app.py

import os
from typing import List
from aimakerspace.text_utils import CharacterTextSplitter, TextFileLoader, PDFLoader
from aimakerspace.openai_utils.prompts import (
    UserRolePrompt,
    SystemRolePrompt,
    AssistantRolePrompt,
)
from aimakerspace.openai_utils.embedding import EmbeddingModel
from aimakerspace.vectordatabase import VectorDatabase
from aimakerspace.openai_utils.chatmodel import ChatOpenAI

system_template = """\
Use the following context to answer a users question. If you cannot find the answer in the context, say you don't know the answer."""
system_role_prompt = SystemRolePrompt(system_template)

user_prompt_template = """\
Context:
{context}

Question:
{question}
"""
user_role_prompt = UserRolePrompt(user_prompt_template)

class RetrievalAugmentedQAPipeline:
    def __init__(self, llm: ChatOpenAI(), vector_db_retriever: VectorDatabase) -> None:
        self.llm = llm
        self.vector_db_retriever = vector_db_retriever

    async def arun_pipeline(self, user_query: str):
        context_list = self.vector_db_retriever.search_by_text(user_query, k=4)

        context_prompt = ""
        for context in context_list:
            context_prompt += context[0] + "\n"

        formatted_system_prompt = system_role_prompt.create_message()
        formatted_user_prompt = user_role_prompt.create_message(question=user_query, context=context_prompt)

        async def generate_response():
            async for chunk in self.llm.astream([formatted_system_prompt, formatted_user_prompt]):
                yield chunk

        return {"response": generate_response(), "context": context_list}

text_splitter = CharacterTextSplitter()

def process_file(file_path: str, file_name: str):
    print(f"Processing file: {file_name}")

    # Create appropriate loader based on file extension
    if file_name.lower().endswith('.pdf'):
        loader = PDFLoader(file_path)
    else:
        loader = TextFileLoader(file_path)

    # Load and process the documents
    documents = loader.load_documents()
    texts = text_splitter.split_texts(documents)
    return texts