Icon

3.1 - Create a Vector Store

You can easily download and run the workflow directly in your KNIME installation. We recommend that you use the latest version of the KNIME Analytics Platform for optimal performance.

It also shows how the Vector Store Retriever can be used to query the vector store for similar documents.

In order to run the workflow you need an OpenAI API key. If you don't have one already, register with OpenAI and create a new API key under https://platform.openai.com/account/api-keys.

URL: OpenAI API Keys https://platform.openai.com/account/api-keys
URL: Faiss LangChain Documentation https://python.langchain.com/docs/modules/data_connection/vectorstores/integrations/faiss
URL: Vector Stores LangChain Documentation https://python.langchain.com/docs/modules/data_connection/vectorstores/

Create a Vector Store with OpenAI Embeddings

  • This workflow shows how to create a vector store from a KNIME table using OpenAI Embeddings and the FAISS Vector Store Creator.

  • In order to run the workflow you need an OpenAI API key. If you don't have one already, register with OpenAI and create a new API key under https://platform.openai.com/account/api-keys

  • To learn more about the workflow, click the left bar and check the description section.


We can then perform a similarity search to retrieve the top k most similar documents from the store.


OpenAIAPI Key
Credentials Configuration
To open the view, hover over the node and click the lens icon.
Table View
Documents
Table Creator
Query
Table Creator
Ungroup
Authenticate
OpenAI Authenticator
Choose and configurea model it
OpenAI Embeddings Connector
Creates embeds the provideddocuments and stores themtogether with their embeddingvectors in a database for laterretrieval
FAISS Vector Store Creator
Embeds the query andsearches for similarembedding vectors inthe vector store
Vector Store Retriever

Nodes

Extensions

Links