update app.py for docx

app.py

@@ -1,70 +1,58 @@
+import os, glob, re
 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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+from docx import Document
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+DOCS_DIR = "."
+CHUNK_SIZE = 900
+OVERLAP = 150
+
+def _read_docx(path):
+    doc = Document(path)
+    full_text = []
+    for para in doc.paragraphs:
+        if para.text.strip():
+            full_text.append(para.text)
+    return "\n".join(full_text)
+
+def _chunk(text, size=CHUNK_SIZE, overlap=OVERLAP):
+    text = re.sub(r"\s+", " ", text).strip()
+    chunks, i = [], 0
+    while i < len(text):
+        chunks.append(text[i:i+size])
+        i += (size - overlap)
+    return chunks
+
+# 1) Cargar documentos DOCX
+docs = []
+for path in glob.glob(os.path.join(DOCS_DIR, "*.docx")):
+    docs.append((path, _read_docx(path)))
+
+corpus, sources = [], []
+for src, fulltext in docs:
+    for ch in _chunk(fulltext):
+        corpus.append(ch)
+        sources.append(src)
+
+if not corpus:
+    corpus = ["(Aún no subiste documentos .docx)"]
+    sources = [""]
+
+# 2) Vectorizar
+vectorizer = TfidfVectorizer(stop_words="spanish")
+X = vectorizer.fit_transform(corpus)
+
+# 3) Función de respuesta
+def answer_fn(message, history):
+    if "(Aún no" in corpus[0]:
+        return "No hay documentos .docx disponibles."
+    q = vectorizer.transform([message])
+    sims = cosine_similarity(q, X).ravel()
+    top_idx = sims.argsort()[::-1][:3]
+    bullets = []
+    for i in top_idx:
+        frag = corpus[i]
+        src = os.path.basename(sources[i])
+        bullets.append(f"**{src}** · …{frag[:420]}…")
+    return "Fragmentos relevantes:\n\n- " + "\n