Update app.py

app.py

@@ -1,23 +1,11 @@
 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 sentence_transformers import SentenceTransformer
-import csv
-import os
-import csv
-import os
-from datasets import Dataset, DatasetDict
-
-PERSIST_DIR = "history"  # Replace with your actual directory path
-CSV_FILE = os.path.join(PERSIST_DIR, "chat_history.csv")
-
-# Assuming current_chat_history is managed within a Dataset or DatasetDict
-current_chat_history = Dataset({"query": [], "response": []})
-
-
+from datasets import Dataset
 
 # Load environment variables
 load_dotenv()
@@ -36,29 +24,28 @@ Settings.embed_model = HuggingFaceEmbedding(
 )
 
 # Define the directory for persistent storage and data
-PERSIST_DIR = "db"
-PDF_DIRECTORY = 'data'  # Changed to the directory containing PDFs
+PERSIST_DIR = "history"  # Replace with your actual directory path
+CSV_FILE = os.path.join(PERSIST_DIR, "chat_history.csv")
 
 # 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 = []
+current_chat_history = Dataset.from_dict({"query": [], "response": []})
+
 
 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
 
-    # Ensure the directory exists or create it
-    os.makedirs(PERSIST_DIR, exist_ok=True)
-
     chat_text_qa_msgs = [
         (
             "user",
@@ -95,8 +82,7 @@ def handle_query(query):
         response = "Sorry, I couldn't find an answer."
 
     # Update current chat history
-    current_chat_history["query"].append(query)
-    current_chat_history["response"].append(response)
+    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:
@@ -105,14 +91,7 @@ def handle_query(query):
 
     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 = '''
@@ -167,9 +146,11 @@ 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(share=False)