Update app.py

app.py

@@ -1,70 +1,77 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+from langchain_huggingface import HuggingFaceEmbeddings, HuggingFacePipeline
+from langchain_community.vectorstores import FAISS
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.output_parsers import StrOutputParser
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
+import torch
+
+
+embed_model_id = "BAAI/bge-small-en-v1.5"
+embeddings = HuggingFaceEmbeddings(
+    model_name=embed_model_id,
+    model_kwargs={"device": "cuda" if torch.cuda.is_available() else "cpu"}
+)
+
+
+texts = [
+    "Kragujevac is a city in central Serbia founded in the 15th century.",
+    "The main industry in Kragujevac includes automotive manufacturing.",
+    "Famous landmarks: The Šumarice Memorial Park and the Old Foundry Museum."
+]
+
+
+text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=80)
+docs = text_splitter.create_documents(texts)
+
+
+vectorstore = FAISS.from_documents(docs, embeddings)
+retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
+
+
+model_id = "Qwen/Qwen2.5-0.5B-Instruct"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    device_map="cpu",
+    torch_dtype=torch.float32
+)
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    max_new_tokens=200,
+    temperature=0.7,
+    do_sample=True
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+llm = HuggingFacePipeline(pipeline=pipe)
+
+template = """You are a helpful assistant. Use only the provided context to answer.
+If unsure, say "I don't know."
+
+Context: {context}
 
+Question: {question}
+
+Answer:"""
+prompt = ChatPromptTemplate.from_template(template)
+
+
+def format_docs(docs):
+    return "\n\n".join(doc.page_content for doc in docs)
+
+rag_chain = (
+    {"context": retriever | format_docs, "question": RunnablePassthrough()}
+    | prompt
+    | llm
+    | StrOutputParser()
+)
 
-if __name__ == "__main__":
-    demo.launch()
+question = "What are some landmarks in Kragujevac?"
+print("Question:", question)
+print("Answer:", rag_chain.invoke(question))