Update app.py

app.py

@@ -1,70 +1,69 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain.prompts import PromptTemplate
+from huggingface_hub import hf_hub_download
 
+# Carica modello GRPO fine-tuned
+model_name = "SelmaNajih001/GRPORagMinstral2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+pipe = pipeline(
+    "text-generation",
+    model=model_name,
+    tokenizer=model_name,
+    max_new_tokens=400,
+    temperature=0.5,
+    num_beams=6,
+    repetition_penalty=1.5
+)
 
-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")
+# Prompt template
+prompt_template = """
+You are a financial market analyst.
+Before making a prediction you always analyze the past, which is given by the Context below.
+Answer the Question based on what happened in the past.
 
-    messages = [{"role": "system", "content": system_message}]
+Please respond with:
+- Chosen Stock: (name)
+- Prediction: (price change)
+- Explanation: (brief and clear)
 
-    messages.extend(history)
+Context:
+{context}
 
-    messages.append({"role": "user", "content": message})
+Question:
+{question}
+"""
+prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
 
-    response = ""
+# Carica FAISS dal dataset
+faiss_index_path = hf_hub_download(repo_id="SelmaNajih001/DatasetStockFAISS", filename="index.faiss")
+docstore_path = hf_hub_download(repo_id="SelmaNajih001/DatasetStockFAISS", filename="docstore.json")
 
-    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
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/multi-qa-mpnet-base-dot-v1")
+vectorstore = FAISS.load_local("faiss_index", embeddings)
+def analisi_finanziaria(query, k=4):
+    # Recupera i documenti più rilevanti
+    docs_found = vectorstore.similarity_search(query, k=k)
 
-        response += token
-        yield response
+    # Costruisci contesto concatenando i documenti
+    context = "\n".join([doc.page_content for doc in docs_found])
 
+    # Costruisci prompt finale
+    final_prompt = prompt.format(context=context, question=query)
 
-"""
-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)",
-        ),
-    ],
+    # Genera risposta
+    result = pipe(final_prompt)[0]['generated_text']
+    return result
+    
+iface = gr.Interface(
+    fn=analisi_finanziaria,
+    inputs=gr.Textbox(label="Inserisci evento o domanda"),
+    outputs=gr.Textbox(label="Predizione"),
+    title="GRPO Financial Analyst",
+    description="Inserisci un evento finanziario, il modello GRPO analizzerà il contesto storico e fornirà una previsione."
 )
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+iface.launch()
 
-if __name__ == "__main__":
-    demo.launch()