Spaces:
Sleeping
Sleeping
File size: 4,051 Bytes
9918e87 |
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 |
import streamlit as st
from langchain_core.messages import AIMessage, HumanMessage
from langchain_community.document_loaders import WebBaseLoader
from langchain_openai import ChatOpenAI
from langchain_chroma import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_huggingface.embeddings import HuggingFaceEndpointEmbeddings
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain.chains.history_aware_retriever import create_history_aware_retriever
from langchain.chains.retrieval import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from dotenv import load_dotenv
import os
load_dotenv()
llm = ChatOpenAI(temperature=0.5, model="mistralai/mistral-7b-instruct:free",base_url="https://openrouter.ai/api/v1",api_key=os.getenv("OPENAI_API_KEY"))
def get_vector_store(url):
loader = WebBaseLoader(url)
documents = loader.load()
# splitting into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
documents_chunks = text_splitter.split_documents(documents=documents)
# converting the chunks into embeddings
embeddings = HuggingFaceEndpointEmbeddings(huggingfacehub_api_token=os.getenv("HF_TOKEN"))
# store the embeddings in a database
vector_store = Chroma.from_documents(documents_chunks, embeddings)
return vector_store
def get_context_retiriever(vector_store):
retriever = vector_store.as_retriever()
prompt = ChatPromptTemplate.from_messages([
MessagesPlaceholder(variable_name="chat_history"),
("user", "{input}"),
("user", "Given the above conversation, generate a search query to look up in order to get information relevant to the conversation")
])
retriever_chain = create_history_aware_retriever(llm=llm, retriever=retriever, prompt=prompt)
return retriever_chain
def get_conversational_chain(retriever_chain):
prompt = ChatPromptTemplate.from_messages([
("system", "Answer the user's questions based on the below context:\n\n{context}"),
MessagesPlaceholder(variable_name="chat_history"),
("user", "{input}"),
])
stuff_documnets_chain = create_stuff_documents_chain(llm, prompt)
return create_retrieval_chain(retriever_chain, stuff_documnets_chain)
def get_response(user_input):
retriever_chain = get_context_retiriever(st.session_state.vector_store)
conversational_chain = get_conversational_chain(retriever_chain)
response = conversational_chain.invoke({
"chat_history": st.session_state.chat_history,
"input": user_input
})
return response['answer']
st.set_page_config(page_title="Chat with websites", page_icon="🤖")
st.title("Chat with websites")
st.caption("Follow me on Github: [samagra44](https://github.com/samagra44)")
with st.sidebar:
st.header("Settings")
website_url = st.text_input("Website URL")
if website_url is None or website_url == "":
st.info("Please enter a website URL")
else:
if "chat_history" not in st.session_state:
st.session_state.chat_history = [
AIMessage(content="Hello, I am a bot. How can I help you?"),
]
if "vector_store" not in st.session_state:
st.session_state.vector_store = get_vector_store(website_url)
user_query = st.chat_input("Type your message here...")
if user_query is not None and user_query != "":
response = get_response(user_query)
st.session_state.chat_history.append(HumanMessage(content=user_query))
st.session_state.chat_history.append(AIMessage(content=response))
for message in st.session_state.chat_history:
if isinstance(message, AIMessage):
with st.chat_message("AI"):
st.write(message.content)
elif isinstance(message, HumanMessage):
with st.chat_message("Human"):
st.write(message.content) |