Weaviate Vector Store

​

Node Details

• Name: Weaviate
• Type: Weaviate
• Version: 3.0
• Category: Vector Stores

​

Base Classes

• Weaviate
• VectorStoreRetriever
• BaseRetriever

​

Input Parameters

​

Required Parameters

1. Embeddings: The embedding model to use for vectorizing the data.
2. Weaviate Scheme: The scheme to use for connecting to Weaviate (https or http).
3. Weaviate Host: The host address of the Weaviate instance (e.g., localhost:8080).
4. Weaviate Index: The name of the Weaviate index to use.

​

Optional Parameters

1. Document: List of documents to be inserted into the vector store.
2. Record Manager: Keeps track of records to prevent duplication.
3. Weaviate Text Key: The key used for storing text data in Weaviate.
4. Weaviate Metadata Keys: JSON array of metadata keys to be stored in Weaviate.
5. Top K: Number of top results to fetch (default: 4).
6. Weaviate Search Filter: JSON object for filtering search results.
7. MMR Parameters: Additional parameters for Maximal Marginal Relevance search.

​

Credential (Optional)

• Weaviate API Key: Required only when using Weaviate cloud hosted service.

​

Outputs

1. Weaviate Retriever: A retriever object for querying the Weaviate vector store.
2. Weaviate Vector Store: The Weaviate vector store object.

​

Functionality

1. Upsert: Allows inserting or updating documents in the Weaviate vector store.
2. Delete: Enables deletion of documents from the vector store based on their IDs.
3. Initialization: Sets up the Weaviate client and creates a vector store instance.

​

Use Cases

• Semantic search applications
• Recommendation systems
• Document similarity analysis
• Knowledge management systems
• Any application requiring efficient storage and retrieval of vector embeddings

​

Notes

• The node supports both local and cloud-hosted Weaviate instances.
• It integrates with a record manager for tracking and preventing duplicate entries.
• The node allows for customization of text and metadata keys for flexible data storage.
• It supports advanced querying capabilities through Weaviate’s filtering mechanism.