SuperSCC.rag.SimpleRAG

class SuperSCC.rag.SimpleRAG(file_path: str, file_type: str)

A class that encapsulates a complete Retrieval-Augmented Generation (RAG) pipeline, from data loading and processing to answer generation and citation

Parameters:

• (str) (file_type) – The path to the file or the root directory containing the documents to be processed.

• (str) – The file extension to look for (e.g., “pdf”, “csv”). This determines which files are loaded.

__init__(file_path: str, file_type: str)

Methods

__init__(file_path, file_type)
add_documents(file_path, file_type[, ...])
change_text_embedding(model_name[, ...])
create_rag_chain(vector_store, model, ...[, ...])
data_loader(file_path[, mode, metadata_columns])
format_docs(docs)
get_all_ids()
get_answer(gene_list[, query, ...])	The main entry point for asking a question.
get_relevant_segments()
highlight_docs()
hybrid_search([hierarchy_search, key, value])
recursive_search(path[, type])
refine_query()
rerank([model, top_n])
run_rag(qdrant_location, ...[, qdrant_host, ...])	Executes the entire RAG pipeline from scratch: loading, splitting, encoding, and creating the chain.
score_documents([docs])
summary_res(res)
text_encode(text, model_name, location[, ...])
text_split(docs[, chunk_size, ...])
translator([query])
update_rag_chain([model, api_key, base_url, ...])	Updates components of the existing RAG chain, such as the LLM or prompt.