Vector Search Node Documentation
Vector search Node provides the ability to retrie of information retrieval where documents and queries are represented as vectors instead of plain text.
Features
Key Functionalities
-
Dynamic Search Query Input: Allows for customizable search queries using dynamic placeholders like
{{triggerNode_1.output.topic}}. -
Vector Database Selection: Provides an option to select a specific vector database for efficient retrieval of information.
-
Embedding Model Integration: Supports the integration of embedding models by selecting predefined credentials.
-
Certainty Threshold Adjustment: Enables users to set a certainty threshold for search results using an adjustable slider.
-
Result Limitation: Allows limiting the number of search results returned with a configurable limit.
Benefits
-
Customizability: The dynamic query capability ensures that search inputs are adaptable to various scenarios and workflows.
-
Precision: The certainty threshold ensures high relevance of retrieved results by filtering based on confidence levels.
-
Scalability: Supports integration with vector databases and embedding models, making it suitable for complex and large-scale applications.
-
Efficiency: Configurable result limits optimize the retrieval process, saving time and resources.
What can I build?
- Create a dynamic search interface within your application to query a vector database.
- Develop a personalized recommendation system using text and vector based search results.
- Integrate real-time search capabilities to enhance user experience in your app.
Setup
Select the Vector Search Node
- Fill in the required parameters.
- Build the desired flow
- Deploy the Project
- Click Setup on the workflow editor to get the automatically generated instruction and add it in your application.
Configuration Reference
| Parameter | Description | Example Value |
|---|---|---|
| Search Query | Input the query to search the vector database. | Tell me something about Bali |
| Vector DB | Select the vector database to be queried. | Database |
| Embedding Model Name | This field allows the user to select the embedding model used to embed the query into vector space. It loads available embedding models through the listModels method. | Embedding Model Name |
| Boost Properties | Specific properties can be boosted by a factor specified as a number | True/False |
| Certainty | Its the distance score into a value between 0 <= certainty <= 1, where 1 would represent identical vectors and 0 would represent opposite vectors.Its the distance score into a value between 0 <= certainty <= 1, where 1 would represent identical vectors and 0 would represent opposite vectors. | 0.7 |
| Limit | Number of results to return | 3 |
| Filters | Apply JSON-based filters to refine search results. | [] |
Low-Code Example
nodes:
- nodeId: searchNode_747
nodeType: searchNode
nodeName: Vector Search
values:
searchQuery: Tell me something about ${{triggerNode_1.output.topic}}
vectorDB: ""
certainty: "0.85"
limit: "3"
filters: "[]"
needs:
- triggerNode_1
- nodeId: plus-node-addNode_670114
nodeType: addNode
nodeName: ""
values: {}
needs:
- searchNode_747Troubleshooting
Common Issues
| Problem | Solution |
|---|---|
| Invalid API Key | Ensure the API key is correct and has not expired. |
| Dynamic Content Not Loaded | Increase the Wait for Page Load time in the configuration. |
Debugging
- Check Lamatic Flow logs for error details.
- Verify API Key.