Update app.py

app.py

@@ -6,22 +6,23 @@ import requests
 from PIL import Image
 import shutil
 
-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.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
-
+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
 
 app = Flask(__name__)
 UPLOAD_FOLDER = '/code/uploads'
-CHROMA_PATH = tempfile.mkdtemp()  # Use the same folder for Chroma
 if not os.path.exists(UPLOAD_FOLDER):
     os.makedirs(UPLOAD_FOLDER)
 
@@ -54,21 +55,6 @@ 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):
@@ -192,56 +178,6 @@ def download_and_save_as_txt(url, account_sid, auth_token):
     except Exception as err:
         print(f"An error occurred: {err}")
 
-
-def initialize_chroma():
-    try:
-        # Initialize Chroma
-        db = Chroma(persist_directory=CHROMA_PATH, embedding_function=get_embedding_function())
-        # Perform an initial operation to ensure it works
-        db.similarity_search_with_score("test query", k=1)
-        print("Chroma initialized successfully.")
-    except Exception as e:
-        print(f"Error initializing Chroma: {e}")
-
-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:
-        response_text = "Sorry, I couldn't find any relevant information."
-    else:
-        context_text = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
-        prompt_template = ChatPromptTemplate.from_template(PROMPT_TEMPLATE)
-        prompt = prompt_template.format(context=context_text, question=query_text)
-        
-        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 following query based on the given context: {prompt}'''},
-                ],
-                stream=True,
-        ):
-            if chunk.choices[0].delta.content:
-                response += chunk.choices[0].delta.content
-
-        response_text = response.replace("###", '').replace('\nUser:', '')
-
-    return response_text
-    
 def download_file(url, extension):
     try:
         response = requests.get(url)
@@ -260,64 +196,6 @@ def download_file(url, extension):
     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 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())
-        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
-
-    for chunk in chunks:
-        source = chunk.metadata.get("source")
-        page = chunk.metadata.get("page")
-        current_page_id = f"{source}:{page}"
-
-        if current_page_id == last_page_id:
-            current_chunk_index += 1
-        else:
-            current_chunk_index = 0
-
-        last_page_id = current_page_id
-        chunk_id = f"{current_page_id}:{current_chunk_index}"
-        chunk.metadata["id"] = chunk_id
-
-    return chunks
-
 
 @app.route('/whatsapp', methods=['POST'])
 def whatsapp_webhook():
@@ -352,7 +230,7 @@ def whatsapp_webhook():
         news = get_news()
         response_text = generate_response(incoming_msg + ' data is ' + str(news), chat_history)
     else:
-        response_text = query_rag(incoming_msg)
+        response_text = generate_response(incoming_msg, chat_history)
 
     conversation_memory.add_to_memory({"user": incoming_msg, "assistant": response_text})
     send_message(sender, response_text)
@@ -370,34 +248,37 @@ def handle_image(filepath):
 
     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}"
+        disease_info = generate_response(f"Provide brief information about {disease} in agriculture", "")
+        response_text += "\n" + 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}"
+        pest_info = generate_response(f"Provide brief information about {pest} in agriculture", "")
+        response_text += "\n" + pest_info
     else:
-        response_text = "Please upload another image with good quality."
-    
+        response_text = "Sorry, I couldn't detect any disease or pest. Please try another image."
+
     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
-
+    # Read and process the PDF
+    reader = PdfReader(filepath)
+    text = ''
+    for page in reader.pages:
+        text += page.extract_text()
+
+    if not text:
+        return "Sorry, the PDF content could not be extracted."
+    
+    # Generate response based on extracted PDF content
+    response_text = generate_response(f"The PDF content is {text}", "")
+    return response_text
 
-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_message(recipient, message):
+    client.messages.create(
+        body=message,
+        from_=from_whatsapp_number,
+        to=recipient
+    )
 def send_initial_message(to_number):
     send_message(
         f'whatsapp:{to_number}',