Update app.py

app.py

@@ -4,23 +4,23 @@ from llama_index.llms.huggingface import HuggingFaceInferenceAPI
 from dotenv import load_dotenv
 from llama_index.embeddings.huggingface import HuggingFaceEmbedding
 from llama_index.core import Settings
-import os
 from youtube_transcript_api import YouTubeTranscriptApi
-import time
 import shutil
+import os
+import time
 
 # Load environment variables
 load_dotenv()
 
-# icons = {"assistant": "robot.png", "user": "man-kddi.png"}
+icons = {"assistant": "robot.png", "user": "man-kddi.png"}
 
 # Configure the Llama index settings
 Settings.llm = HuggingFaceInferenceAPI(
     model_name="meta-llama/Meta-Llama-3-8B-Instruct",
     tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
-    context_window=3000,
+    context_window=3900,
     token=os.getenv("HF_TOKEN"),
-    max_new_tokens=512,
+    # max_new_tokens=1000,
     generate_kwargs={"temperature": 0.1},
 )
 Settings.embed_model = HuggingFaceEmbedding(
@@ -37,11 +37,20 @@ os.makedirs(PERSIST_DIR, exist_ok=True)
 
 def data_ingestion():
     documents = SimpleDirectoryReader(DATA_DIR).load_data()
-    print(documents)
     storage_context = StorageContext.from_defaults()
-    index = VectorStoreIndex.from_documents(documents,show_progress=True)
+    index = VectorStoreIndex.from_documents(documents)
     index.storage_context.persist(persist_dir=PERSIST_DIR)
 
+def remove_old_files():
+    # Specify the directory path you want to clear
+    directory_path = "data"
+
+    # Remove all files and subdirectories in the specified directory
+    shutil.rmtree(directory_path)
+
+    # Recreate an empty directory if needed
+    os.makedirs(directory_path)
+
 def extract_transcript_details(youtube_video_url):
     try:
         video_id=youtube_video_url.split("=")[1]
@@ -57,24 +66,13 @@ def extract_transcript_details(youtube_video_url):
     except Exception as e:
         st.error(e)
 
-def remove_old_files():
-    # Specify the directory path you want to clear
-    directory_path = "data"
-
-    # Remove all files and subdirectories in the specified directory
-    shutil.rmtree(directory_path)
-
-    # Recreate an empty directory if needed
-    os.makedirs(directory_path)
-
-
 def handle_query(query):
     storage_context = StorageContext.from_defaults(persist_dir=PERSIST_DIR)
     index = load_index_from_storage(storage_context)
     chat_text_qa_msgs = [
     (
         "user",
-        """You are a Q&A assistant named CHATTO, created by Suriya. You have a specific response programmed for when users specifically ask about your creator, Suriya. The response is: "I was created by Suriya, an enthusiast in Artificial Intelligence. He is dedicated to solving complex problems and delivering innovative solutions. With a strong focus on machine learning, deep learning, Python, generative AI, NLP, and computer vision, Suriya is passionate about pushing the boundaries of AI to explore new possibilities." For all other inquiries, your main goal is to provide answers as accurately as possible, based on the instructions and context you have been given. If a question does not match the provided context or is outside the scope of the document, kindly advise the user to ask questions within the context of the document.
+        """You are Q&A assistant named CHATTO, created by Pachaiappan an AI Specialist. Your main goal is to provide answers as accurately as possible, based on the instructions and context you have been given. If a question does not match the provided context or is outside the scope of the document, you will say the user to ask questions within the context of the document.
         Context:
         {context_str}
         Question:
@@ -83,37 +81,34 @@ def handle_query(query):
     )
     ]
     text_qa_template = ChatPromptTemplate.from_messages(chat_text_qa_msgs)
-    
     query_engine = index.as_query_engine(text_qa_template=text_qa_template)
     answer = query_engine.query(query)
-
-    final_ans = []
+    
+    
     if hasattr(answer, 'response'):
-        final_ans.append(answer.response)
+        return answer.response
     elif isinstance(answer, dict) and 'response' in answer:
-        final_ans.append(answer['response'])
+        return answer['response']
     else:
-        final_ans.append("Sorry, I couldn't find an answer.")
+        return "Sorry, I couldn't find an answer."
 
-    ans = " ".join(final_ans)
-    for i in ans:
-        yield str(i)
+def streamer(text):
+    for i in text:
+        yield i
         time.sleep(0.001)
 
 
 # Streamlit app initialization
 st.title("Chat with your PDF📄")
-st.markdown("Built by [Suriya❤️](https://github.com/theSuriya)")
-st.markdown("chat here👇")
+st.markdown("**Built by [Pachaiappan❤️](https://github.com/Mr-Vicky-01)**")
 
 if 'messages' not in st.session_state:
-    st.session_state.messages = [{'role': 'assistant', "content": 'Hello! Upload a PDF and ask me anything about its content.'}]
-    
-# Display or clear chat messages
+    st.session_state.messages = [{'role': 'assistant', "content": 'Hello! Upload a PDF and ask me anything about the content.'}]
+
 for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.write(message["content"])
-        
+    with st.chat_message(message['role'], avatar=icons[message['role']]):
+        st.write(message['content'])
+
 with st.sidebar:
     st.title("Menu:")
     uploaded_file = st.file_uploader("Upload your PDF Files and Click on the Submit & Process Button")
@@ -137,15 +132,15 @@ with st.sidebar:
             st.success("Done")
 
 user_prompt = st.chat_input("Ask me anything about the content of the PDF:")
-if user_prompt and (uploaded_file or video_url):
+
+if user_prompt and uploaded_file:
     st.session_state.messages.append({'role': 'user', "content": user_prompt})
-    with st.chat_message("user"):
+    with st.chat_message("user", avatar="man-kddi.png"):
         st.write(user_prompt)
 
-# Generate a new response if last message is not from assistant
-if st.session_state.messages[-1]["role"] != "assistant":
-    with st.chat_message("assistant"):
+    # Trigger assistant's response retrieval and update UI
+    with st.spinner("Thinking..."):
         response = handle_query(user_prompt)
-        full_response = st.write_stream(response)
-    message = {"role": "assistant", "content": full_response}
-    st.session_state.messages.append(message)
+    with st.chat_message("user", avatar="robot.png"):
+        st.write_stream(streamer(response))
+    st.session_state.messages.append({'role': 'assistant', "content": response})