brain.py

import os
import streamlit as st
from langchain_community.document_loaders import TextLoader, DirectoryLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain_huggingface import HuggingFaceEmbeddings, HuggingFaceEndpoint, ChatHuggingFace
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser

@st.cache_resource
def setup_vector_db():
    loader = DirectoryLoader('./knowledge_base/', glob="./*.txt", loader_cls=TextLoader)
    docs = loader.load()
    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    splits = splitter.split_documents(docs)
    
    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
    vectorstore = FAISS.from_documents(splits, embeddings)
    return vectorstore.as_retriever()

def get_llm(hf_token):
    llm_endpoint = HuggingFaceEndpoint(
        repo_id="mistralai/Mistral-7B-Instruct-v0.2",
        task="conversational",
        huggingfacehub_api_token=hf_token,
        temperature=0.5
    )
    return ChatHuggingFace(llm=llm_endpoint)

def get_rag_chain(retriever, llm):
    template = """You are Ahan Bose's AI Twin. Answer based only on the context provided:
    {context}

    Question: {question}
    """
    prompt = ChatPromptTemplate.from_template(template)
    
    chain = (
        {"context": retriever, "question": RunnablePassthrough()}
        | prompt
        | llm
        | StrOutputParser()
    )
    return chain