Rename apptbc.py to app3.py

apptbc.py → app3.py

@@ -1,8 +1,6 @@
 # -*- coding: utf-8 -*-
 """app
-
 Automatically generated by Colab.
-
 Original file is located at
     https://colab.research.google.com/drive/1pwwcBb5Zlw1DA3u5K8W8mjrwBTBWXc1L
 """
@@ -15,13 +13,35 @@ import time
 import groq
 import uuid  # For generating unique filenames
 
-# Updated imports to address LangChain deprecation warnings:
-from langchain_groq import ChatGroq
-from langchain.schema import HumanMessage
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.vectorstores import Chroma
+# OLD Updated imports to address LangChain deprecation warnings:
+#from langchain_groq import ChatGroq
+#*from langchain.schema import HumanMessage
+#from langchain_core.messages import HumanMessage
+#*from langchain_text_splitters import RecursiveCharacterTextSplitter
+#try:
+    # For newer versions
+#    from langchain_text_splitters import RecursiveCharacterTextSplitter
+#except ImportError:
+    # For older versions
+#    from langchain.text_splitter import RecursiveCharacterTextSplitter
+#from langchain_community.vectorstores import Chroma
+#from langchain_community.embeddings import HuggingFaceEmbeddings
+#*from langchain.docstore.document import Document
+#from langchain_core.documents import Document
+#from langchain.chains import RetrievalQA  # This one might still be in main langchain
+
+
+# NEW IMPORTS (current):
+from langchain_core.messages import HumanMessage, SystemMessage, AIMessage
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_core.documents import Document
+from langchain_community.document_loaders import TextLoader, PyPDFLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings
-from langchain.docstore.document import Document
+from langchain_community.llms import HuggingFaceHub
+#from langchain_community.chains import RetrievalQA
+#from langchain.chains.retrieval_qa.base import RetrievalQA   # This one might still be in main langchain
+from langchain_community.vectorstores import Chroma #from old library
+from langchain_groq import ChatGroq
 
 # Importing chardet (make sure to add chardet to your requirements.txt)
 import chardet
@@ -68,33 +88,24 @@ For each question:
     - Ensure responses are concise and educational to enhance understanding.
 Output Example:
 1. Fill in the blank: The LLM Agent framework has a central decision-making unit called the _______________________.
-
 Answer: Agent Core
-
 Feedback: The Agent Core is the central component of the LLM Agent framework, responsible for managing goals, tool instructions, planning modules, memory integration, and agent persona.
-
 2. What is the main limitation of LLM-based applications?
 a) Limited token capacity
 b) Lack of domain expertise
 c) Prone to hallucination
 d) All of the above
-
 Answer: d) All of the above
-
 Feedback: LLM-based applications have several limitations, including limited token capacity, lack of domain expertise, and being prone to hallucination, among others.
-
 3. Given the following info, what is the value of P(jam|Rain)?
 P(no Rain) = 0.8;
 P(no Jam) = 0.2;
 P(Rain|Jam) = 0.1
-
 a) 0.016
 b) 0.025
 c) 0.1
 d) 0.4
-
 Answer: d) 0.4
-
 Feedback: This question tests understanding of Bayes' Theorem by requiring the calculation of conditional probability using the given values.
 """
 
@@ -111,10 +122,13 @@ def clean_response(response):
 # Function to generate quiz based on content
 def generate_quiz(content):
     prompt = f"{quiz_prompt}\n\nDocument content:\n{content}"
-    response = chat_model([HumanMessage(content=prompt)])
+    #response = chat_model([HumanMessage(content=prompt)])
+    # Use invoke method instead of direct calling
+    response = chat_model.invoke([HumanMessage(content=prompt)])
     cleaned_response = clean_response(response.content)
     return cleaned_response
 
+
 # Function to retrieve relevant documents from vectorstore based on user query
 def retrieve_documents(query):
     results = vectorstore.similarity_search(query, k=3)
@@ -156,7 +170,8 @@ def chat_with_groq(user_input, chat_history):
         prompt = f"{system_prompt}\n\nConversation History:\n{conversation_history}\n\nUser Input: {user_input}\n\nContext:\n{context}"
 
         # Call the chat model
-        response = chat_model([HumanMessage(content=prompt)])
+        #response = chat_model([HumanMessage(content=prompt)])
+        response = chat_model.invoke([HumanMessage(content=prompt)]) # Call the chat model using invoke method  
 
         # Clean response to remove any unwanted formatting
         cleaned_response_text = clean_response(response.content)
@@ -273,33 +288,44 @@ def process_document(file):
 #    y /= np.max(np.abs(y))
 #    return transcriber({"sampling_rate": sr, "raw": y})["text"]
 
+
 #Quick Fixes You Can Try First:
 
 def transcribe_audio(audio):
+    """Real-time optimized transcription"""
+    if audio is None:
+        return ""
+    
     sr, y = audio
+    
+    # Quick preprocessing
     if y.ndim > 1:
         y = y.mean(axis=1)
-    y = y.astype(np.float32)
     
-    # Improved normalization
+    y = y.astype(np.float32)
     max_val = np.max(np.abs(y))
     if max_val > 0:
-        y /= max_val
+        y = y / max_val
     
-    # Use better model
-    better_transcriber = pipeline(
+    # Use tiny model for real-time speed
+    realtime_transcriber = pipeline(
         "automatic-speech-recognition",
-        model="openai/whisper-small.en",  # More accurate
-        chunk_length_s=30
+        model="openai/whisper-tiny.en",  # Fastest model
+        device="cuda" if torch.cuda.is_available() else "cpu",
+        torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,
+        generate_kwargs={
+            "language": "english",
+            "task": "transcribe",
+            "temperature": 0.0,  # More deterministic
+            "no_repeat_ngram_size": 2
+        }
     )
     
-    return better_transcriber({"sampling_rate": sr, "raw": y})["text"]
+    return realtime_transcriber({"sampling_rate": sr, "raw": y})["text"]
 
 # the remaining is the same 
 
 
-
-
 # Clear chat history function
 def clear_chat_history():
     chat_memory.clear()
@@ -333,6 +359,18 @@ def tutor_ai_chatbot():
                 with gr.Column(scale=1):
                     audio_input = gr.Audio(type="numpy", label="Record or Upload Audio")
             
+            # Voice recording tips - ONLY in AI Chatbot tab
+            with gr.Accordion("🎤 Voice Recording Tips", open=False):
+                gr.Markdown("""
+                **For better speech recognition accuracy:**
+                - 🎙️ Speak clearly and at a moderate pace
+                - 🔇 Record in a quiet environment
+                - 📍 Keep the microphone close to your mouth (10-15 cm)
+                - 🎧 Use a good quality microphone if possible
+                - 📝 Review the transcribed text before sending
+                - 🔄 If transcription is poor, try recording again or type manually
+                """)
+            
             # Clear chat history button
             clear_btn = gr.Button("Clear Chat")
 
@@ -398,4 +436,4 @@ def tutor_ai_chatbot():
 
 # Launch the AI chatbot
 if __name__ == "__main__":
-    tutor_ai_chatbot()
+    tutor_ai_chatbot()