Update app.py

app.py

@@ -8,6 +8,7 @@ import shutil
 import os
 import time
 
+
 icons = {"assistant": "robot.png", "user": "man-kddi.png"}
 
 # Configure the Llama index settings
@@ -16,6 +17,7 @@ Settings.llm = HuggingFaceInferenceAPI(
     tokenizer_name="meta-llama/Meta-Llama-3-8B-Instruct",
     context_window=3900,
     token=os.getenv("HF_TOKEN"),
+    # max_new_tokens=1000,
     generate_kwargs={"temperature": 0.1},
 )
 Settings.embed_model = HuggingFaceEmbedding(
@@ -37,20 +39,27 @@ def data_ingestion():
     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]
-        transcript_text = YouTubeTranscriptApi.get_transcript(video_id)
+        video_id=youtube_video_url.split("=")[1]
+        
+        transcript_text=YouTubeTranscriptApi.get_transcript(video_id)
 
         transcript = ""
         for i in transcript_text:
             transcript += " " + i["text"]
        
         return transcript
+
     except Exception as e:
         st.error(e)
 
@@ -58,20 +67,21 @@ 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 Q&A assistant named CHATTO, created by Pachaiappan [linkdin](https://www.linkedin.com/in/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 only say the user to 'Please ask a questions within the context of the document'.
-            Context:
-            {context_str}
-            Question:
-            {query_str}
-            """
-        )
+    (
+        "user",
+        """You are Q&A assistant named CHATTO, created by Pachaiappan [linkdin](https://www.linkedin.com/in/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 only say the user to 'Please ask a questions within the context of the document'.
+        Context:
+        {context_str}
+        Question:
+        {query_str}
+        """
+    )
     ]
     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)
     
+    
     if hasattr(answer, 'response'):
         return answer.response
     elif isinstance(answer, dict) and 'response' in answer:
@@ -84,6 +94,7 @@ def streamer(text):
         yield i
         time.sleep(0.001)
 
+
 # Streamlit app initialization
 st.title("Chat with your PDF📄")
 st.markdown("**Built by [Pachaiappan❤️](https://mr-vicky-01.github.io/Portfolio/)**")
@@ -101,7 +112,7 @@ with st.sidebar:
     video_url = st.text_input("Enter Youtube Video Link: ")
     if st.button("Submit & Process"):
         with st.spinner("Processing..."):
-            if len(os.listdir("data")) != 0:
+            if len(os.listdir("data")) !=0:
                 remove_old_files()
                 
             if uploaded_file:
@@ -128,4 +139,4 @@ if user_prompt and (uploaded_file or video_url):
     with st.spinner("Thinking..."):
         response = handle_query(user_prompt)
     with st.chat_message("user", avatar="robot.png"):
-        st.write_stream(streamer(response))
+        st.write_stream(streamer(response))