Update app.py

app.py

@@ -7,20 +7,27 @@ from langchain_community.vectorstores import FAISS
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.chains import RetrievalQA
 from langchain.prompts import PromptTemplate
-from langchain_groq import GroqLLM
+from langchain.schema import Document
+# from langchain_groq import GroqLLM
+from langchain_groq import ChatGroq
 
-# --- Environment Variable Setup ---
+# --- Environment Variables ---
 GROQ_API_KEY = os.getenv("GROQ_API_KEY", "your-groq-api-key")
 HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY", "your-huggingface-api-key")
 
-# --- Groq LLM Initialization ---
-llm = GroqLLM(
+# --- Initialize Groq LLM ---
+# llm = GroqLLM(
+#     api_key=GROQ_API_KEY,
+#     model="llama3-8b-8192",
+#     temperature=0.1
+# )
+llm = ChatGroq(
     api_key=GROQ_API_KEY,
-    model="llama3-8b-8192",
+    model_name="llama3-8b-8192",  # Note: it's `model_name` not `model`
     temperature=0.1
 )
 
-# --- HuggingFace Embeddings (add a default model name if needed) ---
+# --- HuggingFace Embeddings ---
 embedding = HuggingFaceEmbeddings(
     model_name="sentence-transformers/all-MiniLM-L6-v2",
     cache_folder="./hf_cache",
@@ -28,36 +35,57 @@ embedding = HuggingFaceEmbeddings(
 )
 
 # --- Streamlit UI ---
-st.title("📄 RAG Chat with Groq + HuggingFace")
+st.title("📄📥 Chat with PDF or Text using Groq + RAG")
 
+# Option to upload PDF
 uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
-user_query = st.text_input("Ask something about the document")
+
+# Option to paste raw text
+pasted_text = st.text_area("Or paste some text below:")
+
+# User's question
+user_query = st.text_input("Ask a question about the content")
+
+# Submit button
 submit_button = st.button("Submit")
 
-if uploaded_file and submit_button:
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
-        tmp_file.write(uploaded_file.read())
-        tmp_path = tmp_file.name
+if submit_button:
+    documents = []
+
+    # Handle uploaded PDF
+    if uploaded_file:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+            tmp_file.write(uploaded_file.read())
+            tmp_path = tmp_file.name
 
-    # --- Load and Split PDF ---
-    loader = PyPDFLoader(tmp_path)
-    pages = loader.load_and_split()
+        loader = PyPDFLoader(tmp_path)
+        documents = loader.load_and_split()
 
-    # --- FAISS Vector Store ---
-    vectorstore = FAISS.from_documents(pages, embedding)
+    # Handle pasted text if no PDF
+    elif pasted_text.strip():
+        documents = [Document(page_content=pasted_text)]
+
+    else:
+        st.warning("Please upload a PDF or paste some text.")
+        st.stop()
+
+    # Create vector store
+    vectorstore = FAISS.from_documents(documents, embedding)
     retriever = vectorstore.as_retriever()
 
-    # --- Optional Custom Prompt ---
+    # Optional custom prompt
     prompt_template = PromptTemplate(
         input_variables=["context", "question"],
         template="""
-        You are an intelligent assistant. Use the following context to answer the question accurately.
+        You are an AI assistant. Use the following context to answer the question.
+        Be concise, accurate, and helpful.
+
         Context: {context}
         Question: {question}
         Answer:"""
     )
 
-    # --- RetrievalQA Chain ---
+    # QA Chain
     qa_chain = RetrievalQA.from_chain_type(
         llm=llm,
         chain_type="stuff",
@@ -66,12 +94,15 @@ if uploaded_file and submit_button:
         chain_type_kwargs={"prompt": prompt_template}
     )
 
-    # --- Run the Chain ---
+    # Run QA
     result = qa_chain({"query": user_query})
+
+    # Show result
     st.markdown("### 💬 Answer")
     st.write(result["result"])
 
-    # --- Optional: Show Source Documents ---
-    with st.expander("📄 Sources"):
-        for i, doc in enumerate(result["source_documents"]):
-            st.write(f"**Page {i+1}** — {doc.metadata.get('source', 'Unknown')}")
+    # Show sources (only if from PDF)
+    if uploaded_file:
+        with st.expander("📄 Sources"):
+            for i, doc in enumerate(result["source_documents"]):
+                st.write(f"**Page {i+1}** — {doc.metadata.get('source', 'Unknown')}")