Create app.py

app.py

@@ -0,0 +1,67 @@
+import os
+import zipfile
+import gradio as gr
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+from huggingface_hub import InferenceClient
+from langchain_core.prompts import PromptTemplate
+from langchain_core.runnables import RunnablePassthrough, RunnableLambda, RunnableParallel
+
+# 1. Unzip stored FAISS index
+if not os.path.exists("faiss_store"):
+    with zipfile.ZipFile("faiss_store.zip", "r") as zip_ref:
+        zip_ref.extractall(".")
+
+# 2. Reload FAISS vector store
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+vector_store = FAISS.load_local("faiss_store", embeddings, allow_dangerous_deserialization=True)
+
+# 3. Setup retriever + RAG chain
+retriever = vector_store.as_retriever(search_kwargs={"k": 3})
+hf_token = os.environ.get("HF_TOKEN")
+client = InferenceClient(model="mistralai/Mistral-7B-Instruct-v0.2", token=hf_token)
+
+prompt_template = """Use the following context about my work experience to answer the question. If you don't know, say so.
+Context: {context}
+Question: {question}
+Answer:"""
+
+def generate_with_client(query, context):
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant summarizing work experience."},
+        {"role": "user", "content": prompt_template.format(context=context, question=query)}
+    ]
+    response = client.chat_completion(messages, max_tokens=200)
+    return response.choices[0].message.content
+
+rag_chain = (
+    RunnableParallel({
+        "context": retriever | RunnableLambda(lambda docs: "\n\n".join([doc.page_content for doc in docs])),
+        "question": RunnablePassthrough()
+    })
+    | RunnableLambda(lambda x: generate_with_client(x["question"], x["context"]))
+)
+
+# 4. Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("# 🚀 RAG Chatbot (Prebuilt Vector Store)")
+    chatbot = gr.Chatbot(height=400, type="messages")
+    msg = gr.Textbox(placeholder="Ask about your work experience...")
+    clear = gr.Button("Clear")
+
+    def user(user_message, history):
+        history.append({"role": "user", "content": user_message})
+        return "", history
+
+    def respond(history):
+        user_message_content = history[-1]["content"]
+        bot_response_content = rag_chain.invoke(user_message_content)
+        history.append({"role": "assistant", "content": bot_response_content})
+        return history
+
+    msg.submit(user, [msg, chatbot], [msg, chatbot], queue=False).then(
+        respond, [chatbot], chatbot
+    )
+    clear.click(lambda: [], None, chatbot, queue=False)
+
+demo.launch()