|
import os |
|
import sys |
|
from queue import Queue |
|
from timeit import default_timer as timer |
|
|
|
from langchain.callbacks.base import BaseCallbackHandler |
|
from langchain.schema import LLMResult |
|
|
|
from app_modules.init import app_init |
|
from app_modules.utils import print_llm_response |
|
|
|
llm_loader, qa_chain = app_init() |
|
|
|
|
|
class MyCustomHandler(BaseCallbackHandler): |
|
def __init__(self): |
|
self.reset() |
|
|
|
def reset(self): |
|
self.texts = [] |
|
|
|
def get_standalone_question(self) -> str: |
|
return self.texts[0].strip() if len(self.texts) > 0 else None |
|
|
|
def on_llm_end(self, response: LLMResult, **kwargs) -> None: |
|
"""Run when chain ends running.""" |
|
print("\non_llm_end - response:") |
|
print(response) |
|
self.texts.append(response.generations[0][0].text) |
|
|
|
|
|
chatting = len(sys.argv) > 1 and sys.argv[1] == "chat" |
|
questions_file_path = os.environ.get("QUESTIONS_FILE_PATH") |
|
chat_history_enabled = os.environ.get("CHAT_HISTORY_ENABLED") or "true" |
|
|
|
custom_handler = MyCustomHandler() |
|
|
|
|
|
chat_history = [] |
|
print("Welcome to the ChatPDF! Type 'exit' to stop.") |
|
|
|
|
|
file = open(questions_file_path, "r") |
|
|
|
|
|
queue = file.readlines() |
|
for i in range(len(queue)): |
|
queue[i] = queue[i].strip() |
|
|
|
|
|
file.close() |
|
|
|
queue.append("exit") |
|
|
|
chat_start = timer() |
|
|
|
while True: |
|
if chatting: |
|
query = input("Please enter your question: ") |
|
else: |
|
query = queue.pop(0) |
|
|
|
query = query.strip() |
|
if query.lower() == "exit": |
|
break |
|
|
|
print("\nQuestion: " + query) |
|
custom_handler.reset() |
|
|
|
start = timer() |
|
result = qa_chain.call_chain( |
|
{"question": query, "chat_history": chat_history}, |
|
custom_handler, |
|
None, |
|
True, |
|
) |
|
end = timer() |
|
print(f"Completed in {end - start:.3f}s") |
|
|
|
print_llm_response(result) |
|
|
|
if len(chat_history) == 0: |
|
standalone_question = query |
|
else: |
|
standalone_question = custom_handler.get_standalone_question() |
|
|
|
if standalone_question is not None: |
|
print(f"Load relevant documents for standalone question: {standalone_question}") |
|
start = timer() |
|
qa = qa_chain.get_chain() |
|
docs = qa.retriever.get_relevant_documents(standalone_question) |
|
end = timer() |
|
|
|
|
|
print(f"Completed in {end - start:.3f}s") |
|
|
|
if chat_history_enabled == "true": |
|
chat_history.append((query, result["answer"])) |
|
|
|
chat_end = timer() |
|
total_time = chat_end - chat_start |
|
print(f"Total time used: {total_time:.3f} s") |
|
print(f"Number of tokens generated: {llm_loader.streamer.total_tokens}") |
|
print( |
|
f"Average generation speed: {llm_loader.streamer.total_tokens / total_time:.3f} tokens/s" |
|
) |
|
|