Add docs for new PGVector Vector store node (#2442)

Co-authored-by: freakwriter <freakwriter@users.noreply.github.com>
This commit is contained in:
jeanpaul 2024-09-09 11:24:06 +02:00 committed by GitHub
parent 16186679df
commit 2de751d415
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 80 additions and 2 deletions

View File

@ -1,6 +1,6 @@
### Operation Mode
Vector Store nodes in n8n have three modes: **Get Many**, **Insert Documents** and **Retrieve Documents**. The mode you select determines the operations you can perform with the node and what inputs and outputs are available.
Vector Store nodes in n8n have three modes: **Get Many**, **Insert Documents**, and **Retrieve Documents**. The mode you select determines the operations you can perform with the node and what inputs and outputs are available.
<!-- vale off -->
#### Get Many
@ -9,7 +9,7 @@ In this mode, you can retrieve multiple documents from your vector database by p
<!-- vale on -->
#### Insert Documents
Use insert documents mode to insert new documents into your vector database.
Use Insert Documents mode to insert new documents into your vector database.
#### Retrieve Documents (For Agent/Chain)

View File

@ -56,6 +56,7 @@ Learn more about [Agents in LangChain](https://js.langchain.com/docs/modules/age
Vector stores store embedded data, and perform vector searches on it.
* [In Memory Vector Store](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreinmemory/)
* [PGVector Vector Store](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepgvector/)
* [Pinecone Vector Store](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone/)
* [Qdrant Vector Store](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreqdrant/)
* [Supabase Vector Store](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase/)

View File

@ -0,0 +1,74 @@
---
#https://www.notion.so/n8n/Frontmatter-432c2b8dff1f43d4b1c8d20075510fe4
title: PGVector Vector Store
description: Documentation for the PGVector node in n8n, a workflow automation platform. Includes details of operations and configuration, and links to examples and credentials information.
priority: medium
---
# PGVector Vector Store
PGVector is an extension of Postgresql. Use this node to interact with the PGVector tables in your Postgresql database. You can insert documents into a vector table, get documents from a vector table, and retrieve documents to provide them to a retriever connected to a chain.
On this page, you'll find the node parameters for the PGVector node, and links to more resources.
/// note | Credentials
You can find authentication information for this node [here](/integrations/builtin/credentials/postgres/).
///
--8<-- "_snippets/integrations/builtin/cluster-nodes/sub-node-expression-resolution.md"
## Node parameters
--8<-- "_snippets/integrations/builtin/cluster-nodes/vector-store-mode.md"
<!-- vale off -->
### Get Many parameters
<!-- vale on -->
* **Table name**: Enter the name of the table you want to query.
* **Prompt**: Enter your search query.
* **Limit**: Enter a number to set how many results to retrieve from the vector store. For example, set this to `10` to get the ten best results.
### Insert Documents parameters
* **Table name**: Enter the name of the table you want to query.
### Retrieve Documents parameters (for Agent/Chain)
* **Table name**: Enter the name of the table you want to query.
## Node options
### Collection
A way to separate datasets in PGVector. This creates a separate table and column to keep track of which collection a vector belongs to.
* **Use Collection**: Select whether to use a collection (turned on) or not (turned off).
* **Collection Name**: Enter the name of the collection you want to use.
* **Collection Table Name**: Enter the name of the table to store collection information in.
### Column Names
The following options specify the names of the columns to store the vectors and corresponding information in:
* **ID Column Name**
* **Vector Column Name**
* **Content Column Name**
* **Metadata Column Name**
### Metadata Filter
--8<-- "_snippets/integrations/builtin/cluster-nodes/langchain-root-nodes/vector-store-metadata-filter.md"
## Templates and examples
<!-- see https://www.notion.so/n8n/Pull-in-templates-for-the-integrations-pages-37c716837b804d30a33b47475f6e3780 -->
[[ templatesWidget(title, 'pgvector-vector-store') ]]
## Related resources
Refer to [LangChain's PGVector documentation](https://js.langchain.com/docs/integrations/vectorstores/pgvector){:target=_blank .external-link} for more information about the service.
--8<-- "_snippets/integrations/builtin/cluster-nodes/langchain-overview-link.md"
--8<-- "_snippets/self-hosting/starter-kits/self-hosted-ai-starter-kit.md"

View File

@ -13,6 +13,7 @@ You can use these credentials to authenticate the following nodes:
- [Postgres](/integrations/builtin/app-nodes/n8n-nodes-base.postgres/)
- [Agent](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.agent)
- [Postgres Chat Memory](/integrations/builtin/cluster-nodes/sub-nodes/n8n-nodes-langchain.memorypostgreschat/)
- [PGVector Vector Store](/integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepgvector/)
/// note | Agent node users
The Agent node doesn't support SSH tunnels.

View File

@ -779,6 +779,7 @@ nav:
- integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.sentimentanalysis.md
- integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.code.md
- integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreinmemory.md
- integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepgvector.md
- integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstorepinecone.md
- integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoreqdrant.md
- integrations/builtin/cluster-nodes/root-nodes/n8n-nodes-langchain.vectorstoresupabase.md

View File

@ -185,6 +185,7 @@ Ortto
Oura
PDFs
Peekalink
PGVector
PhantomBuster
Pinterest
Pipedrive