Create app.py

app.py

@@ -0,0 +1,86 @@
+import streamlit as st
+from PIL import Image
+from dotenv import load_dotenv
+from streamlit_extras.add_vertical_space import add_vertical_space
+from PyPDF2 import PdfReader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.embeddings.huggingface import HuggingFaceEmbeddings
+from langchain.vectorstores import chroma
+from langchain.chains.retrieval_qa.base import RetrievalQA
+from langchain.chains.question_answering import load_qa_chain
+from langchain_community.llms import huggingface_hub
+from langchain.document_loaders.pdf import PyMuPDFLoader 
+#from transformers import AutoTokenizer, AutoModelForCausalLM
+from ctransformers import AutoModelForCausalLM
+import torch
+
+#from langchain.llms import huggingface_endpoint
+import os
+import fitz
+import tempfile
+
+img = Image.open('image/nexio_logo1.png')
+st.set_page_config(page_title="PDF Chatbot App",page_icon=img,layout="centered")
+
+with st.sidebar:
+    st.title('🤖 AI PDF Chatbot 💬')
+    st.markdown('''
+    ## About
+    This app is an AI chatbot for the PDF files
+    ''')
+    add_vertical_space(12)
+    st.write('Powered by ')
+    st.image(image='image/nexio_logo2.png',width=150)
+
+# load huggingface API key .env file
+load_dotenv()
+
+def main():
+    st.header("Chat with PDF 💬")
+
+    # upload pdf file
+    pdf = st.file_uploader("Upload your PDF file",type='pdf')
+    
+    if pdf is not None:
+        pdf_reader = PdfReader(pdf)
+       
+        text = ""
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+            
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=1000,
+            chunk_overlap=200,
+            length_function=len
+        )
+        chunks = text_splitter.split_text(text=text)
+        #chunks = text_splitter.create_documents(text)
+        
+        # embeddings
+        embeddings = HuggingFaceEmbeddings()
+        vector_store = chroma.Chroma.from_texts(chunks,embeddings)
+        
+        # Accept user question
+        query = st.text_input("Ask questions about your PDF file:")
+
+        if query:
+            torch.cuda.empty_cache()
+            PATH = 'model/'
+            #llm = AutoModelForCausalLM.from_pretrained("CohereForAI/aya-101")
+            # llm = AutoModelForCausalLM.from_pretrained(PATH,local_files_only=True)
+            llm = huggingface_hub.HuggingFaceHub(repo_id="CohereForAI/aya-101",
+                                                  model_kwargs={"temperature":1.0, "max_length":100})
+            docs = vector_store.similarity_search(query=query, k=1)
+            global chain
+            chain = load_qa_chain(llm=llm, chain_type="stuff")
+            response = chain.run(input_documents=docs, question=query)
+            # retriever=vector_store.as_retriever()
+            # st.write(retriever)
+            #chain = RetrievalQA.from_chain_type(llm=llm,chain_type="stuff",retriever=retriever)
+            #response = chain.run(chain)
+            st.write(response)
+            
+
+
+if __name__ == '__main__':
+    main()