Update app.py

app.py

@@ -1,93 +1,132 @@
 import streamlit as st
 import os
-from langchain_openai import ChatOpenAI, OpenAIEmbeddings
-from langchain_community.document_loaders import TextLoader, PyPDFLoader
-from langchain_community.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import FAISS
-from langchain.prompts import ChatPromptTemplate
-from langchain_core.output_parsers import StrOutputParser
-import tempfile
+import re
 
 os.environ["OPENAI_API_KEY"] = "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"
 
-def load_vectorstore(file_path):
-    if os.path.exists("faiss_index"):
-        embeddings = OpenAIEmbeddings()
-        return FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
+from langchain_openai import ChatOpenAI
+from openai import OpenAI
+import tempfile
+
+client = OpenAI()
+
+def simple_split(text, chunk_size=1000):
+    """Pure Python splitter"""
+    sentences = re.split(r'[.!?]\s+', text)
+    chunks = []
+    current_chunk = ""
+    
+    for sentence in sentences:
+        if len(current_chunk + sentence) < chunk_size:
+            current_chunk += sentence + ". "
+        else:
+            if current_chunk:
+                chunks.append(current_chunk.strip())
+            current_chunk = sentence + ". "
+    
+    if current_chunk:
+        chunks.append(current_chunk.strip())
+    
+    return chunks
+
+def dynamic_rag(query, document_content):
+    """Dynamic RAG - no external deps"""
+    chunks = simple_split(document_content)
     
-    file_ext = file_path.split('.')[-1].lower()
-    if file_ext == 'pdf':
-        loader = PyPDFLoader(file_path)
-    else:
-        loader = TextLoader(file_path)
+    # Simple similarity (keyword matching)
+    best_chunks = []
+    query_words = set(query.lower().split())
     
-    docs = loader.load()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    splits = text_splitter.split_documents(docs)
+    for chunk in chunks:
+        chunk_words = set(chunk.lower().split())
+        score = len(query_words.intersection(chunk_words))
+        best_chunks.append((score, chunk))
     
-    embeddings = OpenAIEmbeddings()
-    vectorstore = FAISS.from_documents(splits, embeddings)
-    vectorstore.save_local("faiss_index")
-    return vectorstore
-
-def get_rag_chain(vectorstore):
-    retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
-    llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+    best_chunks.sort(reverse=True, key=lambda x: x[0])
+    context = "\n".join([chunk for score, chunk in best_chunks[:3]])
     
-    prompt = ChatPromptTemplate.from_template("Context: {context}. Question: {question}. Answer using context only.")
+    prompt = f"""Use ONLY this context from document:
+
+{context}
+
+Question: {query}
+
+Answer using context only:"""
     
-    chain = (
-        {"context": retriever, "question": lambda x: x} 
-        | prompt 
-        | llm 
-        | StrOutputParser()
+    response = client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=[{"role": "user", "content": prompt}],
+        temperature=0
     )
-    return chain
+    return response.choices[0].message.content
 
 st.title("🧠 Dynamic RAG Chatbot")
-st.markdown("Upload PDF/TXT → Ask ANY question!")
+st.markdown("**Paste text or upload → Ask ANY question!**")
 
-uploaded_file = st.file_uploader("📤 Upload PDF or TXT", type=['pdf', 'txt'])
+# Input options
+col1, col2 = st.columns(2)
 
-if uploaded_file is not None:
-    with tempfile.NamedTemporaryFile(delete=False, suffix=f".{uploaded_file.name.split('.')[-1]}") as tmp_file:
-        tmp_file.write(uploaded_file.getvalue())
-        file_path = tmp_file.name
-    
-    st.success(f"✅ Loaded: {uploaded_file.name}")
-    
-    with st.spinner("🔄 Indexing..."):
-        vectorstore = load_vectorstore(file_path)
-        chain = get_rag_chain(vectorstore)
-        st.session_state.chain = chain
-        st.session_state.ready = True
-        st.session_state.doc_name = uploaded_file.name
-
-if 'ready' in st.session_state and st.session_state.ready:
-    st.success(f"🚀 Ready! Document: {st.session_state.doc_name}")
+with col1:
+    uploaded_file = st.file_uploader("📤 Upload TXT", type='txt')
     
+with col2:
+    pasted_text = st.text_area("📝 Or paste text here", height=150)
+
+document_content = ""
+
+if uploaded_file is not None:
+    content = uploaded_file.read().decode('utf-8')
+    document_content = content
+    st.success("✅ TXT loaded!")
+elif pasted_text:
+    document_content = pasted_text
+    st.success("✅ Text loaded!")
+
+if document_content:
+    st.session_state.document_content = document_content
+    st.success("🚀 Chatbot ready! Ask about your text.")
+
+if 'document_content' in st.session_state:
     if "messages" not in st.session_state:
         st.session_state.messages = []
     
+    # Chat history
     for message in st.session_state.messages:
         with st.chat_message(message["role"]):
             st.markdown(message["content"])
     
+    # Chat input
     if query := st.chat_input("💬 Ask about your document..."):
         st.session_state.messages.append({"role": "user", "content": query})
         with st.chat_message("user"):
             st.markdown(query)
         
         with st.chat_message("assistant"):
-            with st.spinner("Searching..."):
-                response = st.session_state.chain.invoke(query)
+            with st.spinner("🔍 Searching document..."):
+                response = dynamic_rag(query, st.session_state.document_content)
                 st.markdown(response)
         
         st.session_state.messages.append({"role": "assistant", "content": response})
 
+    # Clear
     if st.button("🗑️ Clear Chat"):
         st.session_state.messages = []
         st.rerun()
 
 else:
-    st.info("👆 Upload PDF/TXT to start chatting!")
+    st.info("👆 **Paste text or upload TXT to start chatting!**")
+    st.markdown("""
+    **Test example:**
+    ```
+    Skills: Python, DSA, AI/ML
+    Projects: RAG Chatbot (live demo)
+    LeetCode: 300 problems solved
+    ```
+    Ask: "What projects?" → Perfect answer!
+    """)
+
+st.sidebar.markdown("### 🛠️ Pure Python RAG")
+st.markdown("• Custom text splitter")
+st.markdown("• Keyword similarity")
+st.markdown("• OpenAI GPT-4o-mini")
+st.markdown("• Dynamic input")