Update app.py

app.py

@@ -1,16 +1,18 @@
 import os
 from dotenv import load_dotenv
 import gradio as gr
-from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate
+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
-from llama_index.core import StorageContext, load_index_from_storage, VectorStoreIndex, SimpleDirectoryReader, ChatPromptTemplate, Settings
+
+# Load environment variables
 load_dotenv()
+
 # Configure the Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
-    model_name="google/gemma-1.1-7b-it",
-    tokenizer_name="google/gemma-1.1-7b-it",
+    model_name="meta-llama/Meta-Llama-3-8B-Instruct",
+    tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
     context_window=3000,
     token=os.getenv("HF_TOKEN"),
     max_new_tokens=512,
@@ -24,10 +26,13 @@ Settings.embed_model = HuggingFaceEmbedding(
 PERSIST_DIR = "db"
 PDF_DIRECTORY = 'data'  # Changed to the directory containing PDFs
 
-# Ensure PDF directory exists
+# 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 = []
+
 def data_ingestion_from_directory():
     # Use SimpleDirectoryReader on the directory containing the PDF files
     documents = SimpleDirectoryReader(PDF_DIRECTORY).load_data()
@@ -40,21 +45,7 @@ def handle_query(query):
         (
             "user",
             """
-            Provide the best user experience by delivering accurate and professional responses to user inquiries. Ensure all interactions reflect the professionalism and expertise of RedfernsTech.
-           Guidelines:
-           Professional Tone:
-           Always maintain a polite, professional, and helpful tone.
-           Use clear and concise language.
-          Single Best Answer:
-         Provide only one comprehensive and accurate answer to each question.
-         Ensure the response is detailed enough to address the user’s inquiry fully.
-         Redirect Personal Questions:
-           If users ask personal questions about the chatbot, redirect them to ask about the company.
-         Example: "For more information about RedfernsTech, please ask me specific questions about our products or services."
-             Company-Centric Responses:
-          Focus on delivering information relevant to RedfernsTech’s products, services, and values.
-            Highlight the benefits and features of RedfernsTech offerings whenever possible.
-            Context:
+            You are now the RedFerns Tech chatbot. Your aim is to provide answers to the user based on the conversation flow only.
             {context_str}
             Question:
             {query_str}
@@ -67,31 +58,31 @@ def handle_query(query):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
     index = load_index_from_storage(storage_context)
 
-    query_engine = index.as_query_engine(text_qa_template=text_qa_template)
+    # Use chat history to enhance response
+    context_str = ""
+    for past_query, response in reversed(current_chat_history):
+        if past_query.strip():
+            context_str += f"User asked: '{past_query}'\nBot answered: '{response}'\n"
+
+    query_engine = index.as_query_engine(text_qa_template=text_qa_template, context_str=context_str)
     answer = query_engine.query(query)
 
     if hasattr(answer, 'response'):
-        return answer.response
+        response = answer.response
     elif isinstance(answer, dict) and 'response' in answer:
-        return answer['response']
+        response = answer['response']
     else:
-        return "Sorry, I couldn't find an answer."
+        response = "Sorry, I couldn't find an answer."
 
-# Example usage
+    # Update current chat history
+    current_chat_history.append((query, response))
 
-    # Process PDF ingestion from directory
+    return response
+
+# Example usage: Process PDF ingestion from directory
 print("Processing PDF ingestion from directory:", PDF_DIRECTORY)
 data_ingestion_from_directory()
 
-    # Example query
-query = "How do I use the RedfernsTech Q&A assistant?"
-print("Query:", query)
-response = handle_query(query)
-print("Answer:", response)
-# prompt: create a gradio chatbot for this
-
-
-
 # Define the input and output components for the Gradio interface
 input_component = gr.Textbox(
     show_label=False,
@@ -100,9 +91,14 @@ input_component = gr.Textbox(
 
 output_component = gr.Textbox()
 
+# Function to handle queries
+def chatbot_handler(query):
+    response = handle_query(query)
+    return response
+
 # Create the Gradio interface
 interface = gr.Interface(
-    fn=handle_query,
+    fn=chatbot_handler,
     inputs=input_component,
     outputs=output_component,
     title="RedfernsTech Q&A Chatbot",