Update app.py

app.py

@@ -1,64 +1,103 @@
+# @title set API key
+import os
+import getpass
+from pprint import pprint
+import warnings
+
+warnings.filterwarnings("ignore")
+
+from IPython import get_ipython
+
+if "google.colab" in str(get_ipython()):
+    # Running in Google Colab. Please set the UPSTAGE_API_KEY in the Colab Secrets
+    from google.colab import userdata
+    os.environ["UPSTAGE_API_KEY"]= "up_PaTDq3Dd12IekZZ6KYG4g0deWcWyR"
+else:
+    # Running locally. Please set the UPSTAGE_API_KEY in the .env file
+    from dotenv import load_dotenv
+
+    load_dotenv()
+
+if "UPSTAGE_API_KEY" not in os.environ:
+    os.environ["UPSTAGE_API_KEY"] = getpass.getpass("Enter your Upstage API key: ")
+
+
+from pydantic import BaseModel
+from langchain_upstage import ChatUpstage, UpstageEmbeddings
+
+from langchain_chroma import Chroma
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders.csv_loader import CSVLoader
+from langchain_community.document_loaders import JSONLoader
+from langchain_core.prompts import PromptTemplate
+from langchain_core.output_parsers import StrOutputParser
+from langchain_upstage import ChatUpstage
+from langchain import hub
+
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+
+import pandas as pd
+
+
+
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
+from langchain_core.messages import AIMessage, HumanMessage
+
+rag_with_history_prompt = ChatPromptTemplate.from_messages(
+    [
+        (
+            "system",
+            """
+You are an intelligent assistant helping the members of the Korean National Assembly with questions related to law and policy. As you will respond to the Korean National Assembly, you must answer politely. Read the given questions carefully and give the answer in Korean ONLY using the following pieces of the context.
+
+Do not try to make up an answer:
+ - If the answer to the question cannot be determined from the context alone, say "I cannot determine the answer to that."
+ - If the context is empty, just say "I do not know the answer to that."
+
+Answer the question chronologically by issue.
+
+Context: {context}
+
+Question: {input} 구체적으로 시간순으로 답변해줘.
+
+Answer:
+            """,
         ),
-    ],
+        MessagesPlaceholder(variable_name="history"),
+        ("human", "{input}"),
+    ]
 )
 
+llm = ChatUpstage()
+chain = rag_with_history_prompt | llm | StrOutputParser()
+
+
+DB_PATH = './chroma_db/chroma_db'
+db = Chroma(persist_directory=DB_PATH, embedding_function=UpstageEmbeddings(model="solar-embedding-1-large"))
+retriever = db.as_retriever(search_kwargs={"k": 3})
+
+
+history = []
+
+def chatbot_response(input_text, history):
+    result_docs = retriever.invoke(input_text)  
+    response = chain.invoke({"history": history, "context": result_docs, "input": input_text}) 
+
+    history.append((input_text, response))
+    
+    return history, history  
+
+with gr.Blocks() as demo:
+    gr.Markdown("## 국회 회의록 기반 의정활동 지원 및 대국민 알권리 보장 챗봇")
+    
+    chatbot = gr.Chatbot(label="챗봇")
+    txt = gr.Textbox(label="질문을 입력하세요")
+    submit_btn = gr.Button("질문하기")
+    
+    submit_btn.click(chatbot_response, inputs=[txt, chatbot], outputs=[chatbot, chatbot])
+
+# 앱 실행
+demo.launch(share=True)
+
+
 
-if __name__ == "__main__":
-    demo.launch()