Update app.py

app.py

@@ -1,89 +1,85 @@
-#creating directory
-
-from google.colab import files
-upload = files.upload()
-
-#necessary installations
-# !pip install --upgrade langchain openai -q
-# !pip install unstructured -q
-# !pip install unstructured[local-inference] -q
-# !pip install detectron2@git+https://github.com/facebookresearch/detectron2.git@v0.6#egg=detectron2 -q
-# !apt-get install poppler-utils
-# !pip install pinecone-client -q
-
-#importing necessary modules
-import os
-import openai
-import pinecone
-from langchain.vectorstores import Pinecone
-os.environ["OpenAI_API_Key"] = "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"
-from langchain.document_loaders import DirectoryLoader
-
-#Provding directory to the file
-pdf = 'mod3.pdf'
-os.system(pdf)
-directory = '/content/Dir'
-
-def load_docs(directory):
-  loader = PyPDFLoader(directory)
-  documents = loader.load()
-  return documents
-documents = load_docs(directory)
-len(documents)
-
-#Splitting directory into chunks using RecursiveCharacterTextSplitter
+import streamlit as st
+from dotenv import load_dotenv
+import pickle
+from PyPDF2 import PdfReader
+from streamlit_extras.add_vertical_space import add_vertical_space
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-
-def split_docs(documents, chunk_size=1000, chunk_overlap=20):
-  text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
-  docs = text_splitter.split_documents(documents)
-  return docs
-
-docs = split_docs(documents)
-print(len(docs))
-
-#!pip install tiktoken -q
-
 from langchain.embeddings.openai import OpenAIEmbeddings
-
-#Creating embeddings for the chunks
-embeddings = OpenAIEmbeddings(model_name="ada")
-
-query_result = embeddings.embed_query("Hello world")
-len(query_result)
-
-pinecone.init(
-    api_key="80e2dca6-e86a-4669-ad68-f751aaf739f4", 
-    environment="us-west4-gcp-free"
-) 
-        
-#creating a index in pinecone for storing the embeddings
-index_name = "pdf_read" 
-
-index = Pinecone.from_documents(docs, embeddings, index_name=index_name)
-
-#Checking similar texts
-def get_similiar_docs(query, k=2, score=False):
-  if score:
-    similar_docs = index.similarity_search_with_score(query, k=k)
-  else:
-    similar_docs = index.similarity_search(query, k=k)
-  return similar_docs
-
-#Providing openAI model
+from langchain.vectorstores import FAISS
 from langchain.llms import OpenAI
-
-# model_name = "text-davinci-003"
-# model_name = "gpt-3.5-turbo"
-model_name = "gpt-4"
-llm = OpenAI(model_name=model_name)
-
-#Chaining the relevant docs and query 
 from langchain.chains.question_answering import load_qa_chain
-
-chain = load_qa_chain(llm, chain_type="stuff")
-
-def get_answer(query):
-  similar_docs = get_similiar_docs(query)
-  answer = chain.run(input_documents=similar_docs, question=query)
-  return answer
+from langchain.callbacks import get_openai_callback
+import os
+ 
+# Sidebar contents
+with st.sidebar:
+    st.title('🤗💬 LLM Chat App')
+    st.markdown('''
+    ## About
+    This app is an LLM-powered chatbot built using:
+    - [Streamlit](https://streamlit.io/)
+    - [LangChain](https://python.langchain.com/)
+    - [OpenAI](https://platform.openai.com/docs/models) LLM model
+ 
+    ''')
+    add_vertical_space(5)
+    st.write('Made with ❤️ by [Prompt Engineer](https://youtube.com/@engineerprompt)')
+ 
+load_dotenv()
+ 
+def main():
+    st.header("Chat with PDF 💬")
+ 
+ 
+    # upload a PDF file
+    pdf = st.file_uploader("Upload your PDF", type='pdf')
+ 
+    # st.write(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)
+ 
+        # # embeddings
+        store_name = pdf.name[:-4]
+        st.write(f'{store_name}')
+        # st.write(chunks)
+ 
+        if os.path.exists(f"{store_name}.pkl"):
+            with open(f"{store_name}.pkl", "rb") as f:
+                VectorStore = pickle.load(f)
+            # st.write('Embeddings Loaded from the Disk')s
+        else:
+            embeddings = OpenAIEmbeddings()
+            VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
+            with open(f"{store_name}.pkl", "wb") as f:
+                pickle.dump(VectorStore, f)
+ 
+        # embeddings = OpenAIEmbeddings()
+        # VectorStore = FAISS.from_texts(chunks, embedding=embeddings)
+ 
+        # Accept user questions/query
+        query = st.text_input("Ask questions about your PDF file:")
+        # st.write(query)
+ 
+        if query:
+            docs = VectorStore.similarity_search(query=query, k=3)
+ 
+            llm = OpenAI()
+            chain = load_qa_chain(llm=llm, chain_type="stuff")
+            with get_openai_callback() as cb:
+                response = chain.run(input_documents=docs, question=query)
+                print(cb)
+            st.write(response)
+ 
+if __name__ == '__main__':
+    main()