Create app.py

app.py

@@ -0,0 +1,147 @@
+import os
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain_community.vectorstores import Chroma
+from langchain.chains import ConversationalRetrievalChain
+from langchain_community.chat_models import ChatOpenAI
+from langchain_community.document_loaders import PyPDFLoader
+import fitz
+from PIL import Image
+from gtts import gTTS
+import playsound
+import gradio as gr
+from dotenv import load_dotenv
+
+# Load environment variables from .env file
+load_dotenv()
+
+# Global variables
+count = 0
+n = 0
+chat_history = []
+chain = ''
+
+# Function to set the OpenAI API key
+def set_api_key(api_key):
+    os.environ['OPENAI_API_KEY'] = api_key
+    return 'OpenAI API key is set'
+
+# Function to enable the API key input box
+def enable_api_box():
+    return
+
+# Function to add text to the chat history
+def add_text(history, text):
+    if not text:
+        raise gr.Error('Enter text')
+    history.append((text, ''))
+    return history
+
+# Function to process the PDF file and create a conversation chain
+def process_file(file):
+    api_key = os.getenv('OPENAI_API_KEY')
+    if api_key is None:
+        raise gr.Error('OpenAI API key not found in environment variables or .env file')
+
+    loader = PyPDFLoader(file.name)
+    documents = loader.load()
+
+    # Set the OpenAI API key in the environment variable
+    os.environ['OPENAI_API_KEY'] = api_key
+    print("API Key set:", api_key)  # Debug print
+
+    # Assuming OpenAIEmbeddings uses the environment variable
+    embeddings = OpenAIEmbeddings()
+
+    pdf_search = Chroma.from_documents(documents, embeddings)
+
+    chain = ConversationalRetrievalChain.from_llm(ChatOpenAI(temperature=0.3),
+                                                  retriever=pdf_search.as_retriever(search_kwargs={"k": 1}),
+                                                  return_source_documents=True)
+    return chain
+
+# Function to generate a response based on the chat history and query
+def generate_response(history, query, btn):
+    global count, n, chat_history, chain
+
+    if not btn:
+        raise gr.Error(message='Upload a PDF')
+    if count == 0:
+        chain = process_file(btn)
+        count += 1
+
+    result = chain({"question": query, 'chat_history': chat_history}, return_only_outputs=True)
+    chat_history.append((query, result["answer"]))
+    n = list(result['source_documents'][0])[1][1]['page']
+
+    for char in result['answer']:
+        history[-1][-1] += char
+
+    # Generate speech from the answer
+    generate_speech(result["answer"])
+
+    return history, " "
+
+# Function to render a specific page of a PDF file as an image
+def render_file(file):
+    global n
+    doc = fitz.open(file.name)
+    page = doc[n]
+    pix = page.get_pixmap(matrix=fitz.Matrix(300 / 72, 300 / 72))
+    image = Image.frombytes('RGB', [pix.width, pix.height], pix.samples)
+    return image
+
+# Function to generate speech from text
+def generate_speech(text):
+    tts = gTTS(text=text, lang='en')
+    tts.save("output.mp3")
+    playsound.playsound("output.mp3")
+
+# Additional cleanup to remove temporary files
+def cleanup():
+    if os.path.exists("output.mp3"):
+        os.remove("output.mp3")
+
+import gradio as gr
+
+def create_demo():
+    with gr.Blocks(title="PDF Chatbot", theme="Soft") as demo:
+        with gr.Column():
+            with gr.Row():
+                chatbot = gr.Chatbot(value=[], elem_id='chatbot', height=680)
+                show_img = gr.Image(label='PDF Preview', height=680)
+
+        with gr.Row():
+            with gr.Column(scale=0.60):
+                text_input = gr.Textbox(
+                    show_label=False,
+                    placeholder="Ask your pdf?",
+                    container=False
+                )
+
+            with gr.Column(scale=0.20):
+                submit_btn = gr.Button('Send')
+
+            with gr.Column(scale=0.20):
+                upload_btn = gr.UploadButton("📁 Upload PDF", file_types=[".pdf"])
+
+        return demo, chatbot, show_img, text_input, submit_btn, upload_btn
+    
+if __name__ == '__main__':
+    # Create the UI components
+    demo, chatbot, show_img, txt, submit_btn, btn = create_demo()
+
+    # Set up the Gradio UI
+    with demo:
+        # Upload PDF file and render it as an image
+        btn.upload(render_file, inputs=[btn], outputs=[show_img])
+
+        # Add text to chat history, generate response, and render file
+        submit_btn.click(add_text, inputs=[chatbot, txt], outputs=[chatbot], queue=False).\
+            success(generate_response, inputs=[chatbot, txt, btn], outputs=[chatbot, txt]).\
+            success(render_file, inputs=[btn], outputs=[show_img])
+
+    # Launch the app with text-to-speech cleanup
+    try:
+        demo.launch(share=True)
+    finally:
+        cleanup()