Icon

Vector Store_​demo

There has been no title set for this workflow's metadata.

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 EmbeddingsThis 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-keysTo learn more about the workflow, click the left bar and check the description section. We can then perform a similarity search toretrieve the top k most similar documentsfrom the store. Use case 1 - right information Use case 2 - no information change storage location OpenAIAPI KeyChoose and configurea modelCreates embeds the provideddocuments and stores themtogether with their embeddingvectors in a database for laterretrievalEmbeds the query andsearches for similarembedding vectors inthe vector storeQueryNode 149To open the view, hover over the node and click the lens icon.Node 153Node 155Turn the vector storeinto a toolgpt-3.5-turbo(ChatGPT)Read the vectorstoreConversation historyConfigure the agentto be KAILAquademadelixquademadelix row 481 Strings To Document Sentence Extractor CredentialsConfiguration OpenAIAuthenticator OpenAI EmbeddingsConnector FAISS VectorStore Creator Vector StoreRetriever Table Creator Ungroup Table View Tika Parser Model Writer Vector Storeto Tool OpenAI ChatModel Connector Model Reader Agent Prompter Table Creator OpenAI FunctionsAgent Creator Table Creator CSV Reader Create a Vector Store with OpenAI EmbeddingsThis 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-keysTo learn more about the workflow, click the left bar and check the description section. We can then perform a similarity search toretrieve the top k most similar documentsfrom the store. Use case 1 - right information Use case 2 - no information change storage location OpenAIAPI KeyChoose and configurea modelCreates embeds the provideddocuments and stores themtogether with their embeddingvectors in a database for laterretrievalEmbeds the query andsearches for similarembedding vectors inthe vector storeQueryNode 149To open the view, hover over the node and click the lens icon.Node 153Node 155Turn the vector storeinto a toolgpt-3.5-turbo(ChatGPT)Read the vectorstoreConversation historyConfigure the agentto be KAILAquademadelixquademadelix row 481 Strings To Document Sentence Extractor CredentialsConfiguration OpenAIAuthenticator OpenAI EmbeddingsConnector FAISS VectorStore Creator Vector StoreRetriever Table Creator Ungroup Table View Tika Parser Model Writer Vector Storeto Tool OpenAI ChatModel Connector Model Reader Agent Prompter Table Creator OpenAI FunctionsAgent Creator Table Creator CSV Reader

Nodes

Extensions

Links

Download

To use this workflow in KNIME, download it from the below URL and open it in KNIME:

Download Workflow
Created by: knime356
Created at: 2023-07-05
On NodePit since: 2023-08-17
Last update: 2024-05-01
Created with KNIME version: v5.1.0
Tags: OpenAIEmbeddingsVector StoreAI

Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.

Try NodePit Runner!