summ.py

import os
from langchain.chains.llm import LLMChain
from langchain.chat_models import ChatOpenAI
from langchain.prompts import PromptTemplate
from langchain.document_loaders import PDFPlumberLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.chains import ReduceDocumentsChain, MapReduceDocumentsChain
from langchain.chains.combine_documents.stuff import StuffDocumentsChain

os.environ['OPENAI_API_KEY'] = os.getenv("OPENAI_API_KEY")

llm = ChatOpenAI(temperature=0, model_name="gpt-4-0125-preview")

def get_summ(path):

    loader = PDFPlumberLoader(path)
    docs = loader.load()
    # Map
    map_template = """The following is a set of documents
    {docs}
    Based on this list of docs, please identify the main themes and determine the genes relevant or irrelevant to the discussed disease followed by any associated p-values if available.
    Helpful Answer:"""
    map_prompt = PromptTemplate.from_template(map_template)
    map_chain = LLMChain(llm=llm, prompt=map_prompt)

    # Reduce
    reduce_template = """The following is set of summaries:
    {doc_summaries}
    Take these and distill it into a final, consolidated summary of the main themes. 
    Helpful Answer:"""
    reduce_prompt = PromptTemplate.from_template(reduce_template)

    # Run chain
    reduce_chain = LLMChain(llm=llm, prompt=reduce_prompt)

    # Takes a list of documents, combines them into a single string, and passes this to an LLMChain
    combine_documents_chain = StuffDocumentsChain(
        llm_chain=reduce_chain, document_variable_name="doc_summaries"
    )

    # Combines and iteravely reduces the mapped documents
    reduce_documents_chain = ReduceDocumentsChain(
        # This is final chain that is called.
        combine_documents_chain=combine_documents_chain,
        # If documents exceed context for `StuffDocumentsChain`
        collapse_documents_chain=combine_documents_chain,
        # The maximum number of tokens to group documents into.
        token_max=100000,
    )

    # Combining documents by mapping a chain over them, then combining results
    map_reduce_chain = MapReduceDocumentsChain(
        # Map chain
        llm_chain=map_chain,
        # Reduce chain
        reduce_documents_chain=reduce_documents_chain,
        # The variable name in the llm_chain to put the documents in
        document_variable_name="docs",
        # Return the results of the map steps in the output
        return_intermediate_steps=False,
    )

    text_splitter = CharacterTextSplitter.from_tiktoken_encoder(
        chunk_size=100000, chunk_overlap=0
    )
    split_docs = text_splitter.split_documents(docs)

    return map_reduce_chain.run(split_docs)