unit_test.py

# project/test.py

import os
import sys
import unittest
from timeit import default_timer as timer

from langchain.callbacks.base import BaseCallbackHandler
from langchain.schema import HumanMessage

from app_modules.init import app_init
from app_modules.llm_chat_chain import ChatChain
from app_modules.llm_loader import LLMLoader
from app_modules.utils import get_device_types, print_llm_response


class TestLLMLoader(unittest.TestCase):
    question = os.environ.get("CHAT_QUESTION")

    def run_test_case(self, llm_model_type, query):
        n_threds = int(os.environ.get("NUMBER_OF_CPU_CORES") or "4")

        hf_embeddings_device_type, hf_pipeline_device_type = get_device_types()
        print(f"hf_embeddings_device_type: {hf_embeddings_device_type}")
        print(f"hf_pipeline_device_type: {hf_pipeline_device_type}")

        llm_loader = LLMLoader(llm_model_type)
        start = timer()
        llm_loader.init(
            n_threds=n_threds, hf_pipeline_device_type=hf_pipeline_device_type
        )
        end = timer()
        print(f"Model loaded in {end - start:.3f}s")

        result = llm_loader.llm(
            [HumanMessage(content=query)] if llm_model_type == "openai" else query
        )
        end2 = timer()
        print(f"Inference completed in {end2 - end:.3f}s")
        print(result)

    def test_openai(self):
        self.run_test_case("openai", self.question)

    def test_llamacpp(self):
        self.run_test_case("llamacpp", self.question)

    def test_gpt4all_j(self):
        self.run_test_case("gpt4all-j", self.question)

    def test_huggingface(self):
        self.run_test_case("huggingface", self.question)

    def test_hftgi(self):
        self.run_test_case("hftgi", self.question)


class TestChatChain(unittest.TestCase):
    question = os.environ.get("CHAT_QUESTION")

    def run_test_case(self, llm_model_type, query):
        n_threds = int(os.environ.get("NUMBER_OF_CPU_CORES") or "4")

        hf_embeddings_device_type, hf_pipeline_device_type = get_device_types()
        print(f"hf_embeddings_device_type: {hf_embeddings_device_type}")
        print(f"hf_pipeline_device_type: {hf_pipeline_device_type}")

        llm_loader = LLMLoader(llm_model_type)
        start = timer()
        llm_loader.init(
            n_threds=n_threds, hf_pipeline_device_type=hf_pipeline_device_type
        )
        chat = ChatChain(llm_loader)
        end = timer()
        print(f"Model loaded in {end - start:.3f}s")

        inputs = {"question": query}
        result = chat.call_chain(inputs, None)
        end2 = timer()
        print(f"Inference completed in {end2 - end:.3f}s")
        print(result)

        inputs = {"question": "how many people?"}
        result = chat.call_chain(inputs, None)
        end3 = timer()
        print(f"Inference completed in {end3 - end2:.3f}s")
        print(result)

    def test_openai(self):
        self.run_test_case("openai", self.question)

    def test_llamacpp(self):
        self.run_test_case("llamacpp", self.question)

    def test_gpt4all_j(self):
        self.run_test_case("gpt4all-j", self.question)

    def test_huggingface(self):
        self.run_test_case("huggingface", self.question)

    def test_hftgi(self):
        self.run_test_case("hftgi", self.question)


class TestQAChain(unittest.TestCase):
    qa_chain: any
    question = os.environ.get("QA_QUESTION")

    def run_test_case(self, llm_model_type, query):
        start = timer()
        os.environ["LLM_MODEL_TYPE"] = llm_model_type
        qa_chain = app_init()[1]
        end = timer()
        print(f"App initialized in {end - start:.3f}s")

        chat_history = []
        inputs = {"question": query, "chat_history": chat_history}
        result = qa_chain.call_chain(inputs, None)
        end2 = timer()
        print(f"Inference completed in {end2 - end:.3f}s")
        print_llm_response(result)

        chat_history.append((query, result["answer"]))

        inputs = {"question": "tell me more", "chat_history": chat_history}
        result = qa_chain.call_chain(inputs, None)
        end3 = timer()
        print(f"Inference completed in {end3 - end2:.3f}s")
        print_llm_response(result)

    def test_openai(self):
        self.run_test_case("openai", self.question)

    def test_llamacpp(self):
        self.run_test_case("llamacpp", self.question)

    def test_gpt4all_j(self):
        self.run_test_case("gpt4all-j", self.question)

    def test_huggingface(self):
        self.run_test_case("huggingface", self.question)

    def test_hftgi(self):
        self.run_test_case("hftgi", self.question)


def chat():
    start = timer()
    llm_loader = app_init()[0]
    end = timer()
    print(f"Model loaded in {end - start:.3f}s")

    chat_chain = ChatChain(llm_loader)
    chat_history = []

    chat_start = timer()

    while True:
        query = input("Please enter your question: ")
        query = query.strip()
        if query.lower() == "exit":
            break

        print("\nQuestion: " + query)

        start = timer()
        result = chat_chain.call_chain(
            {"question": query, "chat_history": chat_history}, None
        )
        end = timer()
        print(f"Completed in {end - start:.3f}s")

        chat_history.append((query, result["response"]))

    chat_end = timer()
    print(f"Total time used: {chat_end - chat_start:.3f}s")


if __name__ == "__main__":
    if len(sys.argv) > 1 and sys.argv[1] == "chat":
        chat()
    else:
        unittest.main()