Chroma Vector Store

​

Node Details

• Name: Chroma_VectorStores

• Type: Chroma

• Version: 2.0

• Category: Vector Stores

​

Base Classes

• Chroma

• VectorStoreRetriever

• BaseRetriever

​

Inputs

1. Document (optional, list)

   • Type: Document

   • Description: List of documents to be stored in the vector store.

2. Embeddings

   • Type: Embeddings

   • Description: Embedding model to use for vectorizing the documents.

3. Record Manager (optional)

   • Type: RecordManager

   • Description: Keeps track of records to prevent duplication.

4. Collection Name

   • Type: string

   • Description: Name of the Chroma collection to use.

5. Chroma URL (optional)

   • Type: string

   • Description: URL of the Chroma instance if using a remote server.

6. Chroma Metadata Filter (optional)

   • Type: json

   • Description: Metadata filter for querying specific documents.

7. Top K (optional)

   • Type: number

   • Description: Number of top results to fetch (default: 4).

​

Outputs

1. Chroma Retriever

   • Type: retriever

   • Base Classes: [Chroma, VectorStoreRetriever, BaseRetriever]

2. Chroma Vector Store

   • Type: vectorStore

   • Base Classes: [Chroma, …BaseClasses(Chroma)]

​

Credential (Optional)

• Type: chromaApi

• Description: API key for Chroma cloud services (if applicable)

​

Methods

​

Upsert

Adds or updates documents in the Chroma vector store.

​

Delete

Removes documents from the Chroma vector store based on provided IDs.

​

Init

Initializes the Chroma vector store or retriever based on the provided configuration.

​

Usage

This node is used for creating and managing a Chroma-based vector store within a larger system. It can be used to:

1. Store and index documents with their embeddings.

2. Retrieve similar documents based on query embeddings.

3. Manage and update the vector store contents.

It’s particularly useful in applications requiring semantic search, document retrieval, or any task benefiting from efficient similarity comparisons of embedded data.