Update app.py

app.py

@@ -7,7 +7,6 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 import requests
 from twilio.rest import Client
 
-
 # Flask app
 app = Flask(__name__)
 
@@ -15,10 +14,11 @@ app = Flask(__name__)
 CHROMA_PATH = '/code/chroma_db'
 if not os.path.exists(CHROMA_PATH):
     os.makedirs(CHROMA_PATH)
+
+# Initialize ChromaDB
 def initialize_chroma():
     try:
-        # Initialize Chroma
-        embedding_function = HuggingFaceEmbeddings()  # Use your desired embedding function
+        embedding_function = HuggingFaceEmbeddings()
         db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
         
         # Perform an initial operation to ensure the database is correctly initialized
@@ -29,7 +29,6 @@ def initialize_chroma():
 
 initialize_chroma()
 
-
 # Set AI71 API key
 AI71_API_KEY = os.environ.get('AI71_API_KEY')
 account_sid = os.environ.get('TWILIO_ACCOUNT_SID')
@@ -46,68 +45,16 @@ def download_file(url, ext):
                 f.write(chunk)
     return local_filename
 
-# Process PDF and save to ChromaDB
-def save_pdf_and_update_database(pdf_filepath):
+# Process PDF and return text
+def extract_text_from_pdf(pdf_filepath):
     try:
         document_loader = PyPDFLoader(pdf_filepath)
         documents = document_loader.load()
-        
-        text_splitter = RecursiveCharacterTextSplitter(
-            chunk_size=800,
-            chunk_overlap=80,
-            length_function=len,
-            is_separator_regex=False,
-        )
-        chunks = text_splitter.split_documents(documents)
-        
-        embedding_function = HuggingFaceEmbeddings()
-        db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
-        
-        db.add_documents(chunks)
-        db.persist()
-        print("PDF processed and data updated in Chroma.")
+        text = "\n\n".join([doc.page_content for doc in documents])
+        return text
     except Exception as e:
         print(f"Error processing PDF: {e}")
-
-# Generate response using Falcon model
-def generate_response(query, chat_history):
-    response = ''
-    for chunk in AI71(AI71_API_KEY).chat.completions.create(
-            model="tiiuae/falcon-180b-chat",
-            messages=[
-                {"role": "system", "content": "You are the best agricultural assistant. Remember to give a response in not more than 2 sentences."},
-                {"role": "user", "content": f'''Answer the query based on history {chat_history}: {query}'''},
-            ],
-            stream=True,
-    ):
-        if chunk.choices[0].delta.content:
-            response += chunk.choices[0].delta.content
-    return response.replace("###", '').replace('\nUser:', '')
-
-# Query the RAG system
-def query_rag(query_text: str, chat_history):
-    try:
-        # Ensure the database is initialized
-        initialize_chroma()
-
-        embedding_function = HuggingFaceEmbeddings()
-        db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
-        
-        results = db.similarity_search_with_score(query_text, k=5)
-        
-        if not results:
-            return "Sorry, I couldn't find any relevant information."
-        
-        context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
-        
-        prompt = f"Context:\n{context_text}\n\nQuestion:\n{query_text}"
-        response = generate_response(prompt, chat_history)
-        
-        return response
-    except Exception as e:
-        print(f"Error querying RAG system: {e}")
-        return "An error occurred while querying the RAG system."
-
+        return "Error extracting text from PDF."
 
 # Flask route to handle WhatsApp webhook
 @app.route('/whatsapp', methods=['POST'])
@@ -116,25 +63,23 @@ def whatsapp_webhook():
     sender = request.values.get('From')
     num_media = int(request.values.get('NumMedia', 0))
 
-    chat_history = []  # You need to handle chat history appropriately
-
     if num_media > 0:
         media_url = request.values.get('MediaUrl0')
         content_type = request.values.get('MediaContentType0')
 
         if content_type == 'application/pdf':
             filepath = download_file(media_url, ".pdf")
-            save_pdf_and_update_database(filepath)
-            response_text = "PDF has been processed. You can now ask questions related to its content."
+            extracted_text = extract_text_from_pdf(filepath)
+            response_text = f"Here is the content of the PDF:\n\n{extracted_text}"
         else:
             response_text = "Unsupported file type. Please upload a PDF document."
     else:
-        response_text = query_rag(incoming_msg, chat_history)
+        response_text = "Please upload a PDF document."
 
-    # Assuming you have a function to send a message back to the user
     send_message(sender, response_text)
     return '', 204
-    
+
+# Function to send message
 def send_message(to, body):
     try:
         message = client.messages.create(
@@ -145,12 +90,7 @@ def send_message(to, body):
         print(f"Message sent with SID: {message.sid}")
     except Exception as e:
         print(f"Error sending message: {e}")
-        
-def send_initial_message(to_number):
-    send_message(
-        f'whatsapp:{to_number}',
-        'Welcome to the Agri AI Chatbot! How can I assist you today? You can send an image with "pest" or "disease" to classify it.'
-    )
+
 if __name__ == "__main__":
     send_initial_message('919080522395')
     send_initial_message('916382792828')