Icon

08_​Topic Labeling via a Large Language Model (LLM) via Prompt Engineering (Experimental)

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

A Large Language Model such as GPT-3.5 Turbo can perform simple tasks if well instructed. In this instance we provide 10 possible labels and we require the model to answer with 1 word answer (the label).

A vector store is provided for experimental purposes. Usually vector stores are useful to ask the model to retrieve the right doc or answer a question based on the knowledge base of the documents corpus.

Scoring

Reading a CSV
with Documents

Topic Labeling via a Large Language Model (LLM) via Prompt Engineering (Experimental)

A Large Language Model such as GPT-3.5 Turbo can perform simple tasks if well instructed. In this instance we provide 10 possible labels and we require the model to answer with 1 word answer (the label).
A vector store is provided for experimental purposes. Usually vector stores are useful to ask the model to retrieve the right doc or answer a question based on the knowledge base of the documents corpus.

Table Row To Variable
Joiner
String Manipulation (Variable)
Table View
Row Filter
Chunk Loop Start
Post Process
Loop End
Vector Store to Tool
Agent Prompter
Selectgpt-3.5-turbo
OpenAI Chat Model Connector
Empty conversation
Table Creator
FAISS Vector Store Creator
OpenAI Functions Agent Creator
OpenAI Embeddings Connector
OpenAI Authenticator
Partitioning
CSV Reader
sampling in this example as API calls are not free
Row Sampling
OpenAIAPI Key
Credentials Configuration

Nodes

Extensions

Links