Prompt and Response (LLM)

How to import prompt and response from Large Large Model (LLM)

For the Retrieval-Augmented Generation (RAG) use case, see the Retrieval section.

Dataframe

Below shows a relevant subsection of the dataframe. The embedding of the prompt is also shown.

prompt	embedding	response
who was the first person that walked on the moon	[-0.0126, 0.0039, 0.0217, ...	Neil Alden Armstrong
who was the 15th prime minister of australia	[0.0351, 0.0632, -0.0609, ...	Francis Michael Forde

Schema

See Retrieval for the Retrieval-Augmented Generation (RAG) use case where relevant documents are retrieved for the question before constructing the context for the LLM.

primary_schema = Schema(
    prediction_id_column_name="id",
    prompt_column_names=EmbeddingColumnNames(
        vector_column_name="embedding",
        raw_data_column_name="prompt",
    )
    response_column_names="response",
)

Inferences

Define the inferences by pairing the dataframe with the schema.

primary_inferences = px.Inferences(primary_dataframe, primary_schema)

Application

session = px.launch_app(primary_inferences)