Spaces:
Sleeping
Sleeping
| import gradio as gr | |
| from huggingface_hub import InferenceClient | |
| from PyPDF2 import PdfReader | |
| import faiss | |
| import numpy as np | |
| from sentence_transformers import SentenceTransformer | |
| # --- 1. Cargar y procesar el PDF --- | |
| pdf_path = "ley_26206.pdf" | |
| reader = PdfReader(pdf_path) | |
| # Extraer texto | |
| text_chunks = [] | |
| for page in reader.pages: | |
| text = page.extract_text() | |
| if text: | |
| # Dividir cada p谩gina en fragmentos de 500 caracteres | |
| for i in range(0, len(text), 500): | |
| text_chunks.append(text[i:i+500]) | |
| # --- 2. Crear embeddings --- | |
| model_emb = SentenceTransformer("all-MiniLM-L6-v2") | |
| embeddings = model_emb.encode(text_chunks, convert_to_numpy=True) | |
| # 脥ndice FAISS para b煤squedas r谩pidas | |
| index = faiss.IndexFlatL2(embeddings.shape[1]) | |
| index.add(embeddings) | |
| def search_pdf(query, top_k=3): | |
| """Busca en el PDF los fragmentos m谩s relevantes""" | |
| q_emb = model_emb.encode([query], convert_to_numpy=True) | |
| D, I = index.search(q_emb, top_k) | |
| results = [text_chunks[i] for i in I[0]] | |
| return "\n".join(results) | |
| # --- 3. Chatbot con b煤squeda en PDF --- | |
| def respond( | |
| message, | |
| history: list[dict[str, str]], | |
| system_message, | |
| max_tokens, | |
| temperature, | |
| top_p, | |
| hf_token: gr.OAuthToken, | |
| ): | |
| client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b") | |
| # Buscar en el PDF | |
| pdf_context = search_pdf(message) | |
| # Si encontr贸 informaci贸n, se agrega al system message | |
| if pdf_context.strip(): | |
| system_message += f"\nUsa la siguiente informaci贸n de la Ley 26.206 si es relevante:\n{pdf_context}" | |
| messages = [{"role": "system", "content": system_message}] | |
| messages.extend(history) | |
| messages.append({"role": "user", "content": message}) | |
| response = "" | |
| for msg in client.chat_completion( | |
| messages, | |
| max_tokens=max_tokens, | |
| stream=True, | |
| temperature=temperature, | |
| top_p=top_p, | |
| ): | |
| choices = msg.choices | |
| token = "" | |
| if len(choices) and choices[0].delta.content: | |
| token = choices[0].delta.content | |
| response += token | |
| yield response | |
| # --- 4. Interfaz --- | |
| chatbot = gr.ChatInterface( | |
| respond, | |
| type="messages", | |
| additional_inputs=[ | |
| gr.Textbox(value="Eres un asistente experto en la Ley 26.206.", 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"), | |
| ], | |
| ) | |
| with gr.Blocks() as demo: | |
| gr.Markdown("# 馃摌 Chatbot sobre la Ley 26.206") | |
| with gr.Sidebar(): | |
| gr.LoginButton() | |
| chatbot.render() | |
| if __name__ == "__main__": | |
| demo.launch() | |