Icon

3.2 - Load an existing Vectore 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.

For now, the FAISS Vector Store Reader Node only supports local paths. Copy the NodeDescriptions folder to a local path and point the FAISS Vector Store Reader to the folder to run the workflow.

The vector store was created using a Python script and the embeddings model used was "text-embedding-ada-002" from OpenAI.

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/

Read an existing Vector Store

  • This workflow shows how to read an existing vector store into KNIME.

  • 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.


The result table contains documents (in this case chunks of documents) that are similar to the whole query words and not necessarily the content.


OpenAIAPI Key
Credentials Configuration
Questions to the store(similarity search)
Table Creator
Most similar documents
Ungroup
Authenticate
OpenAI Authenticator
Choose a modeland configure it
OpenAI Embeddings Connector
Node descriptionsvector store
FAISS Vector Store Reader
Retrieve documents fittingthe query from the vector store
Vector Store Retriever

Nodes

Extensions

Links