Spaces:
Sleeping
Sleeping
File size: 3,945 Bytes
a6980c7 8fff224 a6980c7 8fff224 a6980c7 8fff224 a6980c7 8fff224 a6980c7 8fff224 a6980c7 |
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 |
import streamlit as st
from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_groq import ChatGroq
from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains.question_answering import load_qa_chain
from langchain.prompts import PromptTemplate
import tempfile
from gtts import gTTS
import os
def text_to_speech(text):
tts = gTTS(text=text, lang='en')
audio_file = tempfile.NamedTemporaryFile(suffix=".mp3", delete=False)
temp_filename = audio_file.name
tts.save(temp_filename)
st.audio(temp_filename, format='audio/mp3')
os.remove(temp_filename)
def get_pdf_text(pdf_docs):
text=""
for pdf in pdf_docs:
pdf_reader= PdfReader(pdf)
for page in pdf_reader.pages:
text+= page.extract_text()
return text
def get_text_chunks(text):
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
chunks = text_splitter.split_text(text)
return chunks
def get_vector_store(text_chunks, api_key):
embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
vector_store.save_local("faiss_index")
def get_conversational_chain():
prompt_template = """
Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
Context:\n {context}?\n
Question: \n{question}\n
Answer:
"""
model = ChatGroq(temperature=0, groq_api_key=os.environ["groq_api_key"], model_name="llama3-8b-8192")
prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
return chain
def user_input(user_question, api_key):
embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
docs = new_db.similarity_search(user_question)
chain = get_conversational_chain()
response = chain(
{"input_documents":docs, "question": user_question}
, return_only_outputs=True)
print(response) # Debugging line
st.write("Replies:")
if isinstance(response["output_text"], str):
response_list = [response["output_text"]]
else:
response_list = response["output_text"]
for text in response_list:
st.write(text)
# Convert text to speech for each response
text_to_speech(text)
def main():
st.set_page_config(layout="centered")
st.header("Chat with DOCS")
st.markdown("<h1 style='font-size:20px;'>ChatBot by Muhammad Huzaifa</h1>", unsafe_allow_html=True)
api_key = st.secrets["inference_api_key"]
with st.sidebar:
st.header("Chat with PDF")
# st.title("Menu:")
pdf_docs = st.file_uploader("Upload your PDF Files and Click on the Submit Button", accept_multiple_files=True, type=["pdf"])
if st.button("Submit"):
with st.spinner("Processing..."):
raw_text = get_pdf_text(pdf_docs)
text_chunks = get_text_chunks(raw_text)
get_vector_store(text_chunks, api_key)
st.success("Done")
# Check if any document is uploaded
if pdf_docs:
user_question = st.text_input("Ask a question from the Docs")
if user_question:
user_input(user_question, api_key)
else:
st.write("Please upload a document first to ask questions.")
if __name__ == "__main__":
main()
|