# Required Imports
import google.generativeai as genai
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain_huggingface import HuggingFaceEmbeddings

# Initialize Google Gemini
genai.configure(api_key="Your api key ")
model = genai.GenerativeModel("gemini-1.5-flash")

# Load and prepare documents
loader = PyPDFLoader('/content/FYP Report PhysioFlex(25july).pdf')  # Load your document
doc = loader.load()
# splitting doucment
text_splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=50)
split_docs = text_splitter.split_documents(doc)
# making embedding
embed_model = HuggingFaceEmbeddings(model_name='BAAI/bge-small-en-v1.5')
vector_store = Chroma.from_documents(split_docs, embed_model)

# Function to handle conversational context
def conversational_rag(query, chat_history):
    # Combine user query with previous chat history
    combined_input = " ".join(chat_history + [query])

    # Perform similarity search to retrieve relevant documents
    retrieved_docs = vector_store.similarity_search(combined_input, k=4)

    # Prepare context from retrieved documents
    retrieved_text = "\n".join([doc.page_content for doc in retrieved_docs])

    # Create a prompt for the LLM
    prompt = f"Based on the following context, answer the question: {combined_input}\n\n{retrieved_text}"

    # Generate the response
    response = model.generate_content(prompt)

    # Append the query and response to chat history
    chat_history.append(query)
    chat_history.append(response.text)

    return response.text, chat_history

# Example usage
chat_history = []
user_query = "Ask the quetsion that you want"
response, chat_history = conversational_rag(user_query, chat_history)

print("LLM Response:", response)

        __
        __