Update app.py

app.py

@@ -1,21 +1,37 @@
+from flask import Flask, request
 import os
+from langchain.vectorstores import Chroma
+from langchain.document_loaders import PyPDFLoader
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import requests
 
+# Flask app
+app = Flask(__name__)
+
+# ChromaDB path
 CHROMA_PATH = '/code/chroma_db'
 if not os.path.exists(CHROMA_PATH):
     os.makedirs(CHROMA_PATH)
-from langchain.vectorstores.chroma import Chroma
-from langchain.document_loaders import PyPDFLoader
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.text_splitter import RecursiveCharacterTextSplitter
 
-# Load and process the PDF
+# Set AI71 API key
+AI71_API_KEY = os.environ.get('AI71_API_KEY')
+
+# Download file utility
+def download_file(url, ext):
+    local_filename = f'/code/uploads/uploaded_file{ext}'
+    with requests.get(url, stream=True) as r:
+        with open(local_filename, 'wb') as f:
+            for chunk in r.iter_content(chunk_size=8192):
+                f.write(chunk)
+    return local_filename
+
+# Process PDF and save to ChromaDB
 def save_pdf_and_update_database(pdf_filepath):
     try:
-        # Load the PDF
         document_loader = PyPDFLoader(pdf_filepath)
         documents = document_loader.load()
         
-        # Split the documents into manageable chunks
         text_splitter = RecursiveCharacterTextSplitter(
             chunk_size=800,
             chunk_overlap=80,
@@ -24,19 +40,16 @@ def save_pdf_and_update_database(pdf_filepath):
         )
         chunks = text_splitter.split_documents(documents)
         
-        # Initialize Chroma with an embedding function
         embedding_function = HuggingFaceEmbeddings()
         db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
         
-        # Add chunks to ChromaDB
         db.add_documents(chunks)
         db.persist()
         print("PDF processed and data updated in Chroma.")
     except Exception as e:
         print(f"Error processing PDF: {e}")
 
-AI71_API_KEY = os.environ.get('AI71_API_KEY')
-
+# Generate response using Falcon model
 def generate_response(query, chat_history):
     response = ''
     for chunk in AI71(AI71_API_KEY).chat.completions.create(
@@ -51,10 +64,10 @@ def generate_response(query, chat_history):
             response += chunk.choices[0].delta.content
     return response.replace("###", '').replace('\nUser:', '')
 
+# Query the RAG system
 def query_rag(query_text: str, chat_history):
     db = Chroma(persist_directory=CHROMA_PATH, embedding_function=HuggingFaceEmbeddings())
     
-    # Perform a similarity search in ChromaDB
     results = db.similarity_search_with_score(query_text, k=5)
     
     if not results:
@@ -62,41 +75,53 @@ def query_rag(query_text: str, chat_history):
     
     context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
     
-    # Generate the response using the Falcon model
     prompt = f"Context:\n{context_text}\n\nQuestion:\n{query_text}"
     response = generate_response(prompt, chat_history)
     
     return response
 
-
+# Flask route to handle WhatsApp webhook
 @app.route('/whatsapp', methods=['POST'])
 def whatsapp_webhook():
     incoming_msg = request.values.get('Body', '').lower()
     sender = request.values.get('From')
     num_media = int(request.values.get('NumMedia', 0))
 
-    chat_history = conversation_memory.get_memory()
+    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':
-            # Handle PDF processing
             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."
         else:
             response_text = "Unsupported file type. Please upload a PDF document."
     else:
-        # Handle queries
         response_text = query_rag(incoming_msg, chat_history)
 
-    conversation_memory.add_to_memory({"user": incoming_msg, "assistant": response_text})
+    # Assuming you have a function to send a message back to the user
     send_message(sender, response_text)
     return '', 204
-
-
+    
+def send_message(to, body):
+    try:
+        message = client.messages.create(
+            from_=from_whatsapp_number,
+            body=body,
+            to=to
+        )
+        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')