Spaces:
Runtime error
Runtime error
File size: 3,817 Bytes
dca217d |
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 99 100 101 102 |
import streamlit as st
from streamlit_chat import message
from langchain.chains import ConversationalRetrievalChain
from langchain.document_loaders import PyPDFLoader, DirectoryLoader
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.llms import CTransformers
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.memory import ConversationBufferMemory
# Function to load documents
def load_documents():
loader = DirectoryLoader('data/', glob="*.pdf", loader_cls=PyPDFLoader)
documents = loader.load()
return documents
# Function to split text into chunks
def split_text_into_chunks(documents):
text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
text_chunks = text_splitter.split_documents(documents)
return text_chunks
# Function to create embeddings
def create_embeddings():
embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2", model_kwargs={'device': "cpu"})
return embeddings
# Function to create vector store
def create_vector_store(text_chunks, embeddings):
vector_store = FAISS.from_documents(text_chunks, embeddings)
return vector_store
# Function to create LLMS model
def create_llms_model():
llm = CTransformers(model="mistral-7b-instruct-v0.1.Q4_K_M.gguf", config={'max_new_tokens': 128, 'temperature': 0.01})
return llm
# Initialize Streamlit app
st.title("Job Interview Prep ChatBot")
st.title("Personalized Job Success Friend")
st.markdown('<style>h1{color: orange; text-align: center;}</style>', unsafe_allow_html=True)
st.subheader('Get Your Desired Job 💪')
st.markdown('<style>h3{color: pink; text-align: center;}</style>', unsafe_allow_html=True)
# loading of documents
documents = load_documents()
# Split text into chunks
text_chunks = split_text_into_chunks(documents)
# Create embeddings
embeddings = create_embeddings()
# Create vector store
vector_store = create_vector_store(text_chunks, embeddings)
# Create LLMS model
llm = create_llms_model()
# Initialize conversation history
if 'history' not in st.session_state:
st.session_state['history'] = []
if 'generated' not in st.session_state:
st.session_state['generated'] = ["Hello! Ask me anything about 🤗"]
if 'past' not in st.session_state:
st.session_state['past'] = ["Hey! 👋"]
# Create memory
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
# Create chain
chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
retriever=vector_store.as_retriever(search_kwargs={"k": 2}),
memory=memory)
# Define chat function
def conversation_chat(query):
result = chain({"question": query, "chat_history": st.session_state['history']})
st.session_state['history'].append((query, result["answer"]))
return result["answer"]
# Display chat history
reply_container = st.container()
container = st.container()
with container:
with st.form(key='my_form', clear_on_submit=True):
user_input = st.text_input("Question:", placeholder="Ask about your Job Interview", key='input')
submit_button = st.form_submit_button(label='Send')
if submit_button and user_input:
output = conversation_chat(user_input)
st.session_state['past'].append(user_input)
st.session_state['generated'].append(output)
if st.session_state['generated']:
with reply_container:
for i in range(len(st.session_state['generated'])):
message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji") |