Icon

OpenAI Agent

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.

This workflow shows how to provide an OpenAI Functions Agent with a vector store as tool. When the agent is prompted, it can decide based on the input if it needs to retrieve information from the vector store to respond to the prompt.

For now, the FAISS Vector Store Reader Node only supports local paths. Copy the YoutubeTranscripts folder to a local path and point the FAISS Vector Store Reader to it to run the workflow.
Note that this agent requires the tool name to not contain white spaces.

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: OpenAI Functions Agent LangChain Documentation https://python.langchain.com/docs/modules/agents/agent_types/openai_functions_agent
URL: Faiss LangChain Documentation https://python.langchain.com/v0.2/docs/integrations/vectorstores/faiss/
URL: Vector Stores LangChain Documentation https://python.langchain.com/docs/modules/data_connection/vectorstores/

Nodes

Extensions

Links