Streamlit + langchain 实现RAG问答机器人

py 复制代码
import os

os.environ["OPENAI_API_KEY"] = ''
os.environ["OPENAI_API_BASE"] = ''

import streamlit as st
from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings.openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model = 'text-embedding-ada-002'
)
llm = OpenAI(
    model_name = 'gpt-3.5-turbo'
)

st.set_page_config(page_title="Chat", page_icon="", layout="centered", initial_sidebar_state="auto", menu_items=None)
# openai.api_key = st.secrets.openai_key
st.title("Chat with AI")

# function for writing uploaded file in temp
def write_text_file(content, file_path):
    try:
        with open(file_path, 'w') as file:
            file.write(content)
        return True
    except Exception as e:
        print(f"Error occurred while writing the file: {e}")
        return False
    

uploaded_file = st.file_uploader("Upload an article", type="txt")
if uploaded_file is not None:
    content = uploaded_file.read().decode('utf-8')
    # st.write(content)
    file_path = "temp/file.txt"
    write_text_file(content, file_path)   
    
    loader = TextLoader(file_path)
    docs = loader.load()    
    text_splitter = CharacterTextSplitter(chunk_size=100, chunk_overlap=0)
    texts = text_splitter.split_documents(docs)
    db = Chroma.from_documents(texts, embeddings)    
    st.success("File Loaded Successfully!!")
        
if "messages" not in st.session_state.keys(): # Initialize the chat messages history
    st.session_state.messages = [
        {"role": "assistant", "content": "Ask me anything!"}
    ]


if "chat_engine" not in st.session_state.keys(): # Initialize the chat engine
        st.session_state.chat_engine = None

if question := st.chat_input("Your question"): # Prompt for user input and save to chat history
    st.session_state.messages.append({"role": "user", "content": question})

for message in st.session_state.messages: # Display the prior chat messages
    with st.chat_message(message["role"]):
        st.write(message["content"])

# If last message is not from assistant, generate a new response
if st.session_state.messages[-1]["role"] != "assistant":
    with st.chat_message("assistant"):
        with st.spinner("Thinking..."):
            # response = st.session_state.chat_engine.chat(prompt)
            similar_doc = db.similarity_search(question, k=1)
            context = similar_doc[0].page_content

            # set prompt template
            prompt_template = """
Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.

{context}

Question: {question}
Answer:
"""
            prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
            query_llm = LLMChain(llm=llm, prompt=prompt)
            response = query_llm.run({"context": context, "question": question})
            st.write(response)
            message = {"role": "assistant", "content": response}
            st.session_state.messages.append(message) # Add response to message history
相关推荐
Bruce_Liuxiaowei10 分钟前
基于Flask的DeepSeek~学术研究领域智能辅助系统设计与实现
后端·python·flask·deepseek
Swift社区20 分钟前
轻松搞定!Mac 用户的 ESP-IDF 安装全攻略
python·嵌入式
学c真好玩32 分钟前
4.3python操作ppt
开发语言·python·powerpoint
niuTaylor1 小时前
大学生机器人比赛实战(一)综述篇
机器人
巷北夜未央1 小时前
数据结构之二叉树Python版
开发语言·数据结构·python
wapicn991 小时前
手机归属地查询Api接口,数据准确可靠
java·python·智能手机·php
视觉&物联智能2 小时前
【杂谈】-大型语言模型对具身人工智能发展的推动与挑战
人工智能·搜索引擎·语言模型·大模型·llm·具身人工智能
郝YH是人间理想2 小时前
OpenCV基础——傅里叶变换、角点检测
开发语言·图像处理·人工智能·python·opencv·计算机视觉
白白糖2 小时前
二叉树 递归
python·算法·力扣
G皮T3 小时前
【Python Cookbook】字符串和文本(五):递归下降分析器
数据结构·python·正则表达式·字符串·编译原理·词法分析·语法解析