Update app.py

app.py

@@ -10,11 +10,15 @@ from langchain.vectorstores.chroma import Chroma
 from langchain.prompts import ChatPromptTemplate
 from langchain_community.llms.ollama import Ollama
 from get_embedding_function import get_embedding_function
-from langchain.document_loaders import PyPDFDirectoryLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.schema import Document
+from langchain.document_loaders.pdf import PyPDFDirectoryLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain.schema.document import Document
 import tempfile
 
+# Create a temporary directory for Chroma if running in Hugging Face Spaces
+
+
+
 app = Flask(__name__)
 UPLOAD_FOLDER = '/code/uploads'
 CHROMA_PATH = tempfile.mkdtemp()  # Use the same folder for Chroma
@@ -50,6 +54,21 @@ Answer the question based only on the following context:
 Answer the question based on the above context: {question}
 """
 
+from bs4 import BeautifulSoup
+import requests
+from requests.auth import HTTPBasicAuth
+from PIL import Image
+from io import BytesIO
+import pandas as pd
+from urllib.parse import urlparse
+import os
+from pypdf import PdfReader
+from ai71 import AI71
+import uuid
+
+from inference_sdk import InferenceHTTPClient
+import base64
+
 AI71_API_KEY = os.environ.get('AI71_API_KEY')
 
 def generate_response(query, chat_history):
@@ -66,6 +85,23 @@ def generate_response(query, chat_history):
             response += chunk.choices[0].delta.content
     return response.replace("###", '').replace('\nUser:', '')
 
+def predict_pest(filepath):
+    CLIENT = InferenceHTTPClient(
+        api_url="https://detect.roboflow.com",
+        api_key="oF1aC4b1FBCDtK8CoKx7"
+    )
+    result = CLIENT.infer(filepath, model_id="pest-detection-ueoco/1")
+    return result['predictions'][0]
+    
+
+def predict_disease(filepath):
+    CLIENT = InferenceHTTPClient(
+        api_url="https://classify.roboflow.com",
+        api_key="oF1aC4b1FBCDtK8CoKx7"
+    )
+    result = CLIENT.infer(filepath, model_id="plant-disease-detection-iefbi/1")
+    return result['predicted_classes'][0]
+
 def convert_img(url, account_sid, auth_token):
     try:
         response = requests.get(url, auth=HTTPBasicAuth(account_sid, auth_token))
@@ -101,6 +137,40 @@ def get_weather(city):
     temperature = soup.find('div', attrs={'class': 'BNeawe iBp4i AP7Wnd'}).text
     return temperature
 
+from zenrows import ZenRowsClient
+Zenrow_api = os.environ.get('Zenrow_api')
+zenrows_client = ZenRowsClient(Zenrow_api)
+
+def get_rates():
+    url = "https://www.kisandeals.com/mandiprices/ALL/TAMIL-NADU/ALL"
+    response = zenrows_client.get(url)
+
+    if response.status_code == 200:
+        soup = BeautifulSoup(response.content, 'html.parser')
+        rows = soup.select('table tbody tr')
+        data = {}
+        for row in rows:
+            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) + " These are the prices for 1 kg"
+
+def get_news():
+    news = []
+    url = "https://economictimes.indiatimes.com/news/economy/agriculture?from=mdr"
+    response = zenrows_client.get(url)
+
+    if response.status_code == 200:
+        soup = BeautifulSoup(response.content, 'html.parser')
+        headlines = soup.find_all("div", class_="eachStory")
+        for story in headlines:
+            headline = story.find('h3').text.strip()
+            news.append(headline)
+    return news
+
 def download_and_save_as_txt(url, account_sid, auth_token):
     try:
         response = requests.get(url, auth=HTTPBasicAuth(account_sid, auth_token))
@@ -138,7 +208,15 @@ initialize_chroma()
 def query_rag(query_text: str):
     embedding_function = get_embedding_function()
     db = Chroma(persist_directory=CHROMA_PATH, embedding_function=embedding_function)
-    
+    print(query_text)
+    # Check if the query is related to a PDF
+    if "from pdf" in query_text.lower() or "in pdf" in query_text.lower():
+        # Provide some context about handling PDFs
+        response_text = "I see you're asking about a PDF-related query. Let me check the context from the PDF."
+    else:
+        # Regular RAG functionality
+        response_text = "Your query is not related to PDFs. Please make sure your question is clear."
+
     results = db.similarity_search_with_score(query_text, k=5)
     
     if not results:
@@ -163,11 +241,28 @@ def query_rag(query_text: str):
         response_text = response.replace("###", '').replace('\nUser:', '')
 
     return response_text
+    
+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
 
+    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:
-        # Assuming you're loading PDFs from a specific directory
-        document_loader = PyPDFDirectoryLoader(os.path.dirname(pdf_filepath))
+        document_loader = PyPDFDirectoryLoader(UPLOAD_FOLDER)
         documents = document_loader.load()
         
         text_splitter = RecursiveCharacterTextSplitter(
@@ -183,6 +278,10 @@ def save_pdf_and_update_database(pdf_filepath):
     except Exception as e:
         print(f"Error in processing PDF: {e}")
 
+def load_documents():
+    document_loader = PyPDFDirectoryLoader(DATA_PATH)
+    return document_loader.load()
+
 def add_to_chroma(chunks: list[Document]):
     try:
         db = Chroma(persist_directory=CHROMA_PATH, embedding_function=get_embedding_function())
@@ -199,7 +298,6 @@ def add_to_chroma(chunks: list[Document]):
             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
@@ -220,6 +318,7 @@ def calculate_chunk_ids(chunks):
 
     return chunks
 
+
 @app.route('/whatsapp', methods=['POST'])
 def whatsapp_webhook():
     incoming_msg = request.values.get('Body', '').lower()
@@ -236,30 +335,58 @@ def whatsapp_webhook():
             # Handle image processing (disease/pest detection)
             filepath = convert_img(media_url, account_sid, auth_token)
             response_text = handle_image(filepath)
-        elif content_type == 'application/pdf':
+        else:
             # Handle PDF processing
             filepath = download_and_save_as_txt(media_url, account_sid, auth_token)
-            save_pdf_and_update_database(filepath)
-            response_text = "PDF received and processed."
-        else:
-            response_text = "Unsupported media type. Please send a PDF or image file."
-    elif "weather" in incoming_msg:
-        city = incoming_msg.replace("weather", "").strip()
-        temperature = get_weather(city)
-        response_text = f"The current temperature in {city} is {temperature}"
+            response_text = process_and_query_pdf(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:
-        # Generate response using the question and chat history
         response_text = query_rag(incoming_msg)
 
-    # Add interaction to memory
-    interaction = {'role': 'user', 'content': incoming_msg, 'response': response_text}
-    conversation_memory.add_to_memory(interaction)
+    conversation_memory.add_to_memory({"user": incoming_msg, "assistant": response_text})
+    send_message(sender, response_text)
+    return '', 204
+
+def handle_image(filepath):
+    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."
+    
+    return response_text
+
+def process_and_query_pdf(filepath):
+    # Assuming the PDF processing and embedding are handled here.
+    add_to_chroma(load_documents())
+    return query_rag("from pdf")  # Replace with a more specific query if needed
+
 
-    # Send the response
-    resp = MessagingResponse()
-    msg = resp.message()
-    msg.body(response_text)
-    return str(resp)
 def send_message(to, body):
     try:
         message = client.messages.create(
@@ -270,6 +397,7 @@ 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}',
@@ -278,4 +406,4 @@ def send_initial_message(to_number):
 if __name__ == "__main__":
     send_initial_message('919080522395')
     send_initial_message('916382792828')
-    app.run(host='0.0.0.0', port=7860)
+    app.run(host='0.0.0.0', port=7860)