Update app.py

app.py

@@ -16,12 +16,11 @@ from langchain.schema.document import Document
 
 app = Flask(__name__)
 UPLOAD_FOLDER = '/code/uploads'
-if not os.path.exists(UPLOAD_FOLDER):
-    os.makedirs(UPLOAD_FOLDER) # Creates an 'uploads' directory in the current working directory
-
 if not os.path.exists(UPLOAD_FOLDER):
     os.makedirs(UPLOAD_FOLDER)
+
 app.config['UPLOAD_FOLDER'] = UPLOAD_FOLDER
+
 class ConversationBufferMemory:
     def __init__(self, max_size=6):
         self.memory = []
@@ -30,10 +29,11 @@ class ConversationBufferMemory:
     def add_to_memory(self, interaction):
         self.memory.append(interaction)
         if len(self.memory) > self.max_size:
-            self.memory.pop(0)  # Remove the oldest interaction
+            self.memory.pop(0)
 
     def get_memory(self):
         return self.memory
+
 conversation_memory = ConversationBufferMemory(max_size=2)
 
 account_sid = os.environ.get('TWILIO_ACCOUNT_SID')
@@ -45,15 +45,11 @@ CHROMA_PATH = "chroma"
 DATA_PATH = "data"
 PROMPT_TEMPLATE = """
 Answer the question based only on the following context:
-
 {context}
-
 ---
-
 Answer the question based on the above context: {question}
 """
 
-import os
 from bs4 import BeautifulSoup
 import requests
 from requests.auth import HTTPBasicAuth
@@ -64,30 +60,26 @@ from urllib.parse import urlparse
 import os
 from pypdf import PdfReader
 from ai71 import AI71
-import os
-
-import pandas as pd
+import uuid
 
 from inference_sdk import InferenceHTTPClient
 import base64
 
-
-
 AI71_API_KEY = os.environ.get('AI71_API_KEY')
-def generate_response(query,chat_history):
+
+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 a best agricultural assistant.Remember to give response not more than 2 sentence.Greet the user if user greets you."},
-                {"role": "user",
-                 "content": f'''Answer the query based on history {chat_history}:{query}'''},
+                {"role": "system", "content": "You are the best agricultural assistant. Remember to give a response in not more than 2 sentences. Greet the user if the user greets you."},
+                {"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:','')
+    return response.replace("###", '').replace('\nUser:', '')
 
 def predict_pest(filepath):
     CLIENT = InferenceHTTPClient(
@@ -108,27 +100,22 @@ def predict_disease(filepath):
 
 def convert_img(url, account_sid, auth_token):
     try:
-        # Make the request to the media URL with authentication
         response = requests.get(url, auth=HTTPBasicAuth(account_sid, auth_token))
-        response.raise_for_status()  # Raise an error for bad responses
+        response.raise_for_status()
 
-        # Determine a filename from the URL
         parsed_url = urlparse(url)
-        media_id = parsed_url.path.split('/')[-1]  # Get the last part of the URL path
+        media_id = parsed_url.path.split('/')[-1]
         filename = f"downloaded_media_{media_id}"
 
-        # Save the media content to a file
         media_filepath = os.path.join(UPLOAD_FOLDER, filename)
         with open(media_filepath, 'wb') as file:
             file.write(response.content)
         
         print(f"Media downloaded successfully and saved as {media_filepath}")
 
-        # Convert the saved media file to an image
         with open(media_filepath, 'rb') as img_file:
             image = Image.open(img_file)
 
-            # Optionally, convert the image to JPG and save in UPLOAD_FOLDER
             converted_filename = f"image.jpg"
             converted_filepath = os.path.join(UPLOAD_FOLDER, converted_filename)
             image.convert('RGB').save(converted_filepath, 'JPEG')
@@ -138,84 +125,57 @@ def convert_img(url, account_sid, auth_token):
         print(f"HTTP error occurred: {err}")
     except Exception as err:
         print(f"An error occurred: {err}")
-def get_weather(city):
-  city=city.strip()
-  city=city.replace(' ',"+")
-  r = requests.get(f'https://www.google.com/search?q=weather+in+{city}')
-
-  soup=BeautifulSoup(r.text,'html.parser')
-  temperature=soup.find('div',attrs={'class':'BNeawe iBp4i AP7Wnd'}).text
-  
-  return (temperature)
 
+def get_weather(city):
+    city = city.strip().replace(' ', '+')
+    r = requests.get(f'https://www.google.com/search?q=weather+in+{city}')
+    soup = BeautifulSoup(r.text, 'html.parser')
+    temperature = soup.find('div', attrs={'class': 'BNeawe iBp4i AP7Wnd'}).text
+    return temperature
 
 from zenrows import ZenRowsClient
-from bs4 import BeautifulSoup
-Zenrow_api=os.environ.get('Zenrow_api')
-# Initialize ZenRows client with your API key
-client = ZenRowsClient(str(Zenrow_api))
+Zenrow_api = os.environ.get('Zenrow_api')
+zenrows_client = ZenRowsClient(Zenrow_api)
 
-def get_rates():    # URL to scrape
+def get_rates():
     url = "https://www.kisandeals.com/mandiprices/ALL/TAMIL-NADU/ALL"
+    response = zenrows_client.get(url)
 
-    # Fetch the webpage content using ZenRows
-    response = client.get(url)
-
-    # Check if the request was successful
     if response.status_code == 200:
-        # Parse the raw HTML content with BeautifulSoup
         soup = BeautifulSoup(response.content, 'html.parser')
-
-        # Find the table rows containing the data
         rows = soup.select('table tbody tr')
         data = {}
         for row in rows:
-            # Extract commodity and price using BeautifulSoup
             columns = row.find_all('td')
             if len(columns) >= 2:
                 commodity = columns[0].get_text(strip=True)
                 price = columns[1].get_text(strip=True)
                 if '₹' in price:
                     data[commodity] = price
-    return str(data)+" This are the prices for 1 kg"
-
-
+    return str(data) + " These are the prices for 1 kg"
 
-
-def get_news(): 
-    news=[]   # URL to scrape
+def get_news():
+    news = []
     url = "https://economictimes.indiatimes.com/news/economy/agriculture?from=mdr"
+    response = zenrows_client.get(url)
 
-    # Fetch the webpage content using ZenRows
-    response = client.get(url)
-
-    # Check if the request was successful
     if response.status_code == 200:
-        # Parse the raw HTML content with BeautifulSoup
         soup = BeautifulSoup(response.content, 'html.parser')
-
-        # Find the table rows containing the data
         headlines = soup.find_all("div", class_="eachStory")
         for story in headlines:
-    # Extract the headline
             headline = story.find('h3').text.strip()
             news.append(headline)
     return news
 
-
-
 def download_and_save_as_txt(url, account_sid, auth_token):
     try:
-        # Make the request to the media URL with authentication
         response = requests.get(url, auth=HTTPBasicAuth(account_sid, auth_token))
-        response.raise_for_status()  # Raise an error for bad responses
+        response.raise_for_status()
 
-        # Determine a filename from the URL
         parsed_url = urlparse(url)
-        media_id = parsed_url.path.split('/')[-1]  # Get the last part of the URL path
+        media_id = parsed_url.path.split('/')[-1]
         filename = f"pdf_file.pdf"
 
-        # Save the media content to a .txt file
         txt_filepath = os.path.join(UPLOAD_FOLDER, filename)
         with open(txt_filepath, 'wb') as file:
             file.write(response.content)
@@ -227,6 +187,7 @@ def download_and_save_as_txt(url, account_sid, auth_token):
         print(f"HTTP error occurred: {err}")
     except Exception as err:
         print(f"An error occurred: {err}")
+
 def query_rag(query_text: str):
     embedding_function = get_embedding_function()
     db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
@@ -238,19 +199,15 @@ def query_rag(query_text: str):
     response_text = model.invoke(prompt)
     return response_text
 
-
 def save_pdf_and_update_database(media_url):
-    # Download the PDF file
     response = requests.get(media_url)
     pdf_filename = os.path.join(DATA_PATH, f"{uuid.uuid4()}.pdf")
     with open(pdf_filename, 'wb') as f:
         f.write(response.content)
     
-    # Use PyPDFDirectoryLoader if you want to process multiple PDFs in a directory
     document_loader = PyPDFDirectoryLoader(DATA_PATH)
     documents = document_loader.load()
     
-    # The rest of your code remains the same
     text_splitter = RecursiveCharacterTextSplitter(
         chunk_size=800,
         chunk_overlap=80,
@@ -261,11 +218,8 @@ def save_pdf_and_update_database(media_url):
     
     add_to_chroma(chunks)
 
-
 def add_to_chroma(chunks: list[Document]):
-    db = Chroma(
-        persist_directory=CHROMA_PATH, embedding_function=get_embedding_function()
-    )
+    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"])
@@ -277,7 +231,6 @@ def add_to_chroma(chunks: list[Document]):
         db.add_documents(new_chunks, ids=new_chunk_ids)
         db.persist()
 
-
 def calculate_chunk_ids(chunks):
     last_page_id = None
     current_chunk_index = 0
@@ -299,7 +252,6 @@ def calculate_chunk_ids(chunks):
 
     return chunks
 
-
 @app.route('/whatsapp', methods=['POST'])
 def whatsapp_webhook():
     incoming_msg = request.values.get('Body', '').lower()
@@ -334,7 +286,6 @@ def whatsapp_webhook():
             else:
                 response_text = "Please upload another image with good quality."
         elif content_type == "application/pdf":
-            # Process the PDF and update the database
             save_pdf_and_update_database(media_url)
             response_text = "Your PDF has been saved and processed."
         else:
@@ -359,7 +310,6 @@ def whatsapp_webhook():
     send_message(sender, response_text)
     return '', 204
 
-
 def send_message(to, body):
     try:
         message = client.messages.create(
@@ -381,8 +331,6 @@ def send_initial_message(to_number):
         'Welcome to the Agri AI Chatbot! How can I assist you today?'
     )
 
-
 if __name__ == '__main__':
-    #send_initial_message('916382792828')
     send_initial_message('919080522395')
     app.run(host='0.0.0.0', port=7860)