Update pages/summarizer.py

pages/summarizer.py

@@ -1,87 +1,47 @@
 import streamlit as st
-from PyPDF2 import PdfReader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_groq import ChatGroq
-from langchain_community.embeddings import HuggingFaceInferenceAPIEmbeddings
-from langchain.vectorstores import FAISS
-from langchain.chains.question_answering import load_qa_chain
-from langchain.prompts import PromptTemplate
-import tempfile
-from gtts import gTTS
 import os
+import requests
 
-def text_to_speech(text):
-    tts = gTTS(text=text, lang='en')
-    audio_file = tempfile.NamedTemporaryFile(suffix=".mp3", delete=False)
-    temp_filename = audio_file.name
-    tts.save(temp_filename)
-    st.audio(temp_filename, format='audio/mp3')
-    os.remove(temp_filename)
+# Define Hugging Face API details
+API_URL = "https://api-inference.huggingface.co/models/Huzaifa367/chat-summarizer"
+API_TOKEN = os.getenv("AUTH_TOKEN")
+HEADERS = {"Authorization": f"Bearer {API_TOKEN}"}
 
-def get_pdf_text(pdf_docs):
-    text=""
-    for pdf in pdf_docs:
-        pdf_reader= PdfReader(pdf)
-        for page in pdf_reader.pages:
-            text+= page.extract_text()
-    return  text
+# Function to query Hugging Face API
+def query_huggingface(payload):
+    try:
+        response = requests.post(API_URL, headers=HEADERS, json=payload)
+        response.raise_for_status()  # Raise exception for non-2xx status codes
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        st.error(f"Error querying Hugging Face API: {e}")
+        return {"summary_text": f"Error querying Hugging Face API: {e}"}
 
-def get_text_chunks(text):
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    chunks = text_splitter.split_text(text)
-    return chunks
-    
-def get_vector_store(text_chunks, api_key):
-    embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
-    vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
-    vector_store.save_local("faiss_index")
-
-def get_conversational_chain():
 
-    prompt_template = """
-    Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
-    provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
-    Context:\n {context}?\n
-    Question: \n{question}\n
-    Answer:
-    """
-
-    model = ChatGroq(temperature=0, groq_api_key=os.environ["groq_api_key"], model_name="llama3-8b-8192")
+def main():
+    
+    st.set_page_config(layout="centered")
+        st.title("Chat Summarizer")
 
-    prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
-    chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
+    # User input for chat message
+    user_message = st.text_input("User Message", "Enter your message here...")
 
-    return chain
+    # Process user input and query Hugging Face API
+    if st.button("Summarize"):
+        if user_message:
+            # Construct input text for summarization (no system message)
+            input_text = f"User: {user_message}"
 
-def user_input(user_question, api_key):
-    embeddings = HuggingFaceInferenceAPIEmbeddings(api_key=api_key, model_name="sentence-transformers/all-MiniLM-l6-v2")
-    
-    new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
-    docs = new_db.similarity_search(user_question)
+            # Query Hugging Face API for summarization
+            payload = {"inputs": input_text}
+            response = query_huggingface(payload)
 
-    chain = get_conversational_chain()
+            # Extract summary text from the API response
+            summary_text = response.get("summary_text", "")
 
-    response = chain(
-        {"input_documents":docs, "question": user_question}
-        , return_only_outputs=True)
+            # Display summary text
+            st.text_area("Summary", value=summary_text)
 
-    print(response)  # Debugging line
-    
-    st.write("Replies:")
-    if isinstance(response["output_text"], str):
-        response_list = [response["output_text"]]
-    else:
-        response_list = response["output_text"]
-    
-    for text in response_list:
-        st.write(text)
-        # Convert text to speech for each response
-        text_to_speech(text)
-
-def main():
-    
-    st.set_page_config(layout="centered")
-    
     with st.sidebar:
         
         st.header("Chat with PDF")
@@ -95,7 +55,7 @@ def main():
                 st.success("Done")
         
         if st.button("Chat Summarizer"):
-        st.switch_page('app.py')
+            st.switch_page('app.py')
     # Check if any document is uploaded
     if pdf_docs:
         user_question = st.text_input("Ask a question from the Docs")