File size: 3,339 Bytes
8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 8df1e9f fcbb419 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 |
import streamlit as st
from langchain_core.messages import AIMessage, HumanMessage
from langchain_community.chat_models import ChatOpenAI
from dotenv import load_dotenv
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from download_chart import construct_plot
from langchain_core.runnables import RunnablePassthrough
from langchain import hub
from langchain_core.prompts.prompt import PromptTemplate
from langchain_community.vectorstores import FAISS
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_community.document_loaders import PyPDFLoader
from langchain_experimental.text_splitter import SemanticChunker
load_dotenv()
def get_docs_from_pdf(file):
loader = PyPDFLoader(file)
docs = loader.load_and_split()
return docs
def get_doc_chunks(docs):
text_splitter = SemanticChunker(OpenAIEmbeddings())
chunks = text_splitter.split_documents(docs)
return chunks
def get_vectorstore_from_docs(doc_chunks):
embedding = OpenAIEmbeddings()
vectorstore = FAISS.from_documents(documents=doc_chunks, embedding=embedding)
return vectorstore
def get_conversation_chain(vectorstore):
llm = ChatOpenAI(model="gpt-4o",temperature=0.5, max_tokens=2048)
retriever=vectorstore.as_retriever()
prompt = hub.pull("rlm/rag-prompt")
# Chain
rag_chain = (
{"context": retriever , "question": RunnablePassthrough()}
| prompt
| llm
| StrOutputParser()
)
return rag_chain
def create_db(file):
docs = get_docs_from_pdf(file)
doc_chunks = get_doc_chunks(docs)
vectorstore = get_vectorstore_from_docs(doc_chunks)
return vectorstore
def get_response(chain,user_query, chat_history):
template = """
Chat history: {chat_history}
User question: {user_question}
"""
question = ChatPromptTemplate.from_template(template)
question = question.format(chat_history=chat_history, user_question=user_query)
return chain.stream(question)
def display_chat_te():
# app config
st.title("Chatbot")
# session state
if "chat_history_te" not in st.session_state:
st.session_state.chat_history_te = [
AIMessage(content="Salut, posez-moi vos question sur la transistion ecologique."),
]
if "chain" not in st.session_state:
db=create_db("DATA_bziiit/op.pdf")
chain = get_conversation_chain(db)
st.session_state.chain = chain
# conversation
for message in st.session_state.chat_history_te:
if isinstance(message, AIMessage):
with st.chat_message("AI"):
st.write(message.content)
elif isinstance(message, HumanMessage):
with st.chat_message("Moi"):
st.write(message.content)
# user input
user_query = st.chat_input("Par ici...")
if user_query is not None and user_query != "":
st.session_state.chat_history_te.append(HumanMessage(content=user_query))
with st.chat_message("Moi"):
st.markdown(user_query)
with st.chat_message("AI"):
response = st.write_stream(get_response(st.session_state.chain,user_query, st.session_state.chat_history_te))
st.session_state.chat_history_te.append(AIMessage(content=response))
|