Updated Libraries

app.py

@@ -1,126 +1,294 @@
-import gradio as gr
 import os
+import gradio as gr
+
 from google import genai
+
 from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain_community.vectorstores import FAISS
 from langchain_community.document_loaders import TextLoader
-from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+
+
+# ============================================================
+# 1. Gemini Setup
+# ============================================================
+
+GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY")
+
+if not GOOGLE_API_KEY:
+    raise RuntimeError(
+        "GOOGLE_API_KEY is not set. "
+        "Add it to your Hugging Face Space Secrets."
+    )
+
+client = genai.Client(api_key=GOOGLE_API_KEY)
 
-# -------------------------------
-# 1. Setup Gemini
-# -------------------------------
-genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
-gemini_model = genai.GenerativeModel("gemini-2.5-flash")
+GEMINI_MODEL = "gemini-2.5-flash"
 
-# -------------------------------
+
+# ============================================================
 # 2. Ensure about_me.txt exists
-# -------------------------------
-if not os.path.exists("about_me.txt"):
-    with open("about_me.txt", "w") as f:
-        f.write("""
-        Hello! I am a portfolio chatbot. I can help answer questions about projects, skills, and experience.
-        This is a sample portfolio text. Please replace this with your actual portfolio content.
-        """)
-
-# -------------------------------
-# 3. Load data
-# -------------------------------
+# ============================================================
+
+ABOUT_FILE = "about_me.txt"
+
+if not os.path.exists(ABOUT_FILE):
+    with open(ABOUT_FILE, "w", encoding="utf-8") as f:
+        f.write(
+            """
+Hello! I am Abdullah Tahir.
+
+I am an AI Developer and AI Engineer with experience in Python,
+backend development, AI applications, RAG systems, and AI integrations.
+
+I work with technologies such as Python, FastAPI, Django,
+LangChain, LangGraph, Hugging Face, TensorFlow, scikit-learn,
+n8n, and LLM APIs.
+
+This chatbot is connected to my portfolio and can answer questions
+about my background, skills, projects, and experience.
+"""
+        )
+
+
+# ============================================================
+# 3. Load Portfolio Data
+# ============================================================
+
 try:
-    loader = TextLoader("about_me.txt")
-    docs = loader.load()
+    loader = TextLoader(
+        ABOUT_FILE,
+        encoding="utf-8"
+    )
+
+    documents = loader.load()
+
 except Exception as e:
-    print(f"Error loading document: {e}")
-    from langchain.schema import Document
-    docs = [Document(page_content="Hello! I am a portfolio chatbot ready to help you.")]
+    print(f"Error loading {ABOUT_FILE}: {e}")
+
+    from langchain_core.documents import Document
+
+    documents = [
+        Document(
+            page_content=(
+                "This is Abdullah Tahir's portfolio chatbot. "
+                "The portfolio information could not be loaded."
+            )
+        )
+    ]
+
+
+# ============================================================
+# 4. Split Documents
+# ============================================================
 
-# -------------------------------
-# 4. Split documents
-# -------------------------------
 text_splitter = RecursiveCharacterTextSplitter(
     chunk_size=500,
     chunk_overlap=50
 )
-split_docs = text_splitter.split_documents(docs)
 
-# -------------------------------
-# 5. Create embeddings & FAISS
-# -------------------------------
-print("Loading embeddings...")
+split_documents = text_splitter.split_documents(documents)
+
+print(f"Loaded {len(split_documents)} document chunks.")
+
+
+# ============================================================
+# 5. Create Embedding Model
+# ============================================================
+
+print("Loading embedding model...")
+
 embedding_model = HuggingFaceEmbeddings(
     model_name="sentence-transformers/all-MiniLM-L6-v2",
-    model_kwargs={'device': 'cpu'}
+    model_kwargs={
+        "device": "cpu"
+    },
+    encode_kwargs={
+        "normalize_embeddings": True
+    }
+)
+
+print("Embedding model loaded.")
+
+
+# ============================================================
+# 6. Create FAISS Vector Database
+# ============================================================
+
+print("Creating FAISS vector database...")
+
+vector_db = FAISS.from_documents(
+    split_documents,
+    embedding_model
+)
+
+print("FAISS database ready.")
+
+
+# ============================================================
+# 7. Create Retriever
+# ============================================================
+
+retriever = vector_db.as_retriever(
+    search_kwargs={
+        "k": 3
+    }
 )
 
-print("Creating vector database...")
-db = FAISS.from_documents(split_docs, embedding_model)
 
-# -------------------------------
-# 6. Ask function with Gemini refinement
-# -------------------------------
-def ask_bot_alternative(question: str):
+# ============================================================
+# 8. Ask Chatbot
+# ============================================================
+
+def ask_bot(question: str) -> str:
+
     try:
-        if not question.strip():
-            return "Please ask me a question about the portfolio!"
 
-        # Retrieve top documents
-        retriever = db.as_retriever(search_kwargs={"k": 2})
-        context_docs = retriever.get_relevant_documents(question)
+        # --------------------------------------------
+        # Validate question
+        # --------------------------------------------
+
+        if not question or not question.strip():
+            return "Please ask me a question about my portfolio."
+
+
+        question = question.strip()
+
+
+        # --------------------------------------------
+        # Retrieve relevant documents
+        # --------------------------------------------
+
+        context_documents = retriever.invoke(question)
 
-        if not context_docs:
-            return "I could not find an answer in the portfolio content."
+        if not context_documents:
+            return (
+                "I couldn't find relevant information "
+                "in the portfolio."
+            )
 
-        # Combine retrieved docs into context
-        context = "\n".join([doc.page_content for doc in context_docs])
 
-        # Send to Gemini for refinement
+        # --------------------------------------------
+        # Build context
+        # --------------------------------------------
+
+        context = "\n\n".join(
+            document.page_content
+            for document in context_documents
+        )
+
+
+        # --------------------------------------------
+        # Gemini Prompt
+        # --------------------------------------------
+
         prompt = f"""
-        You are a helpful assistant. 
-        Answer the following question using only the given context. 
-        If the answer is not present, say "I don’t know".
+You are Abdullah Tahir's portfolio assistant.
+
+Your job is to answer questions about Abdullah using ONLY
+the portfolio information provided below.
+
+Rules:
+
+1. Use only the provided context.
+2. Do not invent information.
+3. If the answer is not available in the context,
+   clearly say that the information is not available.
+4. Keep answers concise and professional.
+5. Speak naturally.
+6. When appropriate, mention relevant technologies,
+   projects, education, or experience from the context.
+
+Portfolio Context:
+------------------
+{context}
+------------------
+
+User Question:
+{question}
+
+Answer:
+"""
 
-        Question: {question}
 
-        Context:
-        {context}
+        # --------------------------------------------
+        # Call Gemini
+        # --------------------------------------------
 
-        Final Answer:
-        """
+        response = client.models.generate_content(
+            model=GEMINI_MODEL,
+            contents=prompt
+        )
+
+
+        # --------------------------------------------
+        # Return response
+        # --------------------------------------------
+
+        if response and response.text:
+            return response.text.strip()
+
+        return "I couldn't generate a response."
 
-        response = gemini_model.generate_content(prompt)
-        return response.text.strip()
 
     except Exception as e:
-        return f"Sorry, I encountered an error: {str(e)[:200]}"
 
-# -------------------------------
-# 7. Gradio Interface
-# -------------------------------
-iface = gr.Interface(
-    fn=ask_bot_alternative,
+        print(f"Chatbot error: {e}")
+
+        return (
+            "Sorry, I encountered an error while processing "
+            "your question. Please try again."
+        )
+
+
+# ============================================================
+# 9. Gradio Interface
+# ============================================================
+
+interface = gr.Interface(
+
+    fn=ask_bot,
+
     inputs=gr.Textbox(
         label="Ask me about the portfolio",
         placeholder="What would you like to know?",
-        max_lines=3
+        lines=3
     ),
+
     outputs=gr.Textbox(
         label="Response",
-        max_lines=10
+        lines=10
     ),
-    title="Portfolio Chatbot",
-    description="Ask me questions about skills, projects, and experience!",
+
+    title="Abdullah Tahir - Portfolio Chatbot",
+
+    description=(
+        "Ask questions about my background, "
+        "skills, projects, education, and experience."
+    ),
+
     examples=[
         "What are your technical skills?",
-        "Tell me about your projects",
-        "What is your background?"
+        "Tell me about your projects.",
+        "What is your educational background?",
+        "What technologies do you work with?",
+        "Tell me about your AI experience."
     ],
-    cache_examples=False,
-    
+
+    cache_examples=False
 )
 
+
+# ============================================================
+# 10. Launch
+# ============================================================
+
 if __name__ == "__main__":
-    print("Launching chatbot...")
-    iface.launch(
+
+    print("Starting Portfolio Chatbot...")
+
+    interface.launch(
         server_name="0.0.0.0",
-        server_port=7860,
+        server_port=int(os.getenv("PORT", "7860")),
         show_error=True
     )