |\n\nWhen inserting data, the document loader sets the metadata. Refer to [Default Data Loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information on loading documents.\n\n### Metadata Keys\n\nYou can define which metadata keys you want Weaviate to return on your queries. This can reduce network load, as you will only get properties you have defined. Returns all properties from the server by default.\n\nAvailable for the [Get Many](#get-many), [Retrieve Documents (As Vector Store for Chain/Tool)](#retrieve-documents-as-vector-store-for-chaintool), and [Retrieve Documents (As Tool for AI Agent)](#retrieve-documents-as-tool-for-ai-agent) operation modes.\n\n### Hybrid: Query Text\n\nProvide a query text to combine vector search with a keyword/text search.\n\n### Hybrid: Explain Score\n\nWhether to show the score fused between hybrid and vector search explanation.\n\n### Hybrid: Fusion Type\n\nSelect the fusion type for combining vector and keyword search results. [Learn more about fusion algorithms](https://weaviate.io/learn/knowledgecards/fusion-algorithm).\n\nOptions:\n\n- **Relative Score**: Uses relative score fusion\n- **Ranked**: Uses ranked fusion\n\n### Hybrid: Auto Cut Limit\n\nLimit result groups by detecting sudden jumps in score. [Learn more about autocut](https://docs.weaviate.io/weaviate/api/graphql/additional-operators#autocut).\n\n### Hybrid: Alpha\n\nChange the relative weights of the keyword and vector components. 1.0 = pure vector, 0.0 = pure keyword. Default is 0.5. [Learn more about the alpha parameter](https://weaviate.io/learn/knowledgecards/alpha-parameter).\n\n### Hybrid: Query Properties\n\nComma-separated list of properties to include in the query with optionally weighted values, e.g., \"question^2,answer\". [Learn more about setting weights on property values](https://docs.weaviate.io/weaviate/search/hybrid#set-weights-on-property-values).\n\n### Hybrid: Max Vector Distance\n\nSet the maximum allowable distance for the vector search component.\n\n### Tenant Name\n\nThe specific tenant to store or retrieve documents for. [Learn more about multi-tenancy](https://weaviate.io/learn/knowledgecards/multi-tenancy).\n\nMust enable at creation\n\nYou must pass a tenant name at first ingestion to enable multitenancy for a collection. You can't enable or disable multitenancy after creation.\n\n### Text Key\n\nThe key in the document that contains the embedded text.\n\n### Skip Init Checks\n\nWhether to [skip initialization checks](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#initial-connection-checks) when instantiating the client.\n\n### Init Timeout\n\nNumber of seconds to wait before [timing out](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#timeout-values) during initial checks.\n\n### Insert Timeout\n\nNumber of seconds to wait before [timing out](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#timeout-values) during inserts.\n\n### Query Timeout\n\nNumber of seconds to wait before [timing out](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#timeout-values) during queries.\n\n### GRPC Proxy\n\nA proxy to use for gRPC requests.\n\n### Clear Data\n\nAvailable for the [Insert Documents](#insert-documents) operation mode.\n\nWhether to clear the collection or tenant before inserting new data.\n\n## Templates and examples\n\n**Build a Weekly AI Trend Alerter with arXiv and Weaviate**\n\nby Mary Newhauser\n\n[View template details](https://n8n.io/workflows/5817-build-a-weekly-ai-trend-alerter-with-arxiv-and-weaviate/)\n\n**Build person OSINT profiles using Humantic AI, Hunter, CourtListener and GPT-5**\n\nby Open Paws\n\n[View template details](https://n8n.io/workflows/12507-build-person-osint-profiles-using-humantic-ai-hunter-courtlistener-and-gpt-5/)\n\n**Research organizations with GPT‑5, Gemini, CourtListener, LegiScan and OSINT web sources**\n\nby Open Paws\n\n[View template details](https://n8n.io/workflows/12506-research-organizations-with-gpt5-gemini-courtlistener-legiscan-and-osint-web-sources/)\n\n[Browse Weaviate Vector Store integration templates](https://n8n.io/integrations/weaviate-vector-store/), or [search all templates](https://n8n.io/workflows/)\n\n## Related resources\n\nRefer to [LangChain's Weaviate documentation](https://js.langchain.com/docs/integrations/vectorstores/weaviate/) for more information about the service.\n\nRefer to [Weaviate Installation](https://docs.weaviate.io/deploy) for a self hosted Weaviate Cluster.\n\nView n8n's [Advanced AI](../../../../../advanced-ai/) documentation.\n",
-        "excerpt": "# Weaviate Vector Store node  Use the Weaviate node to interact with your Weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into or retrieve documents from a vector database. You can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). On this page,...",
+        "markdown": "# Supabase Vector Store node\n\nUse the Supabase Vector Store to interact with your Supabase database as vector store. You can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.\n\nUse the Supabase Vector Store to interact with your Supabase database as [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into a vector database, get documents from a vector database, retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain), or connect it directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). You can also update an item in a vector store by its ID.\n\nOn this page, you'll find the node parameters for the Supabase node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/supabase/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\nSupabase provides a [quickstart for setting up your vector store](https://supabase.com/docs/guides/ai/langchain?database-method=sql). If you use settings other than the defaults in the quickstart, this may affect parameter settings in n8n. Make sure you understand what you're doing.\n\n## Node usage patterns\n\nYou can use the Supabase Vector Store node in the following patterns.\n\n### Use as a regular node to insert, update, and retrieve documents\n\nYou can use the Supabase Vector Store as a regular node to insert, update, or get documents. This pattern places the Supabase Vector Store in the regular connection flow without using an agent.\n\nYou can see an example of this in scenario 1 of [this template](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/).\n\n### Connect directly to an AI agent as a tool\n\nYou can connect the Supabase Vector Store node directly to the tool connector of an [AI agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nHere, the connection would be: AI agent (tools connector) -> Supabase Vector Store node.\n\n### Use a retriever to fetch documents\n\nYou can use the [Vector Store Retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the Supabase Vector Store node to fetch documents from the Supabase Vector Store node. This is often used with the [Question and Answer Chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\nAn [example of the connection flow](https://n8n.io/workflows/1960-ask-questions-about-a-pdf-using-ai/) (the example uses Pinecone, but the pattern in the same) would be: Question and Answer Chain (Retriever connector) -> Vector Store Retriever (Vector Store connector) -> Supabase Vector Store.\n\n### Use the Vector Store Question Answer Tool to answer questions\n\nAnother pattern uses the [Vector Store Question Answer Tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the Supabase Vector Store node. Rather than connecting the Supabase Vector Store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\nThe [connections flow](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/) in this case would look like this: AI agent (tools connector) -> Vector Store Question Answer Tool (Vector Store connector) -> Supabase Vector store.\n\n## Node parameters\n\n### Operation Mode\n\nThis Vector Store node has five modes: **Get Many**, **Insert Documents**, **Retrieve Documents (As Vector Store for Chain/Tool)**, **Retrieve Documents (As Tool for AI Agent)**, and **Update Documents**. The mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### Get Many\n\nIn this mode, you can retrieve multiple documents from your vector database by providing a prompt. The prompt will be embedded and used for similarity search. The node will return the documents that are most similar to the prompt with their similarity score. This is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### Insert Documents\n\nUse Insert Documents mode to insert new documents into your vector database.\n\n#### Retrieve Documents (As Vector Store for Chain/Tool)\n\nUse Retrieve Documents (As Vector Store for Chain/Tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. In this mode you must connect the node to a retriever node or root node.\n\n#### Retrieve Documents (As Tool for AI Agent)\n\nUse Retrieve Documents (As Tool for AI Agent) mode to use the vector store as a tool resource when answering queries. When formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n#### Update Documents\n\nUse Update Documents mode to update documents in a vector database by ID. Fill in the **ID** with the ID of the embedding entry to update.\n\n### Rerank Results\n\nEnables [reranking](../../../../../glossary/#ai-reranking). If you enable this option, you must connect a reranking node to the vector store. That node will then rerank the results for queries. You can use this option with the `Get Many`, `Retrieve Documents (As Vector Store for Chain/Tool)` and `Retrieve Documents (As Tool for AI Agent)` modes.\n\n### Get Many parameters\n\n- **Table Name**: Enter the Supabase table to use.\n- **Prompt**: Enter the search query.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Insert Documents parameters\n\n- **Table Name**: Enter the Supabase table to use.\n\n### Retrieve Documents (As Vector Store for Chain/Tool) parameters\n\n- **Table Name**: Enter the Supabase table to use.\n\n### Retrieve Documents (As Tool for AI Agent) parameters\n\n- **Name**: The name of the vector store.\n- **Description**: Explain to the LLM what this tool does. A good, specific description allows LLMs to produce expected results more often.\n- **Table Name**: Enter the Supabase table to use.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Update Documents\n\n- **Table Name**: Enter the Supabase table to use.\n- **ID**: The ID of an embedding entry.\n\nParameters for **Update Documents**\n\n- ID\n\n## Node options\n\n### Query Name\n\nThe name of the matching function you set up in Supabase. If you follow the [Supabase quickstart](https://supabase.com/docs/guides/ai/langchain?database-method=sql), this will be `match_documents`.\n\n### Metadata Filter\n\nAvailable in **Get Many** mode. When searching for data, use this to match with metadata associated with the document.\n\nThis is an `AND` query. If you specify more than one metadata filter field, all of them must match.\n\nWhen inserting data, the metadata is set using the document loader. Refer to [Default Data Loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information on loading documents.\n\n## Templates and examples\n\n**AI Agent To Chat With Files In Supabase Storage**\n\nby Mark Shcherbakov\n\n[View template details](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/)\n\n**Automate sales cold calling pipeline with Apify, GPT-4o, and WhatsApp**\n\nby Khairul Muhtadin\n\n[View template details](https://n8n.io/workflows/5449-automate-sales-cold-calling-pipeline-with-apify-gpt-4o-and-whatsapp/)\n\n**🤖 Create a Documentation Expert Bot with RAG, Gemini, and Supabase**\n\nby Lucas Peyrin\n\n[View template details](https://n8n.io/workflows/5993-create-a-documentation-expert-bot-with-rag-gemini-and-supabase/)\n\n[Browse Supabase Vector Store integration templates](https://n8n.io/integrations/supabase-vector-store/), or [search all templates](https://n8n.io/workflows/)\n\n## Related resources\n\nRefer to [LangChain's Supabase documentation](https://js.langchain.com/docs/integrations/vectorstores/supabase/) for more information about the service.\n\nView n8n's [Advanced AI](../../../../../advanced-ai/) documentation.\n",
+        "excerpt": "# Supabase Vector Store node  Use the Supabase Vector Store to interact with your Supabase database as vector store. You can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.  Use the Supabase Vector Store to interact with your Supabase database as [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into a vector database, get documents from a vector databa...",
         "sections": [
           {
-            "title": "Weaviate Vector Store node",
+            "title": "Supabase Vector Store node",
             "level": 1,
-            "content": "Use the Weaviate node to interact with your Weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into or retrieve documents from a vector database. You can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). On this page, you'll find the node parameters for the Weaviate node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/weaviate/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for "
+            "content": "Use the Supabase Vector Store to interact with your Supabase database as vector store. You can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.\n\nUse the Supabase Vector Store to interact with your Supabase database as [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into a vector database, get documents from a vector database, retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain), or connect it directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). You can also update an item in a vector store by its ID.\n\nOn this page, you'll find the node parameters for the Supabase node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/supabase/).\n\nParameter resolution in su"
           }
         ]
       },
       "metadata": {
         "keywords": [
-          "weaviate",
+          "supabase",
           "vector",
           "store",
           "node",
           "usage",
           "patterns",
           "regular",
-          "insert",
+          "insert,",
+          "update,",
           "retrieve",
           "documents",
           "connect",
@@ -43662,38 +43663,17 @@
           "operation",
           "mode",
           "many",
+          "insert",
           "chain/tool)",
           "agent)",
-          "include",
-          "metadata",
+          "update",
           "rerank",
           "results",
           "options",
-          "search",
-          "filters",
-          "keys",
-          "hybrid:",
           "query",
-          "text",
-          "explain",
-          "score",
-          "fusion",
-          "type",
-          "auto",
-          "limit",
-          "alpha",
-          "properties",
-          "distance",
-          "tenant",
           "name",
-          "skip",
-          "init",
-          "checks",
-          "timeout",
-          "grpc",
-          "proxy",
-          "clear",
-          "data",
+          "metadata",
+          "filter",
           "templates",
           "examples",
           "related",
@@ -43703,99 +43683,98 @@
         "operations": [
           "mode"
         ],
-        "codeExamples": 1,
+        "codeExamples": 0,
         "complexity": "intermediate",
-        "readingTime": "9 min",
-        "contentLength": 14378,
+        "readingTime": "7 min",
+        "contentLength": 8921,
         "relatedPages": []
       },
       "searchIndex": {
-        "fullText": "weaviate vector store # weaviate vector store node\n\nuse the weaviate node to interact with your weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). you can insert documents into or retrieve documents from a vector database. you can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). on this page, you'll find the node parameters for the weaviate node, and links to more resources.\n\ncredentials\n\nyou can find authentication information for this node [here](../../../credentials/weaviate/).\n\nparameter resolution in sub-nodes\n\nsub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nmost nodes, including root nodes, take any number of items as input, process these items, and output the results. you can use expressions to refer to input items, and the node resolves the expression for each item in turn. for example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nin sub-nodes, the expression always resolves to the first item. for example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## node usage patterns\n\nyou can use the weaviate vector store node in the following patterns.\n\n### use as a regular node to insert and retrieve documents\n\nyou can use the weaviate vector store as a regular node to insert or get documents. this pattern places the weaviate vector store in the regular connection flow without using an agent.\n\n### connect directly to an ai agent as a tool\n\nyou can connect the weaviate vector store node directly to the tool connector of an [ai agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nhere, the connection would be: ai agent (tools connector) -> weaviate vector store node.\n\n### use a retriever to fetch documents\n\nyou can use the [vector store retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the weaviate vector store node to fetch documents from the weaviate vector store node. this is often used with the [question and answer chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\n### use the vector store question answer tool to answer questions\n\nanother pattern uses the [vector store question answer tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the weaviate vector store node. rather than connecting the weaviate vector store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\n## node parameters\n\nmultitenancy\n\nyou can separate your data into isolated tenants for the same collection (for example, for different customers). for that, you must always provide a [tenant name](#tenant-name) both when inserting and retrieving objects. [read more about multi tenancy in weaviate docs](https://docs.weaviate.io/weaviate/manage-collections/multi-tenancy).\n\n### operation mode\n\nthis vector store node has four modes: **get many**, **insert documents**, **retrieve documents (as vector store for chain/tool)**, and **retrieve documents (as tool for ai agent)**. the mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### get many\n\nin this mode, you can retrieve multiple documents from your vector database by providing a prompt. the prompt is embedded and used for similarity search. the node returns the documents that are most similar to the prompt with their similarity score. this is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### insert documents\n\nuse insert documents mode to insert new documents into your vector database.\n\n#### retrieve documents (as vector store for chain/tool)\n\nuse retrieve documents (as vector store for chain/tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. in this mode you must connect the node to a retriever node or root node.\n\n#### retrieve documents (as tool for ai agent)\n\nuse retrieve documents (as tool for ai agent) mode to use the vector store as a tool resource when answering queries. when formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n### get many parameters\n\n- **weaviate collection**: enter the name of the weaviate collection to use.\n- **prompt**: enter the search query.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### insert documents parameters\n\n- **weaviate collection**: enter the name of the weaviate collection to use.\n- **embedding batch size**: the number of documents to embed in a single batch. the default is 200 documents.\n\n### retrieve documents (as vector store for chain/tool) parameters\n\n- **weaviate collection**: enter the name of the weaviate collection to use.\n\n### retrieve documents (as tool for ai agent) parameters\n\n- **weaviate collection**: the name of the vector store.\n- **description**: explain to the llm what this tool does. a good, specific description allows llms to produce expected results more often.\n- **weaviate collection**: enter the name of the weaviate collection to use.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### include metadata\n\nwhether to include document metadata.\n\nyou can use this with the [get many](#get-many) and [retrieve documents (as tool for ai agent)](#retrieve-documents-as-tool-for-ai-agent-parameters) modes.\n\n### rerank results\n\nenables [reranking](../../../../../glossary/#ai-reranking). if you enable this option, you must connect a reranking node to the vector store. that node will then rerank the results for queries. you can use this option with the `get many`, `retrieve documents (as vector store for chain/tool)` and `retrieve documents (as tool for ai agent)` modes.\n\n## node options\n\n### search filters\n\navailable for the [get many](#get-many), [retrieve documents (as vector store for chain/tool)](#retrieve-documents-as-vector-store-for-chaintool), and [retrieve documents (as tool for ai agent)](#retrieve-documents-as-tool-for-ai-agent) operation modes.\n\nwhen searching for data, use this to match metadata associated with documents. you can learn more about the operators and query structure in [weaviate's conditional filters documentation](https://docs.weaviate.io/weaviate/api/graphql/filters).\n\nyou can use both `and` and `or` with different operators. operators are case insensitive:\n\n```\n{\n  \"or\": [\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"equal\",\n        \"valuestring\": \"source1\"\n    },\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"equal\",\n        \"valuestring\": \"source1\"\n    }\n  ]\n}\n```\n\nsupported operators:\n\n| operator           | required field(s)                                    | description                                                                                                                                                                       |\n| ------------------ | ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `'equal'`          | `valuestring` or `valuenumber`                       | checks if the property is equal to the given string or number.                                                                                                                    |\n| `'like'`           | `valuestring`                                        | checks if the string property matches a pattern (for example, sub-string match).                                                                                                  |\n| `'containsany'`    | `valuetextarray` (string[])                          | checks if the property contains **any** of the given values.                                                                                                                      |\n| `'containsall'`    | `valuetextarray` (string[])                          | checks if the property contains **all** of the given values.                                                                                                                      |\n| `'greaterthan'`    | `valuenumber`                                        | checks if the property value is greater than the given number.                                                                                                                    |\n| `'lessthan'`       | `valuenumber`                                        | checks if the property value is less than the given number.                                                                                                                       |\n| `'isnull'`         | `valueboolean` (true/false)                          | checks if the property is null or not. ([must enable before ingestion](https://docs.weaviate.io/weaviate/manage-collections/collection-operations#set-inverted-index-parameters)) |\n| `'withingeorange'` | `valuegeocoordinates` (object with geolocation data) | filters by proximity to geographic coordinates.                                                                                                                                   |\n\nwhen inserting data, the document loader sets the metadata. refer to [default data loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information ",
+        "fullText": "supabase vector store # supabase vector store node\n\nuse the supabase vector store to interact with your supabase database as vector store. you can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.\n\nuse the supabase vector store to interact with your supabase database as [vector store](../../../../../glossary/#ai-vector-store). you can insert documents into a vector database, get documents from a vector database, retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain), or connect it directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). you can also update an item in a vector store by its id.\n\non this page, you'll find the node parameters for the supabase node, and links to more resources.\n\ncredentials\n\nyou can find authentication information for this node [here](../../../credentials/supabase/).\n\nparameter resolution in sub-nodes\n\nsub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nmost nodes, including root nodes, take any number of items as input, process these items, and output the results. you can use expressions to refer to input items, and the node resolves the expression for each item in turn. for example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nin sub-nodes, the expression always resolves to the first item. for example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\nsupabase provides a [quickstart for setting up your vector store](https://supabase.com/docs/guides/ai/langchain?database-method=sql). if you use settings other than the defaults in the quickstart, this may affect parameter settings in n8n. make sure you understand what you're doing.\n\n## node usage patterns\n\nyou can use the supabase vector store node in the following patterns.\n\n### use as a regular node to insert, update, and retrieve documents\n\nyou can use the supabase vector store as a regular node to insert, update, or get documents. this pattern places the supabase vector store in the regular connection flow without using an agent.\n\nyou can see an example of this in scenario 1 of [this template](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/).\n\n### connect directly to an ai agent as a tool\n\nyou can connect the supabase vector store node directly to the tool connector of an [ai agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nhere, the connection would be: ai agent (tools connector) -> supabase vector store node.\n\n### use a retriever to fetch documents\n\nyou can use the [vector store retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the supabase vector store node to fetch documents from the supabase vector store node. this is often used with the [question and answer chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\nan [example of the connection flow](https://n8n.io/workflows/1960-ask-questions-about-a-pdf-using-ai/) (the example uses pinecone, but the pattern in the same) would be: question and answer chain (retriever connector) -> vector store retriever (vector store connector) -> supabase vector store.\n\n### use the vector store question answer tool to answer questions\n\nanother pattern uses the [vector store question answer tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the supabase vector store node. rather than connecting the supabase vector store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\nthe [connections flow](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/) in this case would look like this: ai agent (tools connector) -> vector store question answer tool (vector store connector) -> supabase vector store.\n\n## node parameters\n\n### operation mode\n\nthis vector store node has five modes: **get many**, **insert documents**, **retrieve documents (as vector store for chain/tool)**, **retrieve documents (as tool for ai agent)**, and **update documents**. the mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### get many\n\nin this mode, you can retrieve multiple documents from your vector database by providing a prompt. the prompt will be embedded and used for similarity search. the node will return the documents that are most similar to the prompt with their similarity score. this is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### insert documents\n\nuse insert documents mode to insert new documents into your vector database.\n\n#### retrieve documents (as vector store for chain/tool)\n\nuse retrieve documents (as vector store for chain/tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. in this mode you must connect the node to a retriever node or root node.\n\n#### retrieve documents (as tool for ai agent)\n\nuse retrieve documents (as tool for ai agent) mode to use the vector store as a tool resource when answering queries. when formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n#### update documents\n\nuse update documents mode to update documents in a vector database by id. fill in the **id** with the id of the embedding entry to update.\n\n### rerank results\n\nenables [reranking](../../../../../glossary/#ai-reranking). if you enable this option, you must connect a reranking node to the vector store. that node will then rerank the results for queries. you can use this option with the `get many`, `retrieve documents (as vector store for chain/tool)` and `retrieve documents (as tool for ai agent)` modes.\n\n### get many parameters\n\n- **table name**: enter the supabase table to use.\n- **prompt**: enter the search query.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### insert documents parameters\n\n- **table name**: enter the supabase table to use.\n\n### retrieve documents (as vector store for chain/tool) parameters\n\n- **table name**: enter the supabase table to use.\n\n### retrieve documents (as tool for ai agent) parameters\n\n- **name**: the name of the vector store.\n- **description**: explain to the llm what this tool does. a good, specific description allows llms to produce expected results more often.\n- **table name**: enter the supabase table to use.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### update documents\n\n- **table name**: enter the supabase table to use.\n- **id**: the id of an embedding entry.\n\nparameters for **update documents**\n\n- id\n\n## node options\n\n### query name\n\nthe name of the matching function you set up in supabase. if you follow the [supabase quickstart](https://supabase.com/docs/guides/ai/langchain?database-method=sql), this will be `match_documents`.\n\n### metadata filter\n\navailable in **get many** mode. when searching for data, use this to match with metadata associated with the document.\n\nthis is an `and` query. if you specify more than one metadata filter field, all of them must match.\n\nwhen inserting data, the metadata is set using the document loader. refer to [default data loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information on loading documents.\n\n## templates and examples\n\n**ai agent to chat with files in supabase storage**\n\nby mark shcherbakov\n\n[view template details](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/)\n\n**automate sales cold calling pipeline with apify, gpt-4o, and whatsapp**\n\nby khairul muhtadin\n\n[view template details](https://n8n.io/workflows/5449-automate-sales-cold-calling-pipeline-with-apify-gpt-4o-and-whatsapp/)\n\n**🤖 create a documentation expert bot with rag, gemini, and supabase**\n\nby lucas peyrin\n\n[view template details](https://n8n.io/workflows/5993-create-a-documentation-expert-bot-with-rag-gemini-and-supabase/)\n\n[browse supabase vector store integration templates](https://n8n.io/integrations/supabase-vector-store/), or [search all templates](https://n8n.io/workflows/)\n\n## related resources\n\nrefer to [langchain's supabase documentation](https://js.langchain.com/docs/integrations/vectorstores/supabase/) for more information about the service.\n\nview n8n's [advanced ai](../../../../../advanced-ai/) documentation.\n supabase vector store node",
         "importantTerms": [
-          "weaviate",
           "vector",
-          "documents",
           "store",
+          "supabase",
+          "documents",
           "node",
-          "retrieve",
-          "tool",
-          "agent",
-          "https",
           "this",
+          "tool",
           "with",
+          "agent",
+          "retrieve",
           "name",
-          "collection",
           "nodes",
-          "docs",
-          "many",
-          "insert",
+          "database",
           "chain",
-          "more",
-          "checks",
-          "results",
-          "values",
-          "search",
+          "https",
+          "update",
+          "table",
+          "insert",
           "from",
-          "when",
-          "learn",
-          "property",
-          "hybrid",
-          "parameters",
-          "number",
-          "given",
-          "data",
-          "about",
-          "mode",
+          "retriever",
+          "results",
           "langchain",
+          "mode",
+          "many",
           "enter",
-          "query",
-          "retriever",
+          "parameters",
+          "when",
           "example",
+          "workflows",
           "answer",
-          "must",
-          "tenant",
-          "score",
-          "best",
-          "metadata",
-          "fusion",
-          "timeout",
+          "connector",
+          "question",
           "your",
+          "them",
           "glossary",
-          "connect"
+          "connect",
+          "more",
+          "expression",
+          "input",
+          "chat",
+          "directly",
+          "items",
+          "using",
+          "resolves",
+          "pattern",
+          "template",
+          "files",
+          "storage",
+          "match",
+          "uses"
         ]
       }
     },
     {
       "id": "page-0557",
-      "title": "Supabase Vector Store",
-      "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/index.md",
-      "urlPath": "integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/index.md",
+      "title": "Weaviate Vector Store",
+      "url": "https://docs.n8n.io/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreweaviate/index.md",
+      "urlPath": "integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreweaviate/index.md",
       "category": "cluster-nodes",
       "subcategory": null,
       "nodeName": null,
       "nodeType": null,
       "content": {
-        "markdown": "# Supabase Vector Store node\n\nUse the Supabase Vector Store to interact with your Supabase database as vector store. You can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.\n\nUse the Supabase Vector Store to interact with your Supabase database as [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into a vector database, get documents from a vector database, retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain), or connect it directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). You can also update an item in a vector store by its ID.\n\nOn this page, you'll find the node parameters for the Supabase node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/supabase/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\nSupabase provides a [quickstart for setting up your vector store](https://supabase.com/docs/guides/ai/langchain?database-method=sql). If you use settings other than the defaults in the quickstart, this may affect parameter settings in n8n. Make sure you understand what you're doing.\n\n## Node usage patterns\n\nYou can use the Supabase Vector Store node in the following patterns.\n\n### Use as a regular node to insert, update, and retrieve documents\n\nYou can use the Supabase Vector Store as a regular node to insert, update, or get documents. This pattern places the Supabase Vector Store in the regular connection flow without using an agent.\n\nYou can see an example of this in scenario 1 of [this template](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/).\n\n### Connect directly to an AI agent as a tool\n\nYou can connect the Supabase Vector Store node directly to the tool connector of an [AI agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nHere, the connection would be: AI agent (tools connector) -> Supabase Vector Store node.\n\n### Use a retriever to fetch documents\n\nYou can use the [Vector Store Retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the Supabase Vector Store node to fetch documents from the Supabase Vector Store node. This is often used with the [Question and Answer Chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\nAn [example of the connection flow](https://n8n.io/workflows/1960-ask-questions-about-a-pdf-using-ai/) (the example uses Pinecone, but the pattern in the same) would be: Question and Answer Chain (Retriever connector) -> Vector Store Retriever (Vector Store connector) -> Supabase Vector Store.\n\n### Use the Vector Store Question Answer Tool to answer questions\n\nAnother pattern uses the [Vector Store Question Answer Tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the Supabase Vector Store node. Rather than connecting the Supabase Vector Store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\nThe [connections flow](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/) in this case would look like this: AI agent (tools connector) -> Vector Store Question Answer Tool (Vector Store connector) -> Supabase Vector store.\n\n## Node parameters\n\n### Operation Mode\n\nThis Vector Store node has five modes: **Get Many**, **Insert Documents**, **Retrieve Documents (As Vector Store for Chain/Tool)**, **Retrieve Documents (As Tool for AI Agent)**, and **Update Documents**. The mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### Get Many\n\nIn this mode, you can retrieve multiple documents from your vector database by providing a prompt. The prompt will be embedded and used for similarity search. The node will return the documents that are most similar to the prompt with their similarity score. This is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### Insert Documents\n\nUse Insert Documents mode to insert new documents into your vector database.\n\n#### Retrieve Documents (As Vector Store for Chain/Tool)\n\nUse Retrieve Documents (As Vector Store for Chain/Tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. In this mode you must connect the node to a retriever node or root node.\n\n#### Retrieve Documents (As Tool for AI Agent)\n\nUse Retrieve Documents (As Tool for AI Agent) mode to use the vector store as a tool resource when answering queries. When formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n#### Update Documents\n\nUse Update Documents mode to update documents in a vector database by ID. Fill in the **ID** with the ID of the embedding entry to update.\n\n### Rerank Results\n\nEnables [reranking](../../../../../glossary/#ai-reranking). If you enable this option, you must connect a reranking node to the vector store. That node will then rerank the results for queries. You can use this option with the `Get Many`, `Retrieve Documents (As Vector Store for Chain/Tool)` and `Retrieve Documents (As Tool for AI Agent)` modes.\n\n### Get Many parameters\n\n- **Table Name**: Enter the Supabase table to use.\n- **Prompt**: Enter the search query.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Insert Documents parameters\n\n- **Table Name**: Enter the Supabase table to use.\n\n### Retrieve Documents (As Vector Store for Chain/Tool) parameters\n\n- **Table Name**: Enter the Supabase table to use.\n\n### Retrieve Documents (As Tool for AI Agent) parameters\n\n- **Name**: The name of the vector store.\n- **Description**: Explain to the LLM what this tool does. A good, specific description allows LLMs to produce expected results more often.\n- **Table Name**: Enter the Supabase table to use.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Update Documents\n\n- **Table Name**: Enter the Supabase table to use.\n- **ID**: The ID of an embedding entry.\n\nParameters for **Update Documents**\n\n- ID\n\n## Node options\n\n### Query Name\n\nThe name of the matching function you set up in Supabase. If you follow the [Supabase quickstart](https://supabase.com/docs/guides/ai/langchain?database-method=sql), this will be `match_documents`.\n\n### Metadata Filter\n\nAvailable in **Get Many** mode. When searching for data, use this to match with metadata associated with the document.\n\nThis is an `AND` query. If you specify more than one metadata filter field, all of them must match.\n\nWhen inserting data, the metadata is set using the document loader. Refer to [Default Data Loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information on loading documents.\n\n## Templates and examples\n\n**AI Agent To Chat With Files In Supabase Storage**\n\nby Mark Shcherbakov\n\n[View template details](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/)\n\n**Automate sales cold calling pipeline with Apify, GPT-4o, and WhatsApp**\n\nby Khairul Muhtadin\n\n[View template details](https://n8n.io/workflows/5449-automate-sales-cold-calling-pipeline-with-apify-gpt-4o-and-whatsapp/)\n\n**🤖 Create a Documentation Expert Bot with RAG, Gemini, and Supabase**\n\nby Lucas Peyrin\n\n[View template details](https://n8n.io/workflows/5993-create-a-documentation-expert-bot-with-rag-gemini-and-supabase/)\n\n[Browse Supabase Vector Store integration templates](https://n8n.io/integrations/supabase-vector-store/), or [search all templates](https://n8n.io/workflows/)\n\n## Related resources\n\nRefer to [LangChain's Supabase documentation](https://js.langchain.com/docs/integrations/vectorstores/supabase/) for more information about the service.\n\nView n8n's [Advanced AI](../../../../../advanced-ai/) documentation.\n",
-        "excerpt": "# Supabase Vector Store node  Use the Supabase Vector Store to interact with your Supabase database as vector store. You can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.  Use the Supabase Vector Store to interact with your Supabase database as [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into a vector database, get documents from a vector databa...",
+        "markdown": "# Weaviate Vector Store node\n\nUse the Weaviate node to interact with your Weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into or retrieve documents from a vector database. You can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). On this page, you'll find the node parameters for the Weaviate node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/weaviate/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for each item in turn. For example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nIn sub-nodes, the expression always resolves to the first item. For example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## Node usage patterns\n\nYou can use the Weaviate Vector Store node in the following patterns.\n\n### Use as a regular node to insert and retrieve documents\n\nYou can use the Weaviate Vector Store as a regular node to insert or get documents. This pattern places the Weaviate Vector Store in the regular connection flow without using an agent.\n\n### Connect directly to an AI agent as a tool\n\nYou can connect the Weaviate Vector Store node directly to the tool connector of an [AI agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nHere, the connection would be: AI agent (tools connector) -> Weaviate Vector Store node.\n\n### Use a retriever to fetch documents\n\nYou can use the [Vector Store Retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the Weaviate Vector Store node to fetch documents from the Weaviate Vector Store node. This is often used with the [Question and Answer Chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\n### Use the Vector Store Question Answer Tool to answer questions\n\nAnother pattern uses the [Vector Store Question Answer Tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the Weaviate Vector Store node. Rather than connecting the Weaviate Vector Store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\n## Node parameters\n\nMultitenancy\n\nYou can separate your data into isolated tenants for the same collection (for example, for different customers). For that, you must always provide a [Tenant Name](#tenant-name) both when inserting and retrieving objects. [Read more about multi tenancy in Weaviate docs](https://docs.weaviate.io/weaviate/manage-collections/multi-tenancy).\n\n### Operation Mode\n\nThis Vector Store node has four modes: **Get Many**, **Insert Documents**, **Retrieve Documents (As Vector Store for Chain/Tool)**, and **Retrieve Documents (As Tool for AI Agent)**. The mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### Get Many\n\nIn this mode, you can retrieve multiple documents from your vector database by providing a prompt. The prompt is embedded and used for similarity search. The node returns the documents that are most similar to the prompt with their similarity score. This is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### Insert Documents\n\nUse insert documents mode to insert new documents into your vector database.\n\n#### Retrieve Documents (as Vector Store for Chain/Tool)\n\nUse Retrieve Documents (As Vector Store for Chain/Tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. In this mode you must connect the node to a retriever node or root node.\n\n#### Retrieve Documents (as Tool for AI Agent)\n\nUse Retrieve Documents (As Tool for AI Agent) mode to use the vector store as a tool resource when answering queries. When formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n### Get Many parameters\n\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n- **Prompt**: Enter the search query.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Insert Documents parameters\n\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n- **Embedding Batch Size**: The number of documents to embed in a single batch. The default is 200 documents.\n\n### Retrieve Documents (As Vector Store for Chain/Tool) parameters\n\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n\n### Retrieve Documents (As Tool for AI Agent) parameters\n\n- **Weaviate Collection**: The name of the vector store.\n- **Description**: Explain to the LLM what this tool does. A good, specific description allows LLMs to produce expected results more often.\n- **Weaviate Collection**: Enter the name of the Weaviate collection to use.\n- **Limit**: Enter how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.\n\n### Include Metadata\n\nWhether to include document metadata.\n\nYou can use this with the [Get Many](#get-many) and [Retrieve Documents (As Tool for AI Agent)](#retrieve-documents-as-tool-for-ai-agent-parameters) modes.\n\n### Rerank Results\n\nEnables [reranking](../../../../../glossary/#ai-reranking). If you enable this option, you must connect a reranking node to the vector store. That node will then rerank the results for queries. You can use this option with the `Get Many`, `Retrieve Documents (As Vector Store for Chain/Tool)` and `Retrieve Documents (As Tool for AI Agent)` modes.\n\n## Node options\n\n### Search Filters\n\nAvailable for the [Get Many](#get-many), [Retrieve Documents (As Vector Store for Chain/Tool)](#retrieve-documents-as-vector-store-for-chaintool), and [Retrieve Documents (As Tool for AI Agent)](#retrieve-documents-as-tool-for-ai-agent) operation modes.\n\nWhen searching for data, use this to match metadata associated with documents. You can learn more about the operators and query structure in [Weaviate's conditional filters documentation](https://docs.weaviate.io/weaviate/api/graphql/filters).\n\nYou can use both `AND` and `OR` with different operators. Operators are case insensitive:\n\n```\n{\n  \"OR\": [\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"Equal\",\n        \"valueString\": \"source1\"\n    },\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"Equal\",\n        \"valueString\": \"source1\"\n    }\n  ]\n}\n```\n\nSupported operators:\n\n| Operator           | Required Field(s)                                    | Description                                                                                                                                                                       |\n| ------------------ | ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `'equal'`          | `valueString` or `valueNumber`                       | Checks if the property is equal to the given string or number.                                                                                                                    |\n| `'like'`           | `valueString`                                        | Checks if the string property matches a pattern (for example, sub-string match).                                                                                                  |\n| `'containsAny'`    | `valueTextArray` (string[])                          | Checks if the property contains **any** of the given values.                                                                                                                      |\n| `'containsAll'`    | `valueTextArray` (string[])                          | Checks if the property contains **all** of the given values.                                                                                                                      |\n| `'greaterThan'`    | `valueNumber`                                        | Checks if the property value is greater than the given number.                                                                                                                    |\n| `'lessThan'`       | `valueNumber`                                        | Checks if the property value is less than the given number.                                                                                                                       |\n| `'isNull'`         | `valueBoolean` (true/false)                          | Checks if the property is null or not. ([must enable before ingestion](https://docs.weaviate.io/weaviate/manage-collections/collection-operations#set-inverted-index-parameters)) |\n| `'withinGeoRange'` | `valueGeoCoordinates` (object with geolocation data) | Filters by proximity to geographic coordinates.                                                                                                                                   |\n\nWhen inserting data, the document loader sets the metadata. Refer to [Default Data Loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information on loading documents.\n\n### Metadata Keys\n\nYou can define which metadata keys you want Weaviate to return on your queries. This can reduce network load, as you will only get properties you have defined. Returns all properties from the server by default.\n\nAvailable for the [Get Many](#get-many), [Retrieve Documents (As Vector Store for Chain/Tool)](#retrieve-documents-as-vector-store-for-chaintool), and [Retrieve Documents (As Tool for AI Agent)](#retrieve-documents-as-tool-for-ai-agent) operation modes.\n\n### Hybrid: Query Text\n\nProvide a query text to combine vector search with a keyword/text search.\n\n### Hybrid: Explain Score\n\nWhether to show the score fused between hybrid and vector search explanation.\n\n### Hybrid: Fusion Type\n\nSelect the fusion type for combining vector and keyword search results. [Learn more about fusion algorithms](https://weaviate.io/learn/knowledgecards/fusion-algorithm).\n\nOptions:\n\n- **Relative Score**: Uses relative score fusion\n- **Ranked**: Uses ranked fusion\n\n### Hybrid: Auto Cut Limit\n\nLimit result groups by detecting sudden jumps in score. [Learn more about autocut](https://docs.weaviate.io/weaviate/api/graphql/additional-operators#autocut).\n\n### Hybrid: Alpha\n\nChange the relative weights of the keyword and vector components. 1.0 = pure vector, 0.0 = pure keyword. Default is 0.5. [Learn more about the alpha parameter](https://weaviate.io/learn/knowledgecards/alpha-parameter).\n\n### Hybrid: Query Properties\n\nComma-separated list of properties to include in the query with optionally weighted values, e.g., \"question^2,answer\". [Learn more about setting weights on property values](https://docs.weaviate.io/weaviate/search/hybrid#set-weights-on-property-values).\n\n### Hybrid: Max Vector Distance\n\nSet the maximum allowable distance for the vector search component.\n\n### Tenant Name\n\nThe specific tenant to store or retrieve documents for. [Learn more about multi-tenancy](https://weaviate.io/learn/knowledgecards/multi-tenancy).\n\nMust enable at creation\n\nYou must pass a tenant name at first ingestion to enable multitenancy for a collection. You can't enable or disable multitenancy after creation.\n\n### Text Key\n\nThe key in the document that contains the embedded text.\n\n### Skip Init Checks\n\nWhether to [skip initialization checks](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#initial-connection-checks) when instantiating the client.\n\n### Init Timeout\n\nNumber of seconds to wait before [timing out](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#timeout-values) during initial checks.\n\n### Insert Timeout\n\nNumber of seconds to wait before [timing out](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#timeout-values) during inserts.\n\n### Query Timeout\n\nNumber of seconds to wait before [timing out](https://docs.weaviate.io/weaviate/client-libraries/typescript/notes-best-practices#timeout-values) during queries.\n\n### GRPC Proxy\n\nA proxy to use for gRPC requests.\n\n### Clear Data\n\nAvailable for the [Insert Documents](#insert-documents) operation mode.\n\nWhether to clear the collection or tenant before inserting new data.\n\n## Templates and examples\n\n**Build a Weekly AI Trend Alerter with arXiv and Weaviate**\n\nby Mary Newhauser\n\n[View template details](https://n8n.io/workflows/5817-build-a-weekly-ai-trend-alerter-with-arxiv-and-weaviate/)\n\n**Build person OSINT profiles using Humantic AI, Hunter, CourtListener and GPT-5**\n\nby Open Paws\n\n[View template details](https://n8n.io/workflows/12507-build-person-osint-profiles-using-humantic-ai-hunter-courtlistener-and-gpt-5/)\n\n**Research organizations with GPT‑5, Gemini, CourtListener, LegiScan and OSINT web sources**\n\nby Open Paws\n\n[View template details](https://n8n.io/workflows/12506-research-organizations-with-gpt5-gemini-courtlistener-legiscan-and-osint-web-sources/)\n\n[Browse Weaviate Vector Store integration templates](https://n8n.io/integrations/weaviate-vector-store/), or [search all templates](https://n8n.io/workflows/)\n\n## Related resources\n\nRefer to [LangChain's Weaviate documentation](https://js.langchain.com/docs/integrations/vectorstores/weaviate/) for more information about the service.\n\nRefer to [Weaviate Installation](https://docs.weaviate.io/deploy) for a self hosted Weaviate Cluster.\n\nView n8n's [Advanced AI](../../../../../advanced-ai/) documentation.\n",
+        "excerpt": "# Weaviate Vector Store node  Use the Weaviate node to interact with your Weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into or retrieve documents from a vector database. You can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). On this page,...",
         "sections": [
           {
-            "title": "Supabase Vector Store node",
+            "title": "Weaviate Vector Store node",
             "level": 1,
-            "content": "Use the Supabase Vector Store to interact with your Supabase database as vector store. You can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.\n\nUse the Supabase Vector Store to interact with your Supabase database as [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into a vector database, get documents from a vector database, retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain), or connect it directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). You can also update an item in a vector store by its ID.\n\nOn this page, you'll find the node parameters for the Supabase node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/supabase/).\n\nParameter resolution in su"
+            "content": "Use the Weaviate node to interact with your Weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). You can insert documents into or retrieve documents from a vector database. You can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). On this page, you'll find the node parameters for the Weaviate node, and links to more resources.\n\nCredentials\n\nYou can find authentication information for this node [here](../../../credentials/weaviate/).\n\nParameter resolution in sub-nodes\n\nSub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nMost nodes, including root nodes, take any number of items as input, process these items, and output the results. You can use expressions to refer to input items, and the node resolves the expression for "
           }
         ]
       },
       "metadata": {
         "keywords": [
-          "supabase",
+          "weaviate",
           "vector",
           "store",
           "node",
           "usage",
           "patterns",
           "regular",
-          "insert,",
-          "update,",
+          "insert",
           "retrieve",
           "documents",
           "connect",
@@ -43811,17 +43790,38 @@
           "operation",
           "mode",
           "many",
-          "insert",
           "chain/tool)",
           "agent)",
-          "update",
+          "include",
+          "metadata",
           "rerank",
           "results",
           "options",
+          "search",
+          "filters",
+          "keys",
+          "hybrid:",
           "query",
+          "text",
+          "explain",
+          "score",
+          "fusion",
+          "type",
+          "auto",
+          "limit",
+          "alpha",
+          "properties",
+          "distance",
+          "tenant",
           "name",
-          "metadata",
-          "filter",
+          "skip",
+          "init",
+          "checks",
+          "timeout",
+          "grpc",
+          "proxy",
+          "clear",
+          "data",
           "templates",
           "examples",
           "related",
@@ -43831,65 +43831,65 @@
         "operations": [
           "mode"
         ],
-        "codeExamples": 0,
+        "codeExamples": 1,
         "complexity": "intermediate",
-        "readingTime": "7 min",
-        "contentLength": 8921,
+        "readingTime": "9 min",
+        "contentLength": 14378,
         "relatedPages": []
       },
       "searchIndex": {
-        "fullText": "supabase vector store # supabase vector store node\n\nuse the supabase vector store to interact with your supabase database as vector store. you can insert documents into a vector database, get many documents from a vector database, and retrieve documents to provide them to a retriever connected to a chain.\n\nuse the supabase vector store to interact with your supabase database as [vector store](../../../../../glossary/#ai-vector-store). you can insert documents into a vector database, get documents from a vector database, retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain), or connect it directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). you can also update an item in a vector store by its id.\n\non this page, you'll find the node parameters for the supabase node, and links to more resources.\n\ncredentials\n\nyou can find authentication information for this node [here](../../../credentials/supabase/).\n\nparameter resolution in sub-nodes\n\nsub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nmost nodes, including root nodes, take any number of items as input, process these items, and output the results. you can use expressions to refer to input items, and the node resolves the expression for each item in turn. for example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nin sub-nodes, the expression always resolves to the first item. for example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\nsupabase provides a [quickstart for setting up your vector store](https://supabase.com/docs/guides/ai/langchain?database-method=sql). if you use settings other than the defaults in the quickstart, this may affect parameter settings in n8n. make sure you understand what you're doing.\n\n## node usage patterns\n\nyou can use the supabase vector store node in the following patterns.\n\n### use as a regular node to insert, update, and retrieve documents\n\nyou can use the supabase vector store as a regular node to insert, update, or get documents. this pattern places the supabase vector store in the regular connection flow without using an agent.\n\nyou can see an example of this in scenario 1 of [this template](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/).\n\n### connect directly to an ai agent as a tool\n\nyou can connect the supabase vector store node directly to the tool connector of an [ai agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nhere, the connection would be: ai agent (tools connector) -> supabase vector store node.\n\n### use a retriever to fetch documents\n\nyou can use the [vector store retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the supabase vector store node to fetch documents from the supabase vector store node. this is often used with the [question and answer chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\nan [example of the connection flow](https://n8n.io/workflows/1960-ask-questions-about-a-pdf-using-ai/) (the example uses pinecone, but the pattern in the same) would be: question and answer chain (retriever connector) -> vector store retriever (vector store connector) -> supabase vector store.\n\n### use the vector store question answer tool to answer questions\n\nanother pattern uses the [vector store question answer tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the supabase vector store node. rather than connecting the supabase vector store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\nthe [connections flow](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/) in this case would look like this: ai agent (tools connector) -> vector store question answer tool (vector store connector) -> supabase vector store.\n\n## node parameters\n\n### operation mode\n\nthis vector store node has five modes: **get many**, **insert documents**, **retrieve documents (as vector store for chain/tool)**, **retrieve documents (as tool for ai agent)**, and **update documents**. the mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### get many\n\nin this mode, you can retrieve multiple documents from your vector database by providing a prompt. the prompt will be embedded and used for similarity search. the node will return the documents that are most similar to the prompt with their similarity score. this is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### insert documents\n\nuse insert documents mode to insert new documents into your vector database.\n\n#### retrieve documents (as vector store for chain/tool)\n\nuse retrieve documents (as vector store for chain/tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. in this mode you must connect the node to a retriever node or root node.\n\n#### retrieve documents (as tool for ai agent)\n\nuse retrieve documents (as tool for ai agent) mode to use the vector store as a tool resource when answering queries. when formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n#### update documents\n\nuse update documents mode to update documents in a vector database by id. fill in the **id** with the id of the embedding entry to update.\n\n### rerank results\n\nenables [reranking](../../../../../glossary/#ai-reranking). if you enable this option, you must connect a reranking node to the vector store. that node will then rerank the results for queries. you can use this option with the `get many`, `retrieve documents (as vector store for chain/tool)` and `retrieve documents (as tool for ai agent)` modes.\n\n### get many parameters\n\n- **table name**: enter the supabase table to use.\n- **prompt**: enter the search query.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### insert documents parameters\n\n- **table name**: enter the supabase table to use.\n\n### retrieve documents (as vector store for chain/tool) parameters\n\n- **table name**: enter the supabase table to use.\n\n### retrieve documents (as tool for ai agent) parameters\n\n- **name**: the name of the vector store.\n- **description**: explain to the llm what this tool does. a good, specific description allows llms to produce expected results more often.\n- **table name**: enter the supabase table to use.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### update documents\n\n- **table name**: enter the supabase table to use.\n- **id**: the id of an embedding entry.\n\nparameters for **update documents**\n\n- id\n\n## node options\n\n### query name\n\nthe name of the matching function you set up in supabase. if you follow the [supabase quickstart](https://supabase.com/docs/guides/ai/langchain?database-method=sql), this will be `match_documents`.\n\n### metadata filter\n\navailable in **get many** mode. when searching for data, use this to match with metadata associated with the document.\n\nthis is an `and` query. if you specify more than one metadata filter field, all of them must match.\n\nwhen inserting data, the metadata is set using the document loader. refer to [default data loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information on loading documents.\n\n## templates and examples\n\n**ai agent to chat with files in supabase storage**\n\nby mark shcherbakov\n\n[view template details](https://n8n.io/workflows/2621-ai-agent-to-chat-with-files-in-supabase-storage/)\n\n**automate sales cold calling pipeline with apify, gpt-4o, and whatsapp**\n\nby khairul muhtadin\n\n[view template details](https://n8n.io/workflows/5449-automate-sales-cold-calling-pipeline-with-apify-gpt-4o-and-whatsapp/)\n\n**🤖 create a documentation expert bot with rag, gemini, and supabase**\n\nby lucas peyrin\n\n[view template details](https://n8n.io/workflows/5993-create-a-documentation-expert-bot-with-rag-gemini-and-supabase/)\n\n[browse supabase vector store integration templates](https://n8n.io/integrations/supabase-vector-store/), or [search all templates](https://n8n.io/workflows/)\n\n## related resources\n\nrefer to [langchain's supabase documentation](https://js.langchain.com/docs/integrations/vectorstores/supabase/) for more information about the service.\n\nview n8n's [advanced ai](../../../../../advanced-ai/) documentation.\n supabase vector store node",
+        "fullText": "weaviate vector store # weaviate vector store node\n\nuse the weaviate node to interact with your weaviate collection as a [vector store](../../../../../glossary/#ai-vector-store). you can insert documents into or retrieve documents from a vector database. you can also retrieve documents to provide them to a retriever connected to a [chain](../../../../../glossary/#ai-chain) or connect this node directly to an [agent](../../../../../glossary/#ai-agent) to use as a [tool](../../../../../glossary/#ai-tool). on this page, you'll find the node parameters for the weaviate node, and links to more resources.\n\ncredentials\n\nyou can find authentication information for this node [here](../../../credentials/weaviate/).\n\nparameter resolution in sub-nodes\n\nsub-nodes behave differently to other nodes when processing multiple items using an expression.\n\nmost nodes, including root nodes, take any number of items as input, process these items, and output the results. you can use expressions to refer to input items, and the node resolves the expression for each item in turn. for example, given an input of five `name` values, the expression `{{ $json.name }}` resolves to each name in turn.\n\nin sub-nodes, the expression always resolves to the first item. for example, given an input of five `name` values, the expression `{{ $json.name }}` always resolves to the first name.\n\n## node usage patterns\n\nyou can use the weaviate vector store node in the following patterns.\n\n### use as a regular node to insert and retrieve documents\n\nyou can use the weaviate vector store as a regular node to insert or get documents. this pattern places the weaviate vector store in the regular connection flow without using an agent.\n\n### connect directly to an ai agent as a tool\n\nyou can connect the weaviate vector store node directly to the tool connector of an [ai agent](../n8n-nodes-langchain.agent/) to use a vector store as a resource when answering queries.\n\nhere, the connection would be: ai agent (tools connector) -> weaviate vector store node.\n\n### use a retriever to fetch documents\n\nyou can use the [vector store retriever](../../sub-nodes/n8n-nodes-langchain.retrievervectorstore/) node with the weaviate vector store node to fetch documents from the weaviate vector store node. this is often used with the [question and answer chain](../n8n-nodes-langchain.chainretrievalqa/) node to fetch documents from the vector store that match the given chat input.\n\n### use the vector store question answer tool to answer questions\n\nanother pattern uses the [vector store question answer tool](../../sub-nodes/n8n-nodes-langchain.toolvectorstore/) to summarize results and answer questions from the weaviate vector store node. rather than connecting the weaviate vector store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.\n\n## node parameters\n\nmultitenancy\n\nyou can separate your data into isolated tenants for the same collection (for example, for different customers). for that, you must always provide a [tenant name](#tenant-name) both when inserting and retrieving objects. [read more about multi tenancy in weaviate docs](https://docs.weaviate.io/weaviate/manage-collections/multi-tenancy).\n\n### operation mode\n\nthis vector store node has four modes: **get many**, **insert documents**, **retrieve documents (as vector store for chain/tool)**, and **retrieve documents (as tool for ai agent)**. the mode you select determines the operations you can perform with the node and what inputs and outputs are available.\n\n#### get many\n\nin this mode, you can retrieve multiple documents from your vector database by providing a prompt. the prompt is embedded and used for similarity search. the node returns the documents that are most similar to the prompt with their similarity score. this is useful if you want to retrieve a list of similar documents and pass them to an agent as additional context.\n\n#### insert documents\n\nuse insert documents mode to insert new documents into your vector database.\n\n#### retrieve documents (as vector store for chain/tool)\n\nuse retrieve documents (as vector store for chain/tool) mode with a vector-store retriever to retrieve documents from a vector database and provide them to the retriever connected to a chain. in this mode you must connect the node to a retriever node or root node.\n\n#### retrieve documents (as tool for ai agent)\n\nuse retrieve documents (as tool for ai agent) mode to use the vector store as a tool resource when answering queries. when formulating responses, the agent uses the vector store when the vector store name and description match the question details.\n\n### get many parameters\n\n- **weaviate collection**: enter the name of the weaviate collection to use.\n- **prompt**: enter the search query.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### insert documents parameters\n\n- **weaviate collection**: enter the name of the weaviate collection to use.\n- **embedding batch size**: the number of documents to embed in a single batch. the default is 200 documents.\n\n### retrieve documents (as vector store for chain/tool) parameters\n\n- **weaviate collection**: enter the name of the weaviate collection to use.\n\n### retrieve documents (as tool for ai agent) parameters\n\n- **weaviate collection**: the name of the vector store.\n- **description**: explain to the llm what this tool does. a good, specific description allows llms to produce expected results more often.\n- **weaviate collection**: enter the name of the weaviate collection to use.\n- **limit**: enter how many results to retrieve from the vector store. for example, set this to `10` to get the ten best results.\n\n### include metadata\n\nwhether to include document metadata.\n\nyou can use this with the [get many](#get-many) and [retrieve documents (as tool for ai agent)](#retrieve-documents-as-tool-for-ai-agent-parameters) modes.\n\n### rerank results\n\nenables [reranking](../../../../../glossary/#ai-reranking). if you enable this option, you must connect a reranking node to the vector store. that node will then rerank the results for queries. you can use this option with the `get many`, `retrieve documents (as vector store for chain/tool)` and `retrieve documents (as tool for ai agent)` modes.\n\n## node options\n\n### search filters\n\navailable for the [get many](#get-many), [retrieve documents (as vector store for chain/tool)](#retrieve-documents-as-vector-store-for-chaintool), and [retrieve documents (as tool for ai agent)](#retrieve-documents-as-tool-for-ai-agent) operation modes.\n\nwhen searching for data, use this to match metadata associated with documents. you can learn more about the operators and query structure in [weaviate's conditional filters documentation](https://docs.weaviate.io/weaviate/api/graphql/filters).\n\nyou can use both `and` and `or` with different operators. operators are case insensitive:\n\n```\n{\n  \"or\": [\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"equal\",\n        \"valuestring\": \"source1\"\n    },\n    {\n        \"path\": [\"source\"],\n        \"operator\": \"equal\",\n        \"valuestring\": \"source1\"\n    }\n  ]\n}\n```\n\nsupported operators:\n\n| operator           | required field(s)                                    | description                                                                                                                                                                       |\n| ------------------ | ---------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |\n| `'equal'`          | `valuestring` or `valuenumber`                       | checks if the property is equal to the given string or number.                                                                                                                    |\n| `'like'`           | `valuestring`                                        | checks if the string property matches a pattern (for example, sub-string match).                                                                                                  |\n| `'containsany'`    | `valuetextarray` (string[])                          | checks if the property contains **any** of the given values.                                                                                                                      |\n| `'containsall'`    | `valuetextarray` (string[])                          | checks if the property contains **all** of the given values.                                                                                                                      |\n| `'greaterthan'`    | `valuenumber`                                        | checks if the property value is greater than the given number.                                                                                                                    |\n| `'lessthan'`       | `valuenumber`                                        | checks if the property value is less than the given number.                                                                                                                       |\n| `'isnull'`         | `valueboolean` (true/false)                          | checks if the property is null or not. ([must enable before ingestion](https://docs.weaviate.io/weaviate/manage-collections/collection-operations#set-inverted-index-parameters)) |\n| `'withingeorange'` | `valuegeocoordinates` (object with geolocation data) | filters by proximity to geographic coordinates.                                                                                                                                   |\n\nwhen inserting data, the document loader sets the metadata. refer to [default data loader](../../sub-nodes/n8n-nodes-langchain.documentdefaultdataloader/) for more information ",
         "importantTerms": [
+          "weaviate",
           "vector",
-          "store",
-          "supabase",
           "documents",
+          "store",
           "node",
-          "this",
+          "retrieve",
           "tool",
-          "with",
           "agent",
-          "retrieve",
+          "https",
+          "this",
+          "with",
           "name",
+          "collection",
           "nodes",
-          "database",
-          "chain",
-          "https",
-          "update",
-          "table",
+          "docs",
+          "many",
           "insert",
-          "from",
-          "retriever",
+          "chain",
+          "more",
+          "checks",
           "results",
-          "langchain",
+          "values",
+          "search",
+          "from",
+          "when",
+          "learn",
+          "property",
+          "hybrid",
+          "parameters",
+          "number",
+          "given",
+          "data",
+          "about",
           "mode",
-          "many",
+          "langchain",
           "enter",
-          "parameters",
-          "when",
+          "query",
+          "retriever",
           "example",
-          "workflows",
           "answer",
-          "connector",
-          "question",
+          "must",
+          "tenant",
+          "score",
+          "best",
+          "metadata",
+          "fusion",
+          "timeout",
           "your",
-          "them",
           "glossary",
-          "connect",
-          "more",
-          "expression",
-          "input",
-          "chat",
-          "directly",
-          "items",
-          "using",
-          "resolves",
-          "pattern",
-          "template",
-          "files",
-          "storage",
-          "match",
-          "uses"
+          "connect"
         ]
       }
     },
@@ -60254,6 +60254,56 @@
     },
     {
       "id": "page-0763",
+      "title": "Clockify credentials",
+      "url": "https://docs.n8n.io/integrations/builtin/credentials/clockify/index.md",
+      "urlPath": "integrations/builtin/credentials/clockify/index.md",
+      "category": "other",
+      "subcategory": null,
+      "nodeName": null,
+      "nodeType": null,
+      "content": {
+        "markdown": "# Clockify credentials\n\nYou can use these credentials to authenticate the following nodes:\n\n- [Clockify](../../app-nodes/n8n-nodes-base.clockify/)\n- [Clockify Trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)\n\n## Prerequisites\n\nCreate a [Clockify](https://www.clockify.com/) account.\n\n## Supported authentication methods\n\n- API key\n\n## Related resources\n\nRefer to [Clockify's API documentation](https://docs.developer.clockify.me/) for more information about the service.\n\n## Using API key\n\nTo configure this credential, you'll need:\n\n- An **API Key**: Access your API key from your [Clockify Profile Settings](https://clockify.me/help/users/profile-settings).\n",
+        "excerpt": "# Clockify credentials  You can use these credentials to authenticate the following nodes:  - [Clockify](../../app-nodes/n8n-nodes-base.clockify/) - [Clockify Trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)  ## Prerequisites  Create a [Clockify](https://www.clockify.com/) account.  ## Supported authentication methods  - API key  ## Related resources  Refer to [Clockify's API documentation](https://docs.developer.clockify.me/) for more information about the service.  ## Using API ke...",
+        "sections": [
+          {
+            "title": "Clockify credentials",
+            "level": 1,
+            "content": "You can use these credentials to authenticate the following nodes:\n\n- [Clockify](../../app-nodes/n8n-nodes-base.clockify/)\n- [Clockify Trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)"
+          }
+        ]
+      },
+      "metadata": {
+        "keywords": [
+          "clockify",
+          "credentials",
+          "prerequisites",
+          "supported",
+          "authentication",
+          "methods",
+          "related",
+          "resources",
+          "using"
+        ],
+        "useCases": [],
+        "operations": [],
+        "codeExamples": 0,
+        "complexity": "beginner",
+        "readingTime": "1 min",
+        "contentLength": 673,
+        "relatedPages": []
+      },
+      "searchIndex": {
+        "fullText": "clockify credentials # clockify credentials\n\nyou can use these credentials to authenticate the following nodes:\n\n- [clockify](../../app-nodes/n8n-nodes-base.clockify/)\n- [clockify trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)\n\n## prerequisites\n\ncreate a [clockify](https://www.clockify.com/) account.\n\n## supported authentication methods\n\n- api key\n\n## related resources\n\nrefer to [clockify's api documentation](https://docs.developer.clockify.me/) for more information about the service.\n\n## using api key\n\nto configure this credential, you'll need:\n\n- an **api key**: access your api key from your [clockify profile settings](https://clockify.me/help/users/profile-settings).\n clockify credentials",
+        "importantTerms": [
+          "clockify",
+          "nodes",
+          "credentials",
+          "https"
+        ]
+      }
+    },
+    {
+      "id": "page-0764",
       "title": "Cloudflare credentials",
       "url": "https://docs.n8n.io/integrations/builtin/credentials/cloudflare/index.md",
       "urlPath": "integrations/builtin/credentials/cloudflare/index.md",
@@ -60308,7 +60358,7 @@
       }
     },
     {
-      "id": "page-0764",
+      "id": "page-0765",
       "title": "Cockpit credentials",
       "url": "https://docs.n8n.io/integrations/builtin/credentials/cockpit/index.md",
       "urlPath": "integrations/builtin/credentials/cockpit/index.md",
@@ -60365,7 +60415,7 @@
       }
     },
     {
-      "id": "page-0765",
+      "id": "page-0766",
       "title": "Coda credentials",
       "url": "https://docs.n8n.io/integrations/builtin/credentials/coda/index.md",
       "urlPath": "integrations/builtin/credentials/coda/index.md",
@@ -60419,7 +60469,7 @@
       }
     },
     {
-      "id": "page-0766",
+      "id": "page-0767",
       "title": "Cohere credentials",
       "url": "https://docs.n8n.io/integrations/builtin/credentials/cohere/index.md",
       "urlPath": "integrations/builtin/credentials/cohere/index.md",
@@ -60472,56 +60522,6 @@
         ]
       }
     },
-    {
-      "id": "page-0767",
-      "title": "Clockify credentials",
-      "url": "https://docs.n8n.io/integrations/builtin/credentials/clockify/index.md",
-      "urlPath": "integrations/builtin/credentials/clockify/index.md",
-      "category": "other",
-      "subcategory": null,
-      "nodeName": null,
-      "nodeType": null,
-      "content": {
-        "markdown": "# Clockify credentials\n\nYou can use these credentials to authenticate the following nodes:\n\n- [Clockify](../../app-nodes/n8n-nodes-base.clockify/)\n- [Clockify Trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)\n\n## Prerequisites\n\nCreate a [Clockify](https://www.clockify.com/) account.\n\n## Supported authentication methods\n\n- API key\n\n## Related resources\n\nRefer to [Clockify's API documentation](https://docs.developer.clockify.me/) for more information about the service.\n\n## Using API key\n\nTo configure this credential, you'll need:\n\n- An **API Key**: Access your API key from your [Clockify Profile Settings](https://clockify.me/help/users/profile-settings).\n",
-        "excerpt": "# Clockify credentials  You can use these credentials to authenticate the following nodes:  - [Clockify](../../app-nodes/n8n-nodes-base.clockify/) - [Clockify Trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)  ## Prerequisites  Create a [Clockify](https://www.clockify.com/) account.  ## Supported authentication methods  - API key  ## Related resources  Refer to [Clockify's API documentation](https://docs.developer.clockify.me/) for more information about the service.  ## Using API ke...",
-        "sections": [
-          {
-            "title": "Clockify credentials",
-            "level": 1,
-            "content": "You can use these credentials to authenticate the following nodes:\n\n- [Clockify](../../app-nodes/n8n-nodes-base.clockify/)\n- [Clockify Trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)"
-          }
-        ]
-      },
-      "metadata": {
-        "keywords": [
-          "clockify",
-          "credentials",
-          "prerequisites",
-          "supported",
-          "authentication",
-          "methods",
-          "related",
-          "resources",
-          "using"
-        ],
-        "useCases": [],
-        "operations": [],
-        "codeExamples": 0,
-        "complexity": "beginner",
-        "readingTime": "1 min",
-        "contentLength": 673,
-        "relatedPages": []
-      },
-      "searchIndex": {
-        "fullText": "clockify credentials # clockify credentials\n\nyou can use these credentials to authenticate the following nodes:\n\n- [clockify](../../app-nodes/n8n-nodes-base.clockify/)\n- [clockify trigger](../../trigger-nodes/n8n-nodes-base.clockifytrigger/)\n\n## prerequisites\n\ncreate a [clockify](https://www.clockify.com/) account.\n\n## supported authentication methods\n\n- api key\n\n## related resources\n\nrefer to [clockify's api documentation](https://docs.developer.clockify.me/) for more information about the service.\n\n## using api key\n\nto configure this credential, you'll need:\n\n- an **api key**: access your api key from your [clockify profile settings](https://clockify.me/help/users/profile-settings).\n clockify credentials",
-        "importantTerms": [
-          "clockify",
-          "nodes",
-          "credentials",
-          "https"
-        ]
-      }
-    },
     {
       "id": "page-0768",
       "title": "Contentful credentials",
@@ -93773,7 +93773,7 @@
         "page-0420",
         "page-0457",
         "page-0549",
-        "page-0556",
+        "page-0557",
         "page-0565",
         "page-0571",
         "page-0626",
@@ -94301,8 +94301,8 @@
         "page-0744",
         "page-0752",
         "page-0762",
-        "page-0764",
         "page-0765",
+        "page-0766",
         "page-0768",
         "page-0777",
         "page-0786",
@@ -97149,7 +97149,7 @@
         "page-0529",
         "page-0537",
         "page-0546",
-        "page-0556",
+        "page-0557",
         "page-0615",
         "page-0616",
         "page-0646",
@@ -97537,7 +97537,7 @@
         "page-0534",
         "page-0547",
         "page-0553",
-        "page-0557",
+        "page-0556",
         "page-0668",
         "page-0674",
         "page-0704",
@@ -100445,9 +100445,9 @@
         "page-0752",
         "page-0756",
         "page-0762",
-        "page-0763",
         "page-0764",
         "page-0765",
+        "page-0766",
         "page-0768",
         "page-0769",
         "page-0777",
@@ -101932,7 +101932,7 @@
         "page-0037",
         "page-0505",
         "page-0547",
-        "page-0556",
+        "page-0557",
         "page-0668",
         "page-0702",
         "page-0736",
@@ -104388,7 +104388,7 @@
         "page-0553",
         "page-0554",
         "page-0555",
-        "page-0557",
+        "page-0556",
         "page-0558",
         "page-0659",
         "page-1168",
@@ -105608,7 +105608,7 @@
       "include": [
         "page-0142",
         "page-0555",
-        "page-0556",
+        "page-0557",
         "page-0565",
         "page-0683",
         "page-0686",
@@ -105668,7 +105668,7 @@
         "page-0512",
         "page-0550",
         "page-0553",
-        "page-0556",
+        "page-0557",
         "page-0710"
       ],
       "info": [
@@ -105860,7 +105860,7 @@
         "page-0457",
         "page-0492",
         "page-0528",
-        "page-0556",
+        "page-0557",
         "page-0659",
         "page-0666",
         "page-0682",
@@ -106062,7 +106062,7 @@
       ],
       "timeout": [
         "page-0160",
-        "page-0556",
+        "page-0557",
         "page-0588",
         "page-0594",
         "page-0595",
@@ -106296,7 +106296,7 @@
       "proxy": [
         "page-0167",
         "page-0224",
-        "page-0556",
+        "page-0557",
         "page-0585",
         "page-0586",
         "page-0589",
@@ -107319,7 +107319,7 @@
       ],
       "checks": [
         "page-0206",
-        "page-0556"
+        "page-0557"
       ],
       "obtain": [
         "page-0208"
@@ -107946,7 +107946,7 @@
       ],
       "limit": [
         "page-0232",
-        "page-0556",
+        "page-0557",
         "page-0565",
         "page-0626",
         "page-0669",
@@ -108345,21 +108345,21 @@
       ],
       "clockify": [
         "page-0275",
-        "page-0767",
+        "page-0763",
         "page-1054"
       ],
       "cloudflare": [
         "page-0276",
-        "page-0763",
+        "page-0764",
         "page-1203"
       ],
       "cockpit": [
         "page-0277",
-        "page-0764"
+        "page-0765"
       ],
       "coda": [
         "page-0278",
-        "page-0765"
+        "page-0766"
       ],
       "coingecko": [
         "page-0279"
@@ -108794,7 +108794,7 @@
       ],
       "auto": [
         "page-0373",
-        "page-0556",
+        "page-0557",
         "page-0558",
         "page-0608",
         "page-1215"
@@ -109429,7 +109429,7 @@
         "page-0498",
         "page-0499",
         "page-0547",
-        "page-0556",
+        "page-0557",
         "page-0674",
         "page-1135"
       ],
@@ -109620,7 +109620,7 @@
       "supabase": [
         "page-0520",
         "page-0521",
-        "page-0557",
+        "page-0556",
         "page-0970"
       ],
       "accessible": [
@@ -110094,12 +110094,12 @@
       ],
       "insert,": [
         "page-0553",
-        "page-0557",
+        "page-0556",
         "page-0558"
       ],
       "update,": [
         "page-0553",
-        "page-0557",
+        "page-0556",
         "page-0558"
       ],
       "**update": [
@@ -110114,53 +110114,53 @@
         "page-1204"
       ],
       "weaviate": [
-        "page-0556",
+        "page-0557",
         "page-1002"
       ],
       "keys": [
-        "page-0556",
+        "page-0557",
         "page-0678",
         "page-1168",
         "page-1183",
         "page-1204"
       ],
       "hybrid:": [
-        "page-0556"
+        "page-0557"
       ],
       "explain": [
-        "page-0556"
+        "page-0557"
       ],
       "score": [
-        "page-0556"
+        "page-0557"
       ],
       "fusion": [
-        "page-0556"
+        "page-0557"
       ],
       "alpha": [
-        "page-0556",
+        "page-0557",
         "page-1204"
       ],
       "properties": [
-        "page-0556",
+        "page-0557",
         "page-1183",
         "page-1187"
       ],
       "distance": [
-        "page-0556"
+        "page-0557"
       ],
       "tenant": [
-        "page-0556"
+        "page-0557"
       ],
       "skip": [
-        "page-0556",
+        "page-0557",
         "page-0644"
       ],
       "init": [
-        "page-0556",
+        "page-0557",
         "page-1187"
       ],
       "grpc": [
-        "page-0556"
+        "page-0557"
       ],
       "dimensions": [
         "page-0558"
@@ -110271,7 +110271,7 @@
         "page-0587",
         "page-0597",
         "page-0610",
-        "page-0766"
+        "page-0767"
       ],
       "palm": [
         "page-0577"