Update app.py

app.py

@@ -3,30 +3,34 @@
 import os
 import tempfile
 import streamlit as st
-
-# ✅ Make sure you have installed langchain-community
-# pip install -U langchain langchain-community
+import requests
 from langchain_community.vectorstores import FAISS
 from langchain_community.document_loaders import PyMuPDFLoader, Docx2txtLoader, UnstructuredImageLoader
 from langchain_community.embeddings import HuggingFaceEmbeddings
-
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_core.documents import Document
 from gtts import gTTS
 import base64
 import shutil
 
+# ----------------------------- UI SETUP --------------------------------------
 st.set_page_config(page_title="Learning with Fun", layout="wide")
 st.title("📚 Learning with Fun - Educational Q&A for Kids")
 
+# ----------------------------- USER INPUT -----------------------------------
 grade = st.selectbox("Select your Grade", ["Grade 5", "Grade 6"])
 subject = st.selectbox("Select Subject", ["Science", "Math", "English"])
+
 uploaded_files = st.file_uploader("Upload textbook files (PDF, DOCX, JPEG)", type=["pdf", "docx", "jpg", "jpeg"], accept_multiple_files=True)
 question = st.text_input("Ask your question in English or Urdu")
+groq_api_key = st.text_input("🔐 Enter your GROQ API Key", type="password")
 
+# ------------------------- SETUP TEMP FOLDER -------------------------------
 temp_dir = tempfile.mkdtemp()
 
+# ------------------------- UTILITY FUNCTIONS -------------------------------
 def load_documents(uploaded_files):
+    """Load various file types into LangChain Document format."""
     docs = []
     for file in uploaded_files:
         ext = file.name.split(".")[-1].lower()
@@ -46,19 +50,27 @@ def load_documents(uploaded_files):
     return docs
 
 def split_documents(documents):
+    """Split documents into smaller chunks."""
     splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
     return splitter.split_documents(documents)
 
 def create_vector_store(chunks):
+    """Create FAISS vector DB from text chunks."""
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     return FAISS.from_documents(chunks, embeddings)
 
 def retrieve_docs(query, vector_store):
+    """Search FAISS for relevant chunks."""
     return vector_store.similarity_search(query, k=3)
 
-def query_llm_groq(context, query):
-    from openai import OpenAI
-    client = OpenAI(api_key=os.getenv("GROQ_API_KEY"), base_url="https://api.groq.com/openai/v1")
+def query_llm_groq(context, query, groq_api_key):
+    """Query GROQ LLaMA 3 API directly and return formatted answers."""
+    url = "https://api.groq.com/openai/v1/chat/completions"
+
+    headers = {
+        "Authorization": f"Bearer {groq_api_key}",
+        "Content-Type": "application/json"
+    }
 
     prompt = f"""
     Context:
@@ -71,13 +83,22 @@ def query_llm_groq(context, query):
     1. A simple, educational explanation in English + Urdu.
     2. A creative storytelling version mixing English and Urdu.
     """
-    response = client.chat.completions.create(
-        model="llama3-8b-8192",
-        messages=[{"role": "user", "content": prompt}]
-    )
-    return response.choices[0].message.content
+
+    data = {
+        "model": "llama3-8b-8192",
+        "messages": [
+            {"role": "user", "content": prompt}
+        ],
+        "temperature": 0.7
+    }
+
+    response = requests.post(url, headers=headers, json=data)
+    response.raise_for_status()
+    result = response.json()
+    return result["choices"][0]["message"]["content"]
 
 def generate_audio(text, lang='ur'):
+    """Convert text to audio using gTTS and return playable audio HTML."""
     tts = gTTS(text, lang=lang)
     audio_path = os.path.join(temp_dir, "response.mp3")
     tts.save(audio_path)
@@ -87,7 +108,8 @@ def generate_audio(text, lang='ur'):
     audio_html = f'<audio autoplay controls><source src="data:audio/mp3;base64,{b64}" type="audio/mp3"></audio>'
     return audio_html
 
-if question and uploaded_files:
+# ----------------------------- MAIN LOGIC ----------------------------------
+if question and uploaded_files and groq_api_key:
     with st.spinner("Processing your documents..."):
         documents = load_documents(uploaded_files)
         chunks = split_documents(documents)
@@ -95,7 +117,7 @@ if question and uploaded_files:
 
         results = retrieve_docs(question, vector_db)
         context_text = "\n".join([doc.page_content for doc in results])
-        answer = query_llm_groq(context_text, question)
+        answer = query_llm_groq(context_text, question, groq_api_key)
 
     st.markdown("### 📘 Answer")
     parts = answer.split("2.")
@@ -106,5 +128,6 @@ if question and uploaded_files:
     else:
         st.markdown(answer)
 
+# ----------------------------- CLEANUP --------------------------------------
 if os.path.exists(temp_dir):
     shutil.rmtree(temp_dir)