Create app.py

app.py

@@ -0,0 +1,56 @@
+import os
+import gradio as gr
+from langchain_huggingface import HuggingFaceEmbeddings, HuggingFaceEndpoint
+from langchain_community.vectorstores import FAISS
+from langchain.chains import create_retrieval_chain
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+
+# 1. Load the pre-computed Vector Database
+embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
+# Allow dangerous deserialization is required for local FAISS loading
+vectorstore = FAISS.load_local("learncpp_faiss_index", embeddings, allow_dangerous_deserialization=True)
+
+# 2. Set up the LLM (Using Mistral-7B for excellent coding logic)
+hf_token = os.environ.get("HF_TOKEN")
+llm = HuggingFaceEndpoint(
+    repo_id="mistralai/Mistral-7B-Instruct-v0.2",
+    task="text-generation",
+    max_new_tokens=512,
+    temperature=0.1,
+    huggingfacehub_api_token=hf_token
+)
+
+# 3. Create the RAG Chain
+system_prompt = (
+    "You are an expert C++ programming assistant. You answer questions strictly based "
+    "on the provided context from learncpp.com. If the answer is not in the context, "
+    "say 'I cannot find the answer in the LearnCpp documentation.'\n\n"
+    "Context:\n{context}"
+)
+
+prompt = ChatPromptTemplate.from_messages([
+    ("system", system_prompt),
+    ("human", "{input}"),
+])
+
+qa_chain = create_stuff_documents_chain(llm, prompt)
+rag_chain = create_retrieval_chain(vectorstore.as_retriever(search_kwargs={"k": 3}), qa_chain)
+
+# 4. Define the Chat Interface
+def chat_function(message, history):
+    try:
+        response = rag_chain.invoke({"input": message})
+        return response["answer"]
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+demo = gr.ChatInterface(
+    fn=chat_function,
+    title="LearnCpp.com AI Assistant",
+    description="Ask me any C++ question! I retrieve my answers directly from the LearnCpp tutorials.",
+    examples=["What is a pointer?", "Explain dynamic memory allocation."]
+)
+
+if __name__ == "__main__":
+    demo.launch()