webread修正

pages/ChatbotWebRead.py

@@ -1,24 +1,18 @@
 
 import streamlit as st
-import os
-import pickle
 import faiss
 import logging
 
-from multiprocessing import Lock
-from multiprocessing.managers import BaseManager
 from llama_index.callbacks import CallbackManager, LlamaDebugHandler
-from llama_index import VectorStoreIndex, Document,Prompt, SimpleDirectoryReader, ServiceContext, StorageContext, load_index_from_storage
+from llama_index import Prompt, ServiceContext
 from llama_index.chat_engine import CondenseQuestionChatEngine;
 from llama_index.node_parser import SimpleNodeParser
 from llama_index.langchain_helpers.text_splitter import TokenTextSplitter
 from llama_index.constants import DEFAULT_CHUNK_OVERLAP
 from llama_index.response_synthesizers import get_response_synthesizer
-from llama_index import ListIndex, SimpleWebPageReader,TrafilaturaWebReader
+from llama_index import ListIndex, SimpleWebPageReader
 
 import tiktoken
-from logging import getLogger, StreamHandler, Formatter
-
 import common
 
 custom_prompt = Prompt("""\
@@ -44,50 +38,32 @@ logger.debug("調査用ログ")
 common.check_login()
 
 st.title("💬 ChatbotWebRead")
-if st.button("リセット",use_container_width=True):
-    st.session_state.web_chat_engine.reset()
-    st.session_state.webmessages = [{"role": "assistant", "content": "お困りごとはございますか？"}]
-    st.experimental_rerun()
-    logger.info("reset")
-
-if "webmessages" not in st.session_state:
-    st.session_state["webmessages"] = [{"role": "assistant", "content": "お困りごとはございますか？"}]
-
-for msg in st.session_state.webmessages:
-    st.chat_message(msg["role"]).write(msg["content"])
-
-if prompt := st.chat_input():
-    st.session_state.webmessages.append({"role": "user", "content": prompt})
-    st.chat_message("user").write(prompt)
-    response = st.session_state.web_chat_engine.chat(prompt)
-    msg = str(response)
-    st.session_state.webmessages.append({"role": "assistant", "content": msg})
-    st.chat_message("assistant").write(msg)
-
 
+URLtext = st.text_input(
+    "読み込むURLを入力してください",
+    placeholder="https://",
+)
 
-def initialize_webindex():
-    logger.info("initialize_web_index start")
+if st.button("URL reading",use_container_width=True):
     text_splitter = TokenTextSplitter(separator="。", chunk_size=1500
       , chunk_overlap=DEFAULT_CHUNK_OVERLAP
       , tokenizer=tiktoken.encoding_for_model("gpt-3.5-turbo").encode)
     node_parser = SimpleNodeParser(text_splitter=text_splitter)
-    service_context = ServiceContext.from_defaults(node_parser=node_parser)
     d = 1536
     k=2
     faiss_index = faiss.IndexFlatL2(d)
     # デバッグ用
     llama_debug_handler = LlamaDebugHandler()
     callback_manager = CallbackManager([llama_debug_handler])
-    service_context = ServiceContext.from_defaults(callback_manager=callback_manager)
+    service_context = ServiceContext.from_defaults(node_parser=node_parser,callback_manager=callback_manager)
 
     webDocuments = SimpleWebPageReader(html_to_text=True).load_data(
-        ["https://www.stylez.co.jp/"]
+        [URLtext]
     )
     logger.info(webDocuments)
     webIndex = ListIndex.from_documents(webDocuments,service_context=service_context)
     response_synthesizer = get_response_synthesizer(response_mode='compact')
-    webQuery_engine = webIndex.as_query_engine(response_synthesizer=response_synthesizer)
+    webQuery_engine = webIndex.as_query_engine(response_synthesizer=response_synthesizer,service_context=service_context)
     st.session_state.web_chat_engine = CondenseQuestionChatEngine.from_defaults(
         query_engine=webQuery_engine, 
         condense_question_prompt=custom_prompt,
@@ -95,10 +71,24 @@ def initialize_webindex():
         verbose=True
     )
 
+if st.button("リセット",use_container_width=True,disabled = not URLtext):
+    st.session_state.web_chat_engine.reset()
+    st.session_state.webmessages = [{"role": "assistant", "content": "お困りごとはございますか？"}]
+    st.experimental_rerun()
+    logger.info("reset")
+
+if "webmessages" not in st.session_state:
+    st.session_state["webmessages"] = [{"role": "assistant", "content": "お困りごとはございますか？"}]
+
+for msg in st.session_state.webmessages:
+    st.chat_message(msg["role"]).write(msg["content"])
+
+if prompt := st.chat_input(disabled = not URLtext):
+    st.session_state.webmessages.append({"role": "user", "content": prompt})
+    st.chat_message("user").write(prompt)
+    response = st.session_state.web_chat_engine.chat(prompt)
+    msg = str(response)
+    st.session_state.webmessages.append({"role": "assistant", "content": msg})
+    st.chat_message("assistant").write(msg)
+
 
-if __name__ == "__main__":
-    # init the global index
-    logger.info("main start")
-    if "web_chat_engine" not in st.session_state:
-      initialize_webindex()
-      logger.info("initializing index...")