Update app.py

app.py

@@ -209,39 +209,58 @@ def query_rag(query_text: str):
             response += chunk.choices[0].delta.content
     
     return response.replace("###", '').replace('\nUser:', '')
+def download_file(url, extension):
+    try:
+        response = requests.get(url)
+        response.raise_for_status()
+        filename = f"{uuid.uuid4()}{extension}"
+        file_path = os.path.join(UPLOAD_FOLDER, filename)
+        
+        with open(file_path, 'wb') as file:
+            file.write(response.content)
+        
+        print(f"File downloaded and saved as {file_path}")
+        return file_path
 
-def save_pdf_and_update_database(media_url):
-    response = requests.get(media_url)
-    pdf_filename = os.path.join(UPLOAD_FOLDER, f"{uuid.uuid4()}.pdf")
-    with open(pdf_filename, 'wb') as f:
-        f.write(response.content)
-    
-    document_loader = PyPDFDirectoryLoader(UPLOAD_FOLDER)
-    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)
-    
-    add_to_chroma(chunks)
+    except requests.exceptions.HTTPError as err:
+        print(f"HTTP error occurred: {err}")
+    except Exception as err:
+        print(f"An error occurred: {err}")
+        return None
+def save_pdf_and_update_database(pdf_filepath):
+    try:
+        document_loader = PyPDFDirectoryLoader(UPLOAD_FOLDER)
+        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)
+        
+        add_to_chroma(chunks)
+        print(f"PDF processed and data updated in Chroma.")
+    except Exception as e:
+        print(f"Error in processing PDF: {e}")
 
 def add_to_chroma(chunks: list[Document]):
-    db = Chroma(persist_directory=CHROMA_PATH, embedding_function=get_embedding_function())
-    chunks_with_ids = calculate_chunk_ids(chunks)
-    existing_items = db.get(include=[])
-    existing_ids = set(existing_items["ids"])
-
-    new_chunks = [chunk for chunk in chunks_with_ids if chunk.metadata["id"] not in existing_ids]
-
-    if new_chunks:
-        new_chunk_ids = [chunk.metadata["id"] for chunk in new_chunks]
-        db.add_documents(new_chunks, ids=new_chunk_ids)
-        db.persist()
-
+    try:
+        db = Chroma(persist_directory=CHROMA_PATH, embedding_function=get_embedding_function())
+        chunks_with_ids = calculate_chunk_ids(chunks)
+        existing_items = db.get(include=[])
+        existing_ids = set(existing_items["ids"])
+
+        new_chunks = [chunk for chunk in chunks_with_ids if chunk.metadata["id"] not in existing_ids]
+
+        if new_chunks:
+            new_chunk_ids = [chunk.metadata["id"] for chunk in new_chunks]
+            db.add_documents(new_chunks, ids=new_chunk_ids)
+            db.persist()
+            print(f"Chunks added to Chroma.")
+    except Exception as e:
+        print(f"Error adding chunks to Chroma: {e}")
 def calculate_chunk_ids(chunks):
     last_page_id = None
     current_chunk_index = 0
@@ -262,73 +281,68 @@ def calculate_chunk_ids(chunks):
 
     return chunks
 
-@app.route("/pdf", methods=["POST"])
-def receive_pdf():
-    media_url = request.values.get("MediaUrl", None)
-    if media_url:
-        save_pdf_and_update_database(media_url)
-        return "PDF processed and saved successfully."
-    return "No media URL found."
-
-@app.route("/whatsapp", methods=["POST"])
-def incoming_whatsapp():
-    media_url = request.values.get("MediaUrl", None)
-    from_number = request.values.get("From", "").strip()
-    from_number = from_number[2:] if from_number.startswith("91") else from_number
+
+@app.route('/whatsapp', methods=['POST'])
+def whatsapp_webhook():
     incoming_msg = request.values.get('Body', '').lower()
-    response = MessagingResponse()
-    message = response.message()
-
-    if media_url:
-        extension = os.path.splitext(media_url)[1]
-        if extension.lower() == ".pdf":
-            media_filepath = download_and_save_as_txt(media_url, account_sid, auth_token)
-            save_pdf_and_update_database(media_url)
-            message.body("The PDF was processed successfully.")
+    sender = request.values.get('From')
+    num_media = int(request.values.get('NumMedia', 0))
+
+    chat_history = conversation_memory.get_memory()
+
+    if num_media > 0:
+        media_url = request.values.get('MediaUrl0')
+        response_text = media_url
+        content_type = request.values.get('MediaContentType0')
+        if content_type.startswith('image/'):
+            filepath = convert_img(media_url, account_sid, auth_token)
+            try:
+                disease = predict_disease(filepath)
+            except:
+                disease = None
+            try:
+                pest = predict_pest(filepath)
+            except:
+                pest = None
+
+            if disease:
+                response_text = f"Detected disease: {disease}"
+                disease_info = generate_response(f"Provide brief information about {disease} in plants", chat_history)
+                response_text += f"\n\nAdditional information: {disease_info}"
+            elif pest:
+                response_text = f"Detected pest: {pest}"
+                pest_info = generate_response(f"Provide brief information about {pest} in agriculture", chat_history)
+                response_text += f"\n\nAdditional information: {pest_info}"
+            else:
+                response_text = "Please upload another image with good quality."
+
         else:
-            message.body("Please send a PDF file.")
-        return str(response)
-
-    if 'get weather for' in incoming_msg:
-        city = incoming_msg.replace("get weather for", "")
-        temperature = get_weather(city)
-        message.body(f'The temperature in {city} is {temperature}.')
-        return str(response)
-
-    if 'get rates' in incoming_msg:
-        message.body(get_rates())
-        return str(response)
-
-    if 'get news' in incoming_msg:
-        message.body(get_news())
-        return str(response)
-
-    if 'pest' in incoming_msg:
-        text = predict_pest(media_filepath)
-        message.body(text)
-        return str(response)
-
-    if 'disease' in incoming_msg:
-        text = predict_disease(media_filepath)
-        message.body(text)
-        return str(response)
-
-    if 'question:' in incoming_msg:
-        conversation_memory.add_to_memory(f"User: {incoming_msg}")
-        chat_history = "\n".join(conversation_memory.get_memory())
-        response_text = generate_response(incoming_msg.replace("question:", ""), chat_history)
-        conversation_memory.add_to_memory(f"Assistant: {response_text}")
-        message.body(response_text)
-        return str(response)
-
-    if 'query:' in incoming_msg:
-        query = incoming_msg.replace("query:", "").strip()
-        response_text = query_rag(query)
-        message.body(response_text)
-        return str(response)
-
-    message.body("I'm sorry, I don't understand that command.")
-    return str(response)
+            filepath = download_and_save_as_txt(media_url, account_sid, auth_token)
+            response_text = query_rag(filepath)
+    
+    elif ('weather' in incoming_msg.lower()) or ('climate' in incoming_msg.lower()) or (
+            'temperature' in incoming_msg.lower()):
+        response_text = get_weather(incoming_msg.lower())
+    elif 'bookkeeping' in incoming_msg:
+        response_text = "Please provide the details you'd like to record."
+    elif ('rates' in incoming_msg.lower()) or ('price' in incoming_msg.lower()) or (
+            'market' in incoming_msg.lower()) or ('rate' in incoming_msg.lower()) or ('prices' in incoming_msg.lower()):
+        rates = get_rates()
+        response_text = generate_response(incoming_msg + ' data is ' + rates, chat_history)
+    elif ('news' in incoming_msg.lower()) or ('information' in incoming_msg.lower()):
+        news = get_news()
+        response_text = generate_response(incoming_msg + ' data is ' + str(news), chat_history)
+    else:
+        # Check if the query is related to a PDF document
+        if 'from pdf' in incoming_msg or 'in pdf' in incoming_msg:
+            response_text = query_rag(incoming_msg)
+        else:
+            response_text = generate_response(incoming_msg, chat_history)
+
+    conversation_memory.add_to_memory({"user": incoming_msg, "assistant": response_text})
+    send_message(sender, response_text)
+    return '', 204
+
 
 def send_message(to, body):
     try: