Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -19,27 +19,20 @@ css_style = """
|
|
| 19 |
font-size: 24px;
|
| 20 |
font-weight: bold;
|
| 21 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 22 |
.metadata-box {
|
| 23 |
padding: 20px;
|
| 24 |
background-color: #f0f2f6;
|
| 25 |
border-radius: 10px;
|
| 26 |
margin-bottom: 20px;
|
| 27 |
}
|
| 28 |
-
.metadata-title {
|
| 29 |
-
font-size: 18px;
|
| 30 |
-
color: #2e3b4e;
|
| 31 |
-
margin-bottom: 10px;
|
| 32 |
-
}
|
| 33 |
-
button {
|
| 34 |
-
height: 35px;
|
| 35 |
-
width: 120px;
|
| 36 |
-
font-size: 14px;
|
| 37 |
-
background-color: #252850;
|
| 38 |
-
color: white;
|
| 39 |
-
border: none;
|
| 40 |
-
border-radius: 5px;
|
| 41 |
-
cursor: pointer;
|
| 42 |
-
}
|
| 43 |
.custom-input {
|
| 44 |
font-size: 16px;
|
| 45 |
padding: 10px;
|
|
@@ -49,6 +42,10 @@ css_style = """
|
|
| 49 |
</style>
|
| 50 |
"""
|
| 51 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
def get_pdf_text(pdf_docs):
|
| 53 |
text = ""
|
| 54 |
for pdf in pdf_docs:
|
|
@@ -67,35 +64,19 @@ def get_vector_store(text_chunks):
|
|
| 67 |
|
| 68 |
def get_conversational_chain():
|
| 69 |
prompt_template = """
|
| 70 |
-
Responde
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
{context}
|
| 74 |
-
Pregunta:
|
| 75 |
-
{question}
|
| 76 |
-
Respuesta:
|
| 77 |
-
"""
|
| 78 |
-
model = ChatGroq(
|
| 79 |
-
temperature=0.3,
|
| 80 |
-
model_name="deepseek-r1-distill-llama-70b",
|
| 81 |
-
groq_api_key=os.getenv("GROQ_API_KEY")
|
| 82 |
-
)
|
| 83 |
-
return load_qa_chain(model, chain_type="stuff",
|
| 84 |
-
prompt=PromptTemplate(template=prompt_template,
|
| 85 |
-
input_variables=["context", "question"]))
|
| 86 |
-
|
| 87 |
-
def get_metadata_chain():
|
| 88 |
-
prompt_template = """
|
| 89 |
-
Responde ÚNICAMENTE con el dato solicitado usando el contexto. Máximo 5 palabras.
|
| 90 |
-
Si no hay información, responde "No disponible".
|
| 91 |
Contexto:
|
| 92 |
{context}
|
|
|
|
| 93 |
Pregunta:
|
| 94 |
{question}
|
|
|
|
| 95 |
Respuesta:
|
| 96 |
"""
|
| 97 |
model = ChatGroq(
|
| 98 |
-
temperature=0.
|
| 99 |
model_name="deepseek-r1-distill-llama-70b",
|
| 100 |
groq_api_key=os.getenv("GROQ_API_KEY")
|
| 101 |
)
|
|
@@ -103,9 +84,6 @@ def get_metadata_chain():
|
|
| 103 |
prompt=PromptTemplate(template=prompt_template,
|
| 104 |
input_variables=["context", "question"]))
|
| 105 |
|
| 106 |
-
def eliminar_texto_entre_tags(texto):
|
| 107 |
-
return re.sub(r'', '', texto, flags=re.DOTALL)
|
| 108 |
-
|
| 109 |
def extract_metadata(vector_store):
|
| 110 |
metadata_questions = {
|
| 111 |
"title": "¿Cuál es el título principal del documento?",
|
|
@@ -114,7 +92,7 @@ def extract_metadata(vector_store):
|
|
| 114 |
}
|
| 115 |
|
| 116 |
metadata = {}
|
| 117 |
-
chain =
|
| 118 |
|
| 119 |
for key, question in metadata_questions.items():
|
| 120 |
docs = vector_store.similarity_search(question, k=2)
|
|
@@ -122,24 +100,32 @@ def extract_metadata(vector_store):
|
|
| 122 |
{"input_documents": docs, "question": question},
|
| 123 |
return_only_outputs=True
|
| 124 |
)
|
| 125 |
-
clean_response =
|
| 126 |
metadata[key] = clean_response if clean_response else "No disponible"
|
| 127 |
|
| 128 |
return metadata
|
| 129 |
|
| 130 |
-
def
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
if 'vector_store' not in st.session_state:
|
| 132 |
st.error("Por favor carga un documento primero")
|
| 133 |
return
|
| 134 |
|
|
|
|
| 135 |
docs = st.session_state.vector_store.similarity_search(user_question)
|
| 136 |
-
response = get_conversational_chain()(
|
| 137 |
-
{"input_documents": docs, "question": user_question},
|
| 138 |
-
return_only_outputs=True
|
| 139 |
-
)
|
| 140 |
|
| 141 |
-
|
| 142 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 143 |
|
| 144 |
def main():
|
| 145 |
st.set_page_config(page_title="PDF Consultor 🔍", page_icon="🔍", layout="wide")
|
|
@@ -147,65 +133,79 @@ def main():
|
|
| 147 |
st.markdown(css_style, unsafe_allow_html=True)
|
| 148 |
|
| 149 |
# Sidebar - Carga de documentos
|
| 150 |
-
st.sidebar
|
| 151 |
-
|
| 152 |
-
|
| 153 |
-
|
| 154 |
-
|
| 155 |
-
|
| 156 |
-
|
|
|
|
| 157 |
|
| 158 |
# Procesamiento automático al cargar documentos
|
| 159 |
-
if pdf_docs and
|
| 160 |
with st.spinner("Analizando documento..."):
|
| 161 |
try:
|
| 162 |
-
# Procesamiento de texto
|
| 163 |
raw_text = get_pdf_text(pdf_docs)
|
| 164 |
text_chunks = get_text_chunks(raw_text)
|
| 165 |
vector_store = get_vector_store(text_chunks)
|
| 166 |
|
| 167 |
-
# Extracción de metadatos
|
| 168 |
st.session_state.metadata = extract_metadata(vector_store)
|
| 169 |
st.session_state.vector_store = vector_store
|
| 170 |
st.session_state.processed = True
|
| 171 |
|
|
|
|
|
|
|
| 172 |
except Exception as e:
|
| 173 |
st.error(f"Error procesando documento: {str(e)}")
|
| 174 |
|
| 175 |
# Mostrar metadatos
|
| 176 |
if 'metadata' in st.session_state:
|
| 177 |
st.markdown("---")
|
| 178 |
-
st.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 179 |
|
| 180 |
-
|
| 181 |
-
|
| 182 |
-
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
|
|
|
| 187 |
st.markdown("---")
|
| 188 |
|
| 189 |
-
# Interfaz de
|
| 190 |
-
st.
|
| 191 |
-
|
| 192 |
-
|
| 193 |
-
|
| 194 |
-
|
| 195 |
-
|
| 196 |
-
|
| 197 |
-
|
| 198 |
-
|
| 199 |
-
|
| 200 |
-
|
| 201 |
-
|
| 202 |
-
|
| 203 |
-
|
| 204 |
-
|
| 205 |
-
|
| 206 |
-
|
| 207 |
-
|
| 208 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 209 |
|
| 210 |
if __name__ == "__main__":
|
| 211 |
main()
|
|
|
|
|
|
| 19 |
font-size: 24px;
|
| 20 |
font-weight: bold;
|
| 21 |
}
|
| 22 |
+
.response-box {
|
| 23 |
+
padding: 20px;
|
| 24 |
+
background-color: #f8f9fa;
|
| 25 |
+
border-radius: 10px;
|
| 26 |
+
border-left: 5px solid #252850;
|
| 27 |
+
margin: 20px 0;
|
| 28 |
+
box-shadow: 0 2px 4px rgba(0,0,0,0.1);
|
| 29 |
+
}
|
| 30 |
.metadata-box {
|
| 31 |
padding: 20px;
|
| 32 |
background-color: #f0f2f6;
|
| 33 |
border-radius: 10px;
|
| 34 |
margin-bottom: 20px;
|
| 35 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
.custom-input {
|
| 37 |
font-size: 16px;
|
| 38 |
padding: 10px;
|
|
|
|
| 42 |
</style>
|
| 43 |
"""
|
| 44 |
|
| 45 |
+
def eliminar_proceso_pensamiento(texto):
|
| 46 |
+
"""Elimina todo contenido entre incluyendo las etiquetas"""
|
| 47 |
+
return re.sub(r'', '', texto, flags=re.DOTALL).strip()
|
| 48 |
+
|
| 49 |
def get_pdf_text(pdf_docs):
|
| 50 |
text = ""
|
| 51 |
for pdf in pdf_docs:
|
|
|
|
| 64 |
|
| 65 |
def get_conversational_chain():
|
| 66 |
prompt_template = """
|
| 67 |
+
Responde en español exclusivamente con la información solicitada usando el contexto.
|
| 68 |
+
Formato: Respuesta directa sin prefijos. Si no hay información, di "No disponible".
|
| 69 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 70 |
Contexto:
|
| 71 |
{context}
|
| 72 |
+
|
| 73 |
Pregunta:
|
| 74 |
{question}
|
| 75 |
+
|
| 76 |
Respuesta:
|
| 77 |
"""
|
| 78 |
model = ChatGroq(
|
| 79 |
+
temperature=0.2,
|
| 80 |
model_name="deepseek-r1-distill-llama-70b",
|
| 81 |
groq_api_key=os.getenv("GROQ_API_KEY")
|
| 82 |
)
|
|
|
|
| 84 |
prompt=PromptTemplate(template=prompt_template,
|
| 85 |
input_variables=["context", "question"]))
|
| 86 |
|
|
|
|
|
|
|
|
|
|
| 87 |
def extract_metadata(vector_store):
|
| 88 |
metadata_questions = {
|
| 89 |
"title": "¿Cuál es el título principal del documento?",
|
|
|
|
| 92 |
}
|
| 93 |
|
| 94 |
metadata = {}
|
| 95 |
+
chain = get_conversational_chain()
|
| 96 |
|
| 97 |
for key, question in metadata_questions.items():
|
| 98 |
docs = vector_store.similarity_search(question, k=2)
|
|
|
|
| 100 |
{"input_documents": docs, "question": question},
|
| 101 |
return_only_outputs=True
|
| 102 |
)
|
| 103 |
+
clean_response = eliminar_proceso_pensamiento(response['output_text'])
|
| 104 |
metadata[key] = clean_response if clean_response else "No disponible"
|
| 105 |
|
| 106 |
return metadata
|
| 107 |
|
| 108 |
+
def mostrar_respuesta(texto):
|
| 109 |
+
"""Muestra la respuesta formateada en un contenedor especial"""
|
| 110 |
+
with st.container():
|
| 111 |
+
st.markdown(f'<div class="response-box">{texto}</div>', unsafe_allow_html=True)
|
| 112 |
+
|
| 113 |
+
def procesar_consulta(user_question):
|
| 114 |
if 'vector_store' not in st.session_state:
|
| 115 |
st.error("Por favor carga un documento primero")
|
| 116 |
return
|
| 117 |
|
| 118 |
+
chain = get_conversational_chain()
|
| 119 |
docs = st.session_state.vector_store.similarity_search(user_question)
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
|
| 121 |
+
with st.spinner("Analizando documento..."):
|
| 122 |
+
response = chain(
|
| 123 |
+
{"input_documents": docs, "question": user_question},
|
| 124 |
+
return_only_outputs=True
|
| 125 |
+
)
|
| 126 |
+
|
| 127 |
+
respuesta_final = eliminar_proceso_pensamiento(response['output_text'])
|
| 128 |
+
mostrar_respuesta(respuesta_final)
|
| 129 |
|
| 130 |
def main():
|
| 131 |
st.set_page_config(page_title="PDF Consultor 🔍", page_icon="🔍", layout="wide")
|
|
|
|
| 133 |
st.markdown(css_style, unsafe_allow_html=True)
|
| 134 |
|
| 135 |
# Sidebar - Carga de documentos
|
| 136 |
+
with st.sidebar:
|
| 137 |
+
st.markdown('<p class="step-number">1 Subir archivos</p>', unsafe_allow_html=True)
|
| 138 |
+
pdf_docs = st.file_uploader(
|
| 139 |
+
"Subir PDF(s)",
|
| 140 |
+
accept_multiple_files=True,
|
| 141 |
+
type=["pdf"],
|
| 142 |
+
label_visibility="collapsed"
|
| 143 |
+
)
|
| 144 |
|
| 145 |
# Procesamiento automático al cargar documentos
|
| 146 |
+
if pdf_docs and not st.session_state.get('processed'):
|
| 147 |
with st.spinner("Analizando documento..."):
|
| 148 |
try:
|
|
|
|
| 149 |
raw_text = get_pdf_text(pdf_docs)
|
| 150 |
text_chunks = get_text_chunks(raw_text)
|
| 151 |
vector_store = get_vector_store(text_chunks)
|
| 152 |
|
|
|
|
| 153 |
st.session_state.metadata = extract_metadata(vector_store)
|
| 154 |
st.session_state.vector_store = vector_store
|
| 155 |
st.session_state.processed = True
|
| 156 |
|
| 157 |
+
st.rerun()
|
| 158 |
+
|
| 159 |
except Exception as e:
|
| 160 |
st.error(f"Error procesando documento: {str(e)}")
|
| 161 |
|
| 162 |
# Mostrar metadatos
|
| 163 |
if 'metadata' in st.session_state:
|
| 164 |
st.markdown("---")
|
| 165 |
+
cols = st.columns(3)
|
| 166 |
+
campos = [
|
| 167 |
+
("📄 Título", "title"),
|
| 168 |
+
("🏛️ Entidad", "entity"),
|
| 169 |
+
("📅 Fecha Implantación", "date")
|
| 170 |
+
]
|
| 171 |
|
| 172 |
+
for col, (icono, key) in zip(cols, campos):
|
| 173 |
+
with col:
|
| 174 |
+
st.markdown(f"""
|
| 175 |
+
<div class="metadata-box">
|
| 176 |
+
<div class="metadata-title">{icono}</div>
|
| 177 |
+
{st.session_state.metadata[key]}
|
| 178 |
+
</div>
|
| 179 |
+
""", unsafe_allow_html=True)
|
| 180 |
st.markdown("---")
|
| 181 |
|
| 182 |
+
# Interfaz de consultas
|
| 183 |
+
with st.form("consulta_form"):
|
| 184 |
+
col1, col2 = st.columns([5, 1])
|
| 185 |
+
with col1:
|
| 186 |
+
user_question = st.text_input(
|
| 187 |
+
"Escribe tu pregunta:",
|
| 188 |
+
placeholder="Ej: ¿Qué normativa regula este proceso?",
|
| 189 |
+
label_visibility="collapsed"
|
| 190 |
+
)
|
| 191 |
+
with col2:
|
| 192 |
+
st.markdown("<br>", unsafe_allow_html=True)
|
| 193 |
+
enviar = st.form_submit_button("Enviar ▶")
|
| 194 |
+
|
| 195 |
+
botones_rapidos = st.columns(3)
|
| 196 |
+
with botones_rapidos[0]:
|
| 197 |
+
if st.form_submit_button("📝 Resumen ejecutivo"):
|
| 198 |
+
user_question = "Genera un resumen ejecutivo de máximo 3 párrafos"
|
| 199 |
+
with botones_rapidos[1]:
|
| 200 |
+
if st.form_submit_button("🏛️ Entidad relacionada"):
|
| 201 |
+
user_question = "¿A qué organización o entidad pertenece este documento?"
|
| 202 |
+
with botones_rapidos[2]:
|
| 203 |
+
if st.form_submit_button("📅 Fechas clave"):
|
| 204 |
+
user_question = "Lista las fechas importantes mencionadas en orden cronológico"
|
| 205 |
+
|
| 206 |
+
if user_question and enviar:
|
| 207 |
+
procesar_consulta(user_question)
|
| 208 |
|
| 209 |
if __name__ == "__main__":
|
| 210 |
main()
|
| 211 |
+
|