llama_call.py

from helper import download_hugging_face_embeddings
from langchain_pinecone import PineconeVectorStore
from langchain.prompts import PromptTemplate
from langchain_community.llms import CTransformers
from langchain.chains import RetrievalQA
from dotenv import load_dotenv
from prompt import prompt_template
import os

load_dotenv()

PINECONE_API_KEY = os.environ.get("PINECONE_API_KEY")
PINECONE_API_ENV = os.environ.get("PINECONE_API_ENV")


embeddings = download_hugging_face_embeddings()
index_name = "llm-chatbot"

# Initializing the Pinecone
docsearch = PineconeVectorStore.from_existing_index(index_name, embeddings)


PROMPT = PromptTemplate(
    template=prompt_template, input_variables=["context", "question"]
)

chain_type_kwargs = {"prompt": PROMPT}

current_dir = os.getcwd()
def load_llm():
    llm = CTransformers(
        model="TheBloke/Llama-2-7B-Chat-GGML",
        model_type="llama",
        max_new_tokens=512,
        temperature=0.5
    )
    return llm
    
llm = load_llm()


qa = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=docsearch.as_retriever(search_kwargs={"k": 2}),
    return_source_documents=True,
    chain_type_kwargs=chain_type_kwargs,
    verbose=True,
)


def llama_call(input):
    result = qa.invoke({"query": input})
    return str(result["result"])