Adds context to be used by the model when answering
add_context.Rdadd_context lets you add context info (in the shape of a context dataframe containing embeddings and text info) to supplement or narrow down the answers from the LLM.
Arguments
- workflow_obj
A workflow object containing all parameters describing the workflow required
- context_df
a dataframe containing the text embeddings and text information that can be used to retrieve relevant context
- context_usage_mandatory
a boolean value (defaults to FALSE) to let the LLM know if it should ONLY use the context to answer, or if it can use the context optionally to answer a question.
Details
For this to work you need to add a context_df that was build using the generate_document_embeddings function.
Examples
conn <- get_ollama_connection()
document <- "Standing proudly on the Île de la Cité in the heart of Paris,
France's capital city, lies one of the world's most beloved and historic
landmarks: the magnificent Notre Dame Cathedral. This Gothic masterpiece
has been welcoming pilgrims and tourists alike for over 850 years, since its
construction began in 1163 under King Louis VII. With its towering spires,
stunning stained glass windows, and intricate stone carvings, this beautiful
church is a testament to medieval architecture and engineering skill.
Unfortunately, a devastating fire ravaged the cathedral on April 15, 2019,
but thanks to swift action from firefighters and restoration efforts
underway, Notre Dame continues to inspire awe in those who visit her."
writeLines(document, con = "doc1.txt")
write_vectors_to_feather_file(file_name = "doc1.feather",
vector_data = generate_document_embeddings(conn,
document_path = "doc1.txt", splitter = "paragraph"))
notre_dame_embeddings <- load_context_embeddings_from_feather_files(filenames = "doc1.feather")
my_workflow <- ai_workflow() |>
set_system_prompt(system_prompt="You are a helpful AI assistant.
Answer to the best of your knowledge.") |>
add_context(context_df = notre_dame_embeddings, use_context_mandatory=TRUE)
#> Error in add_context(set_system_prompt(ai_workflow(), system_prompt = "You are a helpful AI assistant. \nAnswer to the best of your knowledge."), context_df = notre_dame_embeddings, use_context_mandatory = TRUE): unused argument (use_context_mandatory = TRUE)