Update app.py

app.py

@@ -1,15 +1,19 @@
 from dotenv import load_dotenv
 import gradio as gr
 import os
-import csv
 from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate, Settings
 from llama_index.llms.huggingface import HuggingFaceInferenceAPI
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
-from datasets import Dataset
-
+from sentence_transformers import SentenceTransformer
+import firebase_admin
+from firebase_admin import db, credentials
+import datetime
+import uuid
 # Load environment variables
 load_dotenv()
-
+# authenticate to firebase
+cred = credentials.Certificate("redfernstech-fd8fe-firebase-adminsdk-g9vcn-0537b4efd6.json")
+firebase_admin.initialize_app(cred, {"databaseURL": "https://redfernstech-fd8fe-default-rtdb.firebaseio.com/"})
 # Configure the Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
     model_name="meta-llama/Meta-Llama-3-8B-Instruct",
@@ -24,28 +28,24 @@ Settings.embed_model = HuggingFaceEmbedding(
 )
 
 # Define the directory for persistent storage and data
-PERSIST_DIR = "history"  # Replace with your actual directory path
-CSV_FILE = os.path.join(PERSIST_DIR, "chat_history.csv")
+PERSIST_DIR = "db"
+PDF_DIRECTORY = 'data'  # Changed to the directory containing PDFs
 
 # Ensure directories exist
+os.makedirs(PDF_DIRECTORY, exist_ok=True)
 os.makedirs(PERSIST_DIR, exist_ok=True)
 
 # Variable to store current chat conversation
-current_chat_history = Dataset.from_dict({"query": [], "response": []})
-
+current_chat_history = []
 
 def data_ingestion_from_directory():
     # Use SimpleDirectoryReader on the directory containing the PDF files
-    PDF_DIRECTORY = 'data'  # Replace with the directory containing your PDFs
     documents = SimpleDirectoryReader(PDF_DIRECTORY).load_data()
     storage_context = StorageContext.from_defaults()
     index = VectorStoreIndex.from_documents(documents)
     index.storage_context.persist(persist_dir=PERSIST_DIR)
 
-
 def handle_query(query):
-    global current_chat_history
-
     chat_text_qa_msgs = [
         (
             "user",
@@ -67,7 +67,7 @@ def handle_query(query):
 
     # Use chat history to enhance response
     context_str = ""
-    for past_query, response in reversed(current_chat_history["query"]):
+    for past_query, response in reversed(current_chat_history):
         if past_query.strip():
             context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"
 
@@ -82,40 +82,55 @@ def handle_query(query):
         response = "Sorry, I couldn't find an answer."
 
     # Update current chat history
-    current_chat_history = current_chat_history.concat(Dataset.from_dict({"query": [query], "response": [response]}))
-
-    # Save chat history to CSV
-    with open(CSV_FILE, 'a', newline='', encoding='utf-8') as file:
-        csv_writer = csv.writer(file)
-        csv_writer.writerow([query, response])
+    current_chat_history.append((query, response))
 
     return response
 
+# Example usage: Process PDF ingestion from directory
+print("Processing PDF ingestion from directory:", PDF_DIRECTORY)
+data_ingestion_from_directory()
 
+# Define the function to handle predictions
+"""def predict(message,history):
+    response = handle_query(message)
+    return response"""
 def predict(message, history):
-    # Your logo HTML code
     logo_html = '''
     <div class="circle-logo">
       <img src="https://rb.gy/8r06eg" alt="FernAi">
     </div>
     '''
-    
-    # Assuming handle_query function handles the message and returns a response
     response = handle_query(message)
-    
-    # Prepare the response with logo HTML
     response_with_logo = f'<div class="response-with-logo">{logo_html}<div class="response-text">{response}</div></div>'
-    
-    # Convert history to a string (if it's a list)
-    if isinstance(history, list):
-        history = ' '.join(map(str, history))
-    
-    # Save history to kk.txt
-    with open('kk.txt', 'a') as file:
-        file.write(history + '\n')
-    
     return response_with_logo
-
+def save_chat_message(session_id, message_data):
+    ref = db.reference(f'/chat_history/{session_id}')  # Use the session ID to save chat data
+    ref.push().set(message_data)
+
+# Define your Gradio chat interface function (replace with your actual logic)
+def chat_interface(message, history):
+    try:
+        # Generate a unique session ID for this chat session
+        session_id = str(uuid.uuid4())
+
+        # Process the user message and generate a response (your chatbot logic)
+        response = handle_query(message)
+
+        # Capture the message data
+        message_data = {
+            "sender": "user",
+            "message": message,
+            "response": response,
+            "timestamp": datetime.datetime.now().isoformat()  # Use a library like datetime
+        }
+
+        # Call the save function to store in Firebase with the generated session ID
+        save_chat_message(session_id, message_data)
+
+        # Return the bot response
+        return response
+    except Exception as e:
+        return str(e)
 
 # Custom CSS for styling
 css = '''
@@ -128,13 +143,11 @@ css = '''
   margin-right: 10px;
   vertical-align: middle;
 }
-
 .circle-logo img {
   width: 100%;
   height: 100%;
   object-fit: cover;
 }
-
 .response-with-logo {
   display: flex;
   align-items: center;
@@ -146,11 +159,9 @@ footer {
   }
 label.svelte-1b6s6s {display: none}
 '''
-
-# Launch Gradio interface
 gr.ChatInterface(predict,
                  css=css,
                  description="FernAI",
                  clear_btn=None, undo_btn=None, retry_btn=None,
                  examples=['Tell me about Redfernstech?', 'Services in Redfernstech?']
-                 ).launch(share=False)
+                 ).launch()