节点与集成
Milvus Vector Store
Use the Milvus node to interact with your Milvus database as vector store1. 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 chain2, or connect directly to an agent3 as a tool4.
On this page, you'll find the node parameters for the Milvus node, and links to more resources.
Node usage patterns
You can use the Milvus Vector Store node in the following patterns.
Use as a regular node to insert and retrieve documents
You can use the Milvus Vector Store as a regular node to insert, or get documents. This pattern places the Milvus Vector Store in the regular connection flow without using an agent.
See this example template for how to build a system that stores documents in Milvus and retrieves them to support cited, chat-based answers.
Connect directly to an AI agent as a tool
You can connect the Milvus Vector Store node directly to the tool connector of an AI agent to use a vector store as a resource when answering queries.
Here, the connection would be: AI agent (tools connector) -> Milvus Vector Store node. See this example template where data is embedded and indexed in Milvus, and the AI Agent uses the vector store as a knowledge tool for question-answering.
Use a retriever to fetch documents
You can use the Vector Store Retriever node with the Milvus Vector Store node to fetch documents from the Milvus Vector Store node. This is often used with the Question and Answer Chain node to fetch documents from the vector store that match the given chat input.
A typical node connection flow looks like this: Question and Answer Chain (Retriever connector) -> Vector Store Retriever (Vector Store connector) -> Milvus Vector Store.
Check out this workflow example to see how to ingest external data into Milvus and build a chat-based semantic Q\&A system.
Use the Vector Store Question Answer Tool to answer questions
Another pattern uses the Vector Store Question Answer Tool to summarize results and answer questions from the Milvus Vector Store node. Rather than connecting the Milvus Vector Store directly as a tool, this pattern uses a tool specifically designed to summarizes data in the vector store.
The connections flow would look like this: AI agent (tools connector) -> Vector Store Question Answer Tool (Vector Store connector) -> Milvus Vector store.
Node parameters
This 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.
Rerank Results
Enables 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.
Get Many parameters
- Milvus Collection: Select or enter the Milvus Collection to use.
- Prompt: Enter your search query.
- Limit: Enter how many results to retrieve from the vector store. For example, set this to
10to get the ten best results.
Insert Documents parameters
- Milvus Collection: Select or enter the Milvus Collection to use.
- Clear Collection: Specify whether to clear the collection before inserting new documents.
Retrieve Documents (As Vector Store for Chain/Tool) parameters
- Milvus collection: Select or enter the Milvus Collection to use.
Retrieve Documents (As Tool for AI Agent) parameters
- Name: The name of the vector store.
- Description: Explain to the LLM what this tool does. A good, specific description allows LLMs to produce expected results more often.
- Milvus Collection: Select or enter the Milvus Collection to use.
- Limit: Enter how many results to retrieve from the vector store. For example, set this to
10to get the ten best results.
Node options
Metadata Filter
Available in Get Many mode. When searching for data, use this to match with metadata associated with the document.
This is an AND query. If you specify more than one metadata filter field, all of them must match.
When inserting data, the metadata is set using the document loader. Refer to Default Data Loader for more information on loading documents.
Clear Collection
Available in Insert Documents mode. Deletes all data from the collection before inserting the new data.
Related resources
Refer to LangChain's Milvus documentation for more information about the service.
View n8n's Advanced AI documentation.
Footnotes
- Back
A vector store, or vector database, stores mathematical representations of information. Use with embeddings and retrievers to create a database that your AI can access when answering questions.
- Back
AI chains allow you to interact with large language models (LLMs) and other resources in sequences of calls to components. AI chains in n8n don't use persistent memory, so you can't use them to reference previous context (use AI agents for this).
- Back
AI agents are artificial intelligence systems capable of responding to requests, making decisions, and performing real-world tasks for users. They use large language models (LLMs) to interpret user input and make decisions about how to best process requests using the information and resources they have available.
- Back
In an AI context, a tool is an add-on resource that the AI can refer to for specific information or functionality when responding to a request. The AI model can use a tool to interact with external systems or complete specific, focused tasks.
官方原文和授权
本页来自 N8N 英文官方网站固定快照，并转换成 xueai 静态页面。内容以 N8N 持续更新的官方页面为准。