Spaces:
Running
Running
File size: 4,979 Bytes
b4884e4 2851ae4 b4884e4 c76ca13 b4884e4 c76ca13 b4884e4 b11f498 94e245c b4884e4 c4a7f78 b4884e4 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 |
import os
import shutil
import streamlit as st
from dotenv import load_dotenv
from langchain.document_loaders import PyPDFLoader
from langchain.embeddings import HuggingFaceEmbeddings
from langchain.vectorstores import FAISS
from langchain.storage import LocalFileStore
from langchain.embeddings import CacheBackedEmbeddings
from langchain_groq import ChatGroq
from langchain_core.runnables import RunnablePassthrough
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.output_parsers import StrOutputParser
from streamlit_chat import message
# Load environment variables
load_dotenv()
os.environ['GROQ_API_KEY'] = os.getenv('GROQ_API')
os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_API_KEY"] = os.getenv('LANGSMITH_API')
UPLOAD_DIR = "uploaded_files"
def cleanup_files():
if os.path.isdir(UPLOAD_DIR):
shutil.rmtree(UPLOAD_DIR, ignore_errors=True)
if 'file_handle' in st.session_state:
st.session_state.file_handle.close()
if 'cleanup_done' not in st.session_state:
st.session_state.cleanup_done = False
if not st.session_state.cleanup_done:
cleanup_files()
if not os.path.exists(UPLOAD_DIR):
os.makedirs(UPLOAD_DIR, exist_ok=True)
# Custom CSS for Wattpad-like theme with background and header
st.markdown(
"""
<style>
body {
background-color: #FFF7F0;
color: #333333;
font-family: 'Helvetica Neue', sans-serif;
background-image: url('https://drive.google.com/uc?export=view&id=17Vg5hM0-X7fUy2BdYCFqSAQtJVDqYErU');
background-size: cover;
background-position: top center;
}
.stButton button {
background-color: #FF5000;
color: white;
border-radius: 12px;
border: none;
padding: 10px 20px;
font-weight: bold;
}
.stButton button:hover {
background-color: #E64500;
}
.stTextInput > div > input {
border: 1px solid #FF5000;
border-radius: 10px;
padding: 10px;
}
.stFileUploader > div {
border: 2px dashed #FF5000;
border-radius: 10px;
padding: 10px;
}
.header {
display: flex;
align-items: center;
gap: 10px;
padding-top: 50px;
}
</style>
""",
unsafe_allow_html=True
)
# Wattpad-like header without logo
st.markdown(
"""
<div class="header" style="display: flex; align-items: center; gap: 10px;">
<h1 style="color: #FF5000; font-weight: bold;">Hi, we're here to help you.</h1>
</div>
""",
unsafe_allow_html=True
)
# Spacer to push chatbot below the header
st.write("<div style='height: 100px;'></div>", unsafe_allow_html=True)
st.title("Chat with your PDF!!")
uploaded_file = st.file_uploader("Upload a file")
if uploaded_file is not None:
file_path = os.path.join(UPLOAD_DIR, uploaded_file.name)
file_path = os.path.abspath(file_path)
with open(file_path, 'wb') as f:
f.write(uploaded_file.getbuffer())
st.write("You're Ready For a Chat with your PDF")
docs = PyPDFLoader(file_path).load_and_split()
embedding = HuggingFaceEmbeddings(
model_name='BAAI/llm-embedder',
)
store = LocalFileStore("./cache/")
cached_embedder = CacheBackedEmbeddings.from_bytes_store(
embedding, store, namespace='embeddings'
)
vector_base = FAISS.from_documents(
docs,
embedding
)
template = ''''''
prompt = ChatPromptTemplate.from_template(template)
retriever = vector_base.as_retriever()
llm = ChatGroq(
model='mixtral-8x7b-32768',
temperature=0,
)
if 'history' not in st.session_state:
st.session_state.history = []
query = st.text_input("Enter your question", placeholder="Ask something interesting...")
if st.button("Submit!", key="submit_button"):
if query:
chain = (
{'context': retriever, 'question': RunnablePassthrough()}
| prompt | llm | StrOutputParser()
)
answer = chain.invoke(query)
st.session_state.history.append({'question': query, 'answer': answer})
if st.session_state.history:
st.write("### Previous Questions and Answers")
for idx, entry in enumerate(st.session_state.history):
st.markdown(
f"""
<div style="background-color: #FFFAF5; padding: 10px; border-radius: 10px; margin-bottom: 10px;">
<p style="font-weight: bold; color: #FF5000;">Q{idx + 1}: {entry['question']}</p>
<p style="color: #333333;">A{idx + 1}: {entry['answer']}</p>
</div>
""",
unsafe_allow_html=True
)
# Reset functionality
if st.button("Reset and Upload a New PDF"):
st.session_state.clear()
st.session_state.cleanup_done = False
st.experimental_rerun()
if st.session_state.cleanup_done:
cleanup_files()
|