Upload app.py

app.py

@@ -0,0 +1,105 @@
+# Import standard library modules
+import os
+
+# Import third-party modules
+from dotenv import load_dotenv, find_dotenv
+import google.generativeai as palm
+import PyPDF2 # Import PyPDF2 library for reading PDF files
+
+# Import local modules
+from langchain import PromptTemplate, LLMChain
+from langchain.chains import RetrievalQA
+from langchain.chains.question_answering import load_qa_chain
+from langchain.document_loaders import UnstructuredPDFLoader, UnstructuredURLLoader
+from langchain.embeddings import GooglePalmEmbeddings
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.llms import GooglePalm
+from langchain.text_splitter import CharacterTextSplitter
+
+# Import gradio module
+import gradio as gr
+
+# Load environment variables from .env file
+load_dotenv(find_dotenv())
+
+# Configure Google Palm API with API key
+api_key = os.environ["GOOGLE_API_KEY"]
+palm.configure(api_key=api_key)
+
+# Create an instance of Google Palm language model
+llm = GooglePalm()
+llm.temperature = 0.1
+
+# List available models that support generateText method
+models = [
+    m for m in palm.list_models() if "generateText" in m.supported_generation_methods
+]
+print(f"There are {len(models)} model(s) available.")
+
+# Create an instance of VectorstoreIndexCreator with Google Palm embeddings and character text splitter
+index_creator = VectorstoreIndexCreator(
+    embedding=GooglePalmEmbeddings(),
+    text_splitter=CharacterTextSplitter(chunk_size=1000, chunk_overlap=0),
+)
+
+# Define a function that takes a PDF file and returns its text content
+def pdf_to_text(file_obj):
+  # Open the PDF file using PyPDF2 library
+  pdf_file = open(file_obj.name, 'rb')
+  pdf_reader = PyPDF2.PdfFileReader(pdf_file)
+  # Get the number of pages in the PDF file
+  num_pages = pdf_reader.numPages
+  # Initialize an empty string to store the text content
+  text_content = ""
+  # Loop through each page and extract its text
+  for i in range(num_pages):
+    page = pdf_reader.getPage(i)
+    text_content += page.extractText()
+  # Close the PDF file
+  pdf_file.close()
+  # Return the text content
+  return text_content
+
+# Define a function that takes a question and a PDF file and returns the answer from the PDF chain
+def answer_question(question, pdf_file):
+  # Use the pdf_to_text function to get the text content of the PDF file
+  pdf_text = pdf_to_text(pdf_file)
+  # Create an UnstructuredPDFLoader object from the pdf_text
+  pdf_loader = UnstructuredPDFLoader(pdf_text)
+  # Create an index from the PDF loader using the index creator
+  pdf_index = index_creator.from_loaders([pdf_loader])
+  # Create a RetrievalQA chain from the PDF index using the llm and a custom chain type
+  pdf_chain = RetrievalQA.from_chain_type(
+      llm=llm,
+      chain_type="stuff",
+      retriever=pdf_index.vectorstore.as_retriever(),
+      input_key="question",
+  )
+  # Use the PDF chain to answer questions about the document
+  return pdf_chain.run(question)
+
+# Define a template for answering questions as an AI assistant working for Raising The Village
+template = """
+You are an artificial intelligence assistant working for Raising The village. You are asked to answer questions. The assistant gives helpful, detailed, and polite answers to the user's questions.
+
+{question}
+
+"""
+
+# Create a PromptTemplate object from the template with question as an input variable
+prompt = PromptTemplate(template=template, input_variables=["question"])
+
+# Create a LLMChain object from the prompt and the llm with verbose mode on
+llm_chain = LLMChain(prompt=prompt, llm=llm, verbose=True)
+
+# Create a gradio interface with a text input, a file input and a text output for the answer function
+interface = gr.Interface(
+  fn=answer_question,
+  inputs=["text", gr.inputs.File(file_types=['.pdf'])], # Add a file input for PDF files
+  outputs="text",
+  title="AI Assistant",
+  description="Ask me anything about Raising The Village"
+)
+
+# Launch the interface in your browser or notebook
+interface.launch(share=True)