Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,85 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+venv/bin/python filter=lfs diff=lfs merge=lfs -text
+venv/bin/python3 filter=lfs diff=lfs merge=lfs -text
+venv/bin/python3.11 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/Pillow.libs/libfreetype-cb9caf6f.so.6.19.0 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/Pillow.libs/libharfbuzz-3543f599.so.0.60710.0 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/_cffi_backend.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/_pulsar.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/aiohttp/_http_parser.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/altair/vegalite/v5/schema/__pycache__/core.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/bcrypt/_bcrypt.abi3.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/cryptography/hazmat/bindings/_rust.abi3.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/emoji/unicode_codes/__pycache__/data_dict.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/faiss/_swigfaiss.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/faiss/_swigfaiss_avx2.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/faiss_cpu.libs/libgfortran-040039e1.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/fontTools/cu2qu/cu2qu.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/fontTools/feaLib/lexer.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/fontTools/misc/bezierTools.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/fontTools/pens/momentsPen.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/fontTools/qu2cu/qu2cu.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/fontTools/varLib/iup.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/gradio/frpc_linux_amd64_v0.2 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/gradio/templates/cdn/assets/index-1d5a0c4a.js.map filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/gradio/templates/frontend/assets/index-a9692bd2.js.map filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/greenlet/_greenlet.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/hnswlib.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/kiwisolver/_cext.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/lxml/etree.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/lxml/objectify.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/matplotlib/_image.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/matplotlib/_path.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/matplotlib/_qhull.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/matplotlib/backends/_backend_agg.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/matplotlib/ft2font.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/numexpr/interpreter.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/numpy/core/_multiarray_umath.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/numpy/core/_simd.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/numpy/random/_generator.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/numpy.libs/libgfortran-040039e1.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/numpy.libs/libopenblas64_p-r0-5007b62f.3.23.dev.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/onnxruntime/capi/onnxruntime_pybind11_state.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pandas/_libs/algos.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pandas/_libs/groupby.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pandas/_libs/hashtable.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pandas/_libs/interval.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pandas/_libs/join.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pulsar_client.libs/libpulsar-07bd3920.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/_compute.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/_flight.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/lib.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/libarrow.so.1300 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/libarrow_acero.so.1300 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/libarrow_dataset.so.1300 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/libarrow_flight.so.1300 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/libarrow_python.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/libarrow_substrait.so.1300 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pyarrow/libparquet.so.1300 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pydantic_core/_pydantic_core.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/pypdfium2/pdfium filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/regex/_regex.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/rpds/rpds.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/fft/_pocketfft/pypocketfft.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/linalg/_flapack.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/misc/face.dat filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/optimize/_highs/_highs_wrapper.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/sparse/_sparsetools.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/spatial/_ckdtree.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/spatial/_qhull.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/special/_ufuncs.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/special/cython_special.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy/stats/_unuran/unuran_wrapper.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy.libs/libgfortran-040039e1.so.5.0.0 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/scipy.libs/libopenblasp-r0-23e5df77.3.21.dev.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/sqlalchemy/cyextension/collections.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/sympy/polys/benchmarks/__pycache__/bench_solvers.cpython-311.pyc filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/tiktoken/_tiktoken.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/tokenizers/tokenizers.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/tokenizers.libs/libcrypto-d3570994.so.1.0.2k filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/tokenizers.libs/libkrb5-fcafa220.so.3.3 filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/uvloop/loop.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/watchfiles/_rust_notify.abi3.so filter=lfs diff=lfs merge=lfs -text
+venv/lib/python3.11/site-packages/yaml/_yaml.cpython-311-x86_64-linux-gnu.so filter=lfs diff=lfs merge=lfs -text

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/customChatBotDemo.iml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$">
+      <excludeFolder url="file://$MODULE_DIR$/venv" />
+    </content>
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11 (customChatBotDemo)" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/customChatBotDemo.iml" filepath="$PROJECT_DIR$/.idea/customChatBotDemo.iml" />
+    </modules>
+  </component>
+</project>

.idea/workspace.xml

@@ -0,0 +1,81 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="AutoImportSettings">
+    <option name="autoReloadType" value="SELECTIVE" />
+  </component>
+  <component name="ChangeListManager">
+    <list default="true" id="389d532e-4eaf-4367-8bd6-095ab4d8b955" name="Changes" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="FileTemplateManagerImpl">
+    <option name="RECENT_TEMPLATES">
+      <list>
+        <option value="Python Script" />
+      </list>
+    </option>
+  </component>
+  <component name="ProjectColorInfo">{
+  &quot;associatedIndex&quot;: 6
+}</component>
+  <component name="ProjectId" id="2UfxHqM9G5VUMOOUNXWACjL1huw" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;RunOnceActivity.OpenProjectViewOnStart&quot;: &quot;true&quot;,
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;WebServerToolWindowFactoryState&quot;: &quot;false&quot;,
+    &quot;node.js.detected.package.eslint&quot;: &quot;true&quot;,
+    &quot;node.js.detected.package.tslint&quot;: &quot;true&quot;,
+    &quot;node.js.selected.package.eslint&quot;: &quot;(autodetect)&quot;,
+    &quot;node.js.selected.package.tslint&quot;: &quot;(autodetect)&quot;,
+    &quot;settings.editor.selected.configurable&quot;: &quot;preferences.pluginManager&quot;,
+    &quot;vue.rearranger.settings.migration&quot;: &quot;true&quot;
+  }
+}</component>
+  <component name="RunManager">
+    <configuration name="main" type="PythonConfigurationType" factoryName="Python" nameIsGenerated="true">
+      <module name="customChatBotDemo" />
+      <option name="INTERPRETER_OPTIONS" value="" />
+      <option name="PARENT_ENVS" value="true" />
+      <envs>
+        <env name="PYTHONUNBUFFERED" value="1" />
+      </envs>
+      <option name="SDK_HOME" value="" />
+      <option name="WORKING_DIRECTORY" value="$PROJECT_DIR$" />
+      <option name="IS_MODULE_SDK" value="true" />
+      <option name="ADD_CONTENT_ROOTS" value="true" />
+      <option name="ADD_SOURCE_ROOTS" value="true" />
+      <EXTENSION ID="PythonCoverageRunConfigurationExtension" runner="coverage.py" />
+      <option name="SCRIPT_NAME" value="$PROJECT_DIR$/main.py" />
+      <option name="PARAMETERS" value="" />
+      <option name="SHOW_COMMAND_LINE" value="false" />
+      <option name="EMULATE_TERMINAL" value="false" />
+      <option name="MODULE_MODE" value="false" />
+      <option name="REDIRECT_INPUT" value="false" />
+      <option name="INPUT_FILE" value="" />
+      <method v="2" />
+    </configuration>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="389d532e-4eaf-4367-8bd6-095ab4d8b955" name="Changes" comment="" />
+      <created>1693344351359</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1693344351359</updated>
+      <workItem from="1693344352959" duration="1601000" />
+      <workItem from="1693345962391" duration="234000" />
+    </task>
+    <servers />
+  </component>
+  <component name="TypeScriptGeneratedFilesManager">
+    <option name="version" value="3" />
+  </component>
+</project>

README.md

@@ -1,12 +1,6 @@
 ---
 title: PonchoBotDemo
-emoji: 💻
-colorFrom: purple
-colorTo: purple
+app_file: main.py
 sdk: gradio
 sdk_version: 3.41.2
-app_file: app.py
-pinned: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

constants.py

@@ -0,0 +1 @@
+APIKEY = "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"

data/data.txt

@@ -0,0 +1,47 @@
+SOBRE MÍ - EL BOT DEL BANCO ESTRELLA
+
+¡Hola! Soy EstrellaBot, la inteligencia artificial del Banco de Poncho. Estoy aquí para ayudarte en todo lo relacionado con nuestros servicios y productos financieros. Fui diseñado para ofrecer respuestas precisas y rápidas, garantizando que tu experiencia con nosotros sea brillante. Si tienes alguna duda o consulta, no dudes en preguntarme. ¡Estoy aquí para iluminar tu camino financiero!
+
+INFORMACIÓN GENERAL DEL BANCO
+
+Nombre del banco: Banco de Poncho.
+Misión: Facilitar soluciones financieras brillantes a todos nuestros clientes, guiándolos hacia un futuro próspero.
+Visión: Ser el banco líder en innovación y servicio al cliente en el sector financiero.
+PRODUCTOS Y SERVICIOS
+
+Cuentas Bancarias:
+
+Cuenta Corriente: Sin comisiones por manejo de cuenta y acceso a banca en línea.
+Cuenta de Ahorro Estelares: Tasa de interés del 3.5% anual, sin comisiones si mantienes un mínimo de [X dinero].
+Opciones de Inversión:
+
+Fondos Mutuos Dorados: Diversificación de inversiones con rentabilidad estimada entre 5-8% anual.
+Depósitos a Plazo: Duración flexible con tasas de interés competitivas.
+Préstamos:
+
+Préstamos Personales: Desde [X dinero] hasta [X dinero] con tasas a partir del 5% anual.
+Hipotecarios: Financiamiento hasta el 80% del valor de la propiedad, con tasas desde el 4% anual.
+Para Empresas: Soluciones personalizadas para pequeñas y grandes empresas.
+Tarjetas de Crédito:
+
+Tarjeta Estrella: Sin cuota anual el primer año, programa de recompensas con acumulación de puntos por cada compra.
+Tarjeta Estrella Gold: Beneficios premium, acceso a salas VIP en aeropuertos y asistencia personalizada.
+SERVICIOS EN LÍNEA
+
+Banca en línea: Acceso 24/7 a tu cuenta, transferencias, consulta de saldos y movimientos.
+Aplicación móvil: Realiza operaciones desde tu smartphone, localiza cajeros y sucursales cercanas.
+Asistencia virtual: Nuestro bot, siempre disponible para responder tus dudas y brindarte la mejor experiencia.
+SEGURIDAD
+
+Protección: Contamos con sistemas avanzados de cifrado y protección contra fraudes.
+Alertas: Notificaciones en tiempo real para cualquier actividad inusual en tus cuentas.
+Autenticación: Procesos de verificación en dos pasos para garantizar tu seguridad en línea.
+CONTACTO
+
+Atención al cliente: Llámanos al [Número de teléfono] o escríbenos a [Email de atención al cliente].
+Sucursales: Más de [X número] de sucursales en todo el país. Encuentra la más cercana en nuestro sitio web.
+PREGUNTAS FRECUENTES
+
+¿Cómo abro una cuenta?: Solo necesitas tu identificación, comprobante de domicilio y acudir a tu sucursal más cercana.
+¿Puedo transferir dinero a otros bancos?: Sí, mediante nuestro sistema en línea puedes realizar transferencias interbancarias.
+¿Qué hago si pierdo mi tarjeta?: Llámanos de inmediato al [Número de emergencia] para bloquearla y proteger tu dinero.

flagged/log.csv

@@ -0,0 +1,2 @@
+question,output,flag,username,timestamp
+quien eres,"¡Hola! Soy EstrellaBot, la inteligencia artificial del Banco de Poncho. Estoy aquí para ayudarte en todo lo relacionado con nuestros servicios y productos financieros.",,,2023-08-29 15:57:16.002129

main.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import os
+import openai
+from langchain.chains import ConversationalRetrievalChain
+from langchain.chat_models import ChatOpenAI
+from langchain.document_loaders import DirectoryLoader
+from langchain.indexes.vectorstore import VectorStoreIndexWrapper
+from langchain.indexes import VectorstoreIndexCreator
+from langchain.llms import OpenAI
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores.chroma import Chroma
+import constants
+
+os.environ["OPENAI_API_KEY"] = constants.APIKEY
+
+PERSIST = False
+
+if PERSIST and os.path.exists("persist"):
+    print("Reusing index...\n")
+    vectorstore = Chroma(persist_directory="persist", embedding_function=OpenAIEmbeddings())
+    index = VectorStoreIndexWrapper(vectorstore=vectorstore)
+    index.load("persist")
+else:
+    loader = DirectoryLoader("data/")
+    if PERSIST:
+        index = VectorstoreIndexCreator(vectorstore_kwargs={"persist_directory": "persist"}).from_loaders([loader])
+    else:
+        index = VectorstoreIndexCreator().from_loaders([loader])
+
+use_gpt_4 = True
+model_name = "gpt-4" if use_gpt_4 else "gpt-3.5-turbo"
+chain = ConversationalRetrievalChain.from_llm(llm=ChatOpenAI(model=model_name),
+                                              retriever=index.vectorstore.as_retriever(search_kwargs={"k": 1}))
+
+chat_history = []
+
+
+def answer_question(question):
+    global chat_history
+    result = chain({"question": question, "chat_history": chat_history})
+    chat_history.append((question, result['answer']))
+    return result['answer']
+
+
+iface = gr.Interface(
+    fn=answer_question,
+    inputs="text",
+    outputs="text",
+    title="Demo IA Conversacional",
+    description="Pregúntame lo que quieras, te responderé con lo que sé."
+)
+
+iface.launch(share=True)

requirements.txt

@@ -0,0 +1,12 @@
+langchain==0.0.276
+openai==0.27.9
+pandasai==1.0.9
+pdfplumber
+pypdf==3.15.4
+streamlit==1.26.0
+streamlit-chat==0.1.1
+tiktoken==0.4.0
+youtube-transcript-api==0.6.1
+faiss-cpu
+gradio
+unstructured

venv/.gitignore

@@ -0,0 +1,2 @@
+# created by virtualenv automatically
+*

venv/bin/activate

@@ -0,0 +1,83 @@
+# This file must be used with "source bin/activate" *from bash*
+# you cannot run it directly
+
+
+if [ "${BASH_SOURCE-}" = "$0" ]; then
+    echo "You must source this script: \$ source $0" >&2
+    exit 33
+fi
+
+deactivate () {
+    unset -f pydoc >/dev/null 2>&1 || true
+
+    # reset old environment variables
+    # ! [ -z ${VAR+_} ] returns true if VAR is declared at all
+    if ! [ -z "${_OLD_VIRTUAL_PATH:+_}" ] ; then
+        PATH="$_OLD_VIRTUAL_PATH"
+        export PATH
+        unset _OLD_VIRTUAL_PATH
+    fi
+    if ! [ -z "${_OLD_VIRTUAL_PYTHONHOME+_}" ] ; then
+        PYTHONHOME="$_OLD_VIRTUAL_PYTHONHOME"
+        export PYTHONHOME
+        unset _OLD_VIRTUAL_PYTHONHOME
+    fi
+
+    # The hash command must be called to get it to forget past
+    # commands. Without forgetting past commands the $PATH changes
+    # we made may not be respected
+    hash -r 2>/dev/null
+
+    if ! [ -z "${_OLD_VIRTUAL_PS1+_}" ] ; then
+        PS1="$_OLD_VIRTUAL_PS1"
+        export PS1
+        unset _OLD_VIRTUAL_PS1
+    fi
+
+    unset VIRTUAL_ENV
+    if [ ! "${1-}" = "nondestructive" ] ; then
+    # Self destruct!
+        unset -f deactivate
+    fi
+}
+
+# unset irrelevant variables
+deactivate nondestructive
+
+VIRTUAL_ENV='/home/draco/PycharmProjects/customChatBotDemo/venv'
+if ([ "$OSTYPE" = "cygwin" ] || [ "$OSTYPE" = "msys" ]) && $(command -v cygpath &> /dev/null) ; then
+    VIRTUAL_ENV=$(cygpath -u "$VIRTUAL_ENV")
+fi
+export VIRTUAL_ENV
+
+_OLD_VIRTUAL_PATH="$PATH"
+PATH="$VIRTUAL_ENV/bin:$PATH"
+export PATH
+
+# unset PYTHONHOME if set
+if ! [ -z "${PYTHONHOME+_}" ] ; then
+    _OLD_VIRTUAL_PYTHONHOME="$PYTHONHOME"
+    unset PYTHONHOME
+fi
+
+if [ -z "${VIRTUAL_ENV_DISABLE_PROMPT-}" ] ; then
+    _OLD_VIRTUAL_PS1="${PS1-}"
+    if [ "x" != x ] ; then
+        PS1="() ${PS1-}"
+    else
+        PS1="(`basename \"$VIRTUAL_ENV\"`) ${PS1-}"
+    fi
+    export PS1
+fi
+
+# Make sure to unalias pydoc if it's already there
+alias pydoc 2>/dev/null >/dev/null && unalias pydoc || true
+
+pydoc () {
+    python -m pydoc "$@"
+}
+
+# The hash command must be called to get it to forget past
+# commands. Without forgetting past commands the $PATH changes
+# we made may not be respected
+hash -r 2>/dev/null

venv/bin/activate.csh

@@ -0,0 +1,55 @@
+# This file must be used with "source bin/activate.csh" *from csh*.
+# You cannot run it directly.
+# Created by Davide Di Blasi <davidedb@gmail.com>.
+
+set newline='\
+'
+
+alias deactivate 'test $?_OLD_VIRTUAL_PATH != 0 && setenv PATH "$_OLD_VIRTUAL_PATH:q" && unset _OLD_VIRTUAL_PATH; rehash; test $?_OLD_VIRTUAL_PROMPT != 0 && set prompt="$_OLD_VIRTUAL_PROMPT:q" && unset _OLD_VIRTUAL_PROMPT; unsetenv VIRTUAL_ENV; test "\!:*" != "nondestructive" && unalias deactivate && unalias pydoc'
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+setenv VIRTUAL_ENV '/home/draco/PycharmProjects/customChatBotDemo/venv'
+
+set _OLD_VIRTUAL_PATH="$PATH:q"
+setenv PATH "$VIRTUAL_ENV:q/bin:$PATH:q"
+
+
+
+if ('' != "") then
+    set env_name = '() '
+else
+    set env_name = '('"$VIRTUAL_ENV:t:q"') '
+endif
+
+if ( $?VIRTUAL_ENV_DISABLE_PROMPT ) then
+    if ( $VIRTUAL_ENV_DISABLE_PROMPT == "" ) then
+        set do_prompt = "1"
+    else
+        set do_prompt = "0"
+    endif
+else
+    set do_prompt = "1"
+endif
+
+if ( $do_prompt == "1" ) then
+    # Could be in a non-interactive environment,
+    # in which case, $prompt is undefined and we wouldn't
+    # care about the prompt anyway.
+    if ( $?prompt ) then
+        set _OLD_VIRTUAL_PROMPT="$prompt:q"
+        if ( "$prompt:q" =~ *"$newline:q"* ) then
+            :
+        else
+            set prompt = "$env_name:q$prompt:q"
+        endif
+    endif
+endif
+
+unset env_name
+unset do_prompt
+
+alias pydoc python -m pydoc
+
+rehash

venv/bin/activate.fish

@@ -0,0 +1,100 @@
+# This file must be used using `source bin/activate.fish` *within a running fish ( http://fishshell.com ) session*.
+# Do not run it directly.
+
+function _bashify_path -d "Converts a fish path to something bash can recognize"
+    set fishy_path $argv
+    set bashy_path $fishy_path[1]
+    for path_part in $fishy_path[2..-1]
+        set bashy_path "$bashy_path:$path_part"
+    end
+    echo $bashy_path
+end
+
+function _fishify_path -d "Converts a bash path to something fish can recognize"
+    echo $argv | tr ':' '\n'
+end
+
+function deactivate -d 'Exit virtualenv mode and return to the normal environment.'
+    # reset old environment variables
+    if test -n "$_OLD_VIRTUAL_PATH"
+        # https://github.com/fish-shell/fish-shell/issues/436 altered PATH handling
+        if test (echo $FISH_VERSION | head -c 1) -lt 3
+            set -gx PATH (_fishify_path "$_OLD_VIRTUAL_PATH")
+        else
+            set -gx PATH $_OLD_VIRTUAL_PATH
+        end
+        set -e _OLD_VIRTUAL_PATH
+    end
+
+    if test -n "$_OLD_VIRTUAL_PYTHONHOME"
+        set -gx PYTHONHOME "$_OLD_VIRTUAL_PYTHONHOME"
+        set -e _OLD_VIRTUAL_PYTHONHOME
+    end
+
+    if test -n "$_OLD_FISH_PROMPT_OVERRIDE"
+       and functions -q _old_fish_prompt
+        # Set an empty local `$fish_function_path` to allow the removal of `fish_prompt` using `functions -e`.
+        set -l fish_function_path
+
+        # Erase virtualenv's `fish_prompt` and restore the original.
+        functions -e fish_prompt
+        functions -c _old_fish_prompt fish_prompt
+        functions -e _old_fish_prompt
+        set -e _OLD_FISH_PROMPT_OVERRIDE
+    end
+
+    set -e VIRTUAL_ENV
+
+    if test "$argv[1]" != 'nondestructive'
+        # Self-destruct!
+        functions -e pydoc
+        functions -e deactivate
+        functions -e _bashify_path
+        functions -e _fishify_path
+    end
+end
+
+# Unset irrelevant variables.
+deactivate nondestructive
+
+set -gx VIRTUAL_ENV '/home/draco/PycharmProjects/customChatBotDemo/venv'
+
+# https://github.com/fish-shell/fish-shell/issues/436 altered PATH handling
+if test (echo $FISH_VERSION | head -c 1) -lt 3
+   set -gx _OLD_VIRTUAL_PATH (_bashify_path $PATH)
+else
+    set -gx _OLD_VIRTUAL_PATH $PATH
+end
+set -gx PATH "$VIRTUAL_ENV"'/bin' $PATH
+
+# Unset `$PYTHONHOME` if set.
+if set -q PYTHONHOME
+    set -gx _OLD_VIRTUAL_PYTHONHOME $PYTHONHOME
+    set -e PYTHONHOME
+end
+
+function pydoc
+    python -m pydoc $argv
+end
+
+if test -z "$VIRTUAL_ENV_DISABLE_PROMPT"
+    # Copy the current `fish_prompt` function as `_old_fish_prompt`.
+    functions -c fish_prompt _old_fish_prompt
+
+    function fish_prompt
+        # Run the user's prompt first; it might depend on (pipe)status.
+        set -l prompt (_old_fish_prompt)
+
+        # Prompt override provided?
+        # If not, just prepend the environment name.
+        if test -n ''
+            printf '(%s) ' ''
+        else
+            printf '(%s) ' (basename "$VIRTUAL_ENV")
+        end
+
+        string join -- \n $prompt # handle multi-line prompts
+    end
+
+    set -gx _OLD_FISH_PROMPT_OVERRIDE "$VIRTUAL_ENV"
+end

venv/bin/activate.nu

@@ -0,0 +1,92 @@
+# This command prepares the required environment variables
+def-env activate-virtualenv [] {
+    def is-string [x] {
+        ($x | describe) == 'string'
+    }
+
+    def has-env [name: string] {
+        $name in (env).name
+    }
+
+    let is_windows = ((sys).host.name | str downcase) == 'windows'
+    let virtual_env = '/home/draco/PycharmProjects/customChatBotDemo/venv'
+    let bin = 'bin'
+    let path_sep = ':'
+    let path_name = if $is_windows {
+        if (has-env 'Path') {
+            'Path'
+        } else {
+            'PATH'
+        }
+    } else {
+        'PATH'
+    }
+
+    let old_path = (
+        if $is_windows {
+            if (has-env 'Path') {
+                $env.Path
+            } else {
+                $env.PATH
+            }
+        } else {
+            $env.PATH
+        } | if (is-string $in) {
+            # if Path/PATH is a string, make it a list
+            $in | split row $path_sep | path expand
+        } else {
+            $in
+        }
+    )
+
+    let venv_path = ([$virtual_env $bin] | path join)
+    let new_path = ($old_path | prepend $venv_path | str collect $path_sep)
+
+    # Creating the new prompt for the session
+    let virtual_prompt = if ('' == '') {
+        $'(char lparen)($virtual_env | path basename)(char rparen) '
+    } else {
+        '() '
+    }
+
+    # Back up the old prompt builder
+    let old_prompt_command = if (has-env 'VIRTUAL_ENV') && (has-env '_OLD_PROMPT_COMMAND') {
+        $env._OLD_PROMPT_COMMAND
+    } else {
+        if (has-env 'PROMPT_COMMAND') {
+            $env.PROMPT_COMMAND
+        } else {
+            ''
+        }
+    }
+
+    # If there is no default prompt, then only the env is printed in the prompt
+    let new_prompt = if (has-env 'PROMPT_COMMAND') {
+        if ($old_prompt_command | describe) == 'block' {
+            { $'($virtual_prompt)(do $old_prompt_command)' }
+        } else {
+            { $'($virtual_prompt)($old_prompt_command)' }
+        }
+    } else {
+        { $'($virtual_prompt)' }
+    }
+
+    # Environment variables that will be batched loaded to the virtual env
+    let new_env = {
+        $path_name          : $new_path
+        VIRTUAL_ENV         : $virtual_env
+        _OLD_VIRTUAL_PATH   : ($old_path | str collect $path_sep)
+        _OLD_PROMPT_COMMAND : $old_prompt_command
+        PROMPT_COMMAND      : $new_prompt
+        VIRTUAL_PROMPT      : $virtual_prompt
+    }
+
+    # Activate the environment variables
+    load-env $new_env
+}
+
+# Activate the virtualenv
+activate-virtualenv
+
+alias pydoc = python -m pydoc
+alias deactivate = source '/home/draco/PycharmProjects/customChatBotDemo/venv/bin/deactivate.nu'

venv/bin/activate.ps1

@@ -0,0 +1,60 @@
+$script:THIS_PATH = $myinvocation.mycommand.path
+$script:BASE_DIR = Split-Path (Resolve-Path "$THIS_PATH/..") -Parent
+
+function global:deactivate([switch] $NonDestructive) {
+    if (Test-Path variable:_OLD_VIRTUAL_PATH) {
+        $env:PATH = $variable:_OLD_VIRTUAL_PATH
+        Remove-Variable "_OLD_VIRTUAL_PATH" -Scope global
+    }
+
+    if (Test-Path function:_old_virtual_prompt) {
+        $function:prompt = $function:_old_virtual_prompt
+        Remove-Item function:\_old_virtual_prompt
+    }
+
+    if ($env:VIRTUAL_ENV) {
+        Remove-Item env:VIRTUAL_ENV -ErrorAction SilentlyContinue
+    }
+
+    if (!$NonDestructive) {
+        # Self destruct!
+        Remove-Item function:deactivate
+        Remove-Item function:pydoc
+    }
+}
+
+function global:pydoc {
+    python -m pydoc $args
+}
+
+# unset irrelevant variables
+deactivate -nondestructive
+
+$VIRTUAL_ENV = $BASE_DIR
+$env:VIRTUAL_ENV = $VIRTUAL_ENV
+
+New-Variable -Scope global -Name _OLD_VIRTUAL_PATH -Value $env:PATH
+
+$env:PATH = "$env:VIRTUAL_ENV/bin:" + $env:PATH
+if (!$env:VIRTUAL_ENV_DISABLE_PROMPT) {
+    function global:_old_virtual_prompt {
+        ""
+    }
+    $function:_old_virtual_prompt = $function:prompt
+
+    if ("" -ne "") {
+        function global:prompt {
+            # Add the custom prefix to the existing prompt
+            $previous_prompt_value = & $function:_old_virtual_prompt
+            ("() " + $previous_prompt_value)
+        }
+    }
+    else {
+        function global:prompt {
+            # Add a prefix to the current prompt, but don't discard it.
+            $previous_prompt_value = & $function:_old_virtual_prompt
+            $new_prompt_value = "($( Split-Path $env:VIRTUAL_ENV -Leaf )) "
+            ($new_prompt_value + $previous_prompt_value)
+        }
+    }
+}

venv/bin/activate_this.py

@@ -0,0 +1,31 @@
+"""Activate virtualenv for current interpreter:
+
+Use exec(open(this_file).read(), {'__file__': this_file}).
+
+This can be used when you must use an existing Python interpreter, not the virtualenv bin/python.
+"""
+import os
+import site
+import sys
+
+try:
+    abs_file = os.path.abspath(__file__)
+except NameError:
+    raise AssertionError("You must use exec(open(this_file).read(), {'__file__': this_file}))")
+
+bin_dir = os.path.dirname(abs_file)
+base = bin_dir[: -len("bin") - 1]  # strip away the bin part from the __file__, plus the path separator
+
+# prepend bin to PATH (this file is inside the bin directory)
+os.environ["PATH"] = os.pathsep.join([bin_dir] + os.environ.get("PATH", "").split(os.pathsep))
+os.environ["VIRTUAL_ENV"] = base  # virtual env is right above bin directory
+
+# add the virtual environments libraries to the host python import mechanism
+prev_length = len(sys.path)
+for lib in "../lib/python3.11/site-packages".split(os.pathsep):
+    path = os.path.realpath(os.path.join(bin_dir, lib))
+    site.addsitedir(path.decode("utf-8") if "" else path)
+sys.path[:] = sys.path[prev_length:] + sys.path[0:prev_length]
+
+sys.real_prefix = sys.prefix
+sys.prefix = base

venv/bin/chardetect

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from chardet.cli.chardetect import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/coloredlogs

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from coloredlogs.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/deactivate.nu

@@ -0,0 +1,32 @@
+def-env deactivate-virtualenv [] {
+    def has-env [name: string] {
+        $name in (env).name
+    }
+
+    let is_windows = ((sys).host.name | str downcase) == 'windows'
+
+    let path_name = if $is_windows {
+        if (has-env 'Path') {
+            'Path'
+        } else {
+            'PATH'
+        }
+    } else {
+        'PATH'
+    }
+
+    load-env { $path_name : $env._OLD_VIRTUAL_PATH }
+
+    let-env PROMPT_COMMAND = $env._OLD_PROMPT_COMMAND
+
+    # Hiding the environment variables that were created when activating the env
+    hide _OLD_VIRTUAL_PATH
+    hide _OLD_PROMPT_COMMAND
+    hide VIRTUAL_ENV
+    hide VIRTUAL_PROMPT
+}
+
+deactivate-virtualenv
+
+hide pydoc
+hide deactivate

venv/bin/dotenv

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from dotenv.__main__ import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli())

venv/bin/dumppdf.py

@@ -0,0 +1,473 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+"""Extract pdf structure in XML format"""
+import logging
+import os.path
+import re
+import sys
+from typing import Any, Container, Dict, Iterable, List, Optional, TextIO, Union, cast
+from argparse import ArgumentParser
+
+import pdfminer
+from pdfminer.pdfdocument import PDFDocument, PDFNoOutlines, PDFXRefFallback
+from pdfminer.pdfpage import PDFPage
+from pdfminer.pdfparser import PDFParser
+from pdfminer.pdftypes import PDFObjectNotFound, PDFValueError
+from pdfminer.pdftypes import PDFStream, PDFObjRef, resolve1, stream_value
+from pdfminer.psparser import PSKeyword, PSLiteral, LIT
+from pdfminer.utils import isnumber
+
+logging.basicConfig()
+logger = logging.getLogger(__name__)
+
+ESC_PAT = re.compile(r'[\000-\037&<>()"\042\047\134\177-\377]')
+
+
+def escape(s: Union[str, bytes]) -> str:
+    if isinstance(s, bytes):
+        us = str(s, "latin-1")
+    else:
+        us = s
+    return ESC_PAT.sub(lambda m: "&#%d;" % ord(m.group(0)), us)
+
+
+def dumpxml(out: TextIO, obj: object, codec: Optional[str] = None) -> None:
+    if obj is None:
+        out.write("<null />")
+        return
+
+    if isinstance(obj, dict):
+        out.write('<dict size="%d">\n' % len(obj))
+        for (k, v) in obj.items():
+            out.write("<key>%s</key>\n" % k)
+            out.write("<value>")
+            dumpxml(out, v)
+            out.write("</value>\n")
+        out.write("</dict>")
+        return
+
+    if isinstance(obj, list):
+        out.write('<list size="%d">\n' % len(obj))
+        for v in obj:
+            dumpxml(out, v)
+            out.write("\n")
+        out.write("</list>")
+        return
+
+    if isinstance(obj, (str, bytes)):
+        out.write('<string size="%d">%s</string>' % (len(obj), escape(obj)))
+        return
+
+    if isinstance(obj, PDFStream):
+        if codec == "raw":
+            # Bug: writing bytes to text I/O. This will raise TypeError.
+            out.write(obj.get_rawdata())  # type: ignore [arg-type]
+        elif codec == "binary":
+            # Bug: writing bytes to text I/O. This will raise TypeError.
+            out.write(obj.get_data())  # type: ignore [arg-type]
+        else:
+            out.write("<stream>\n<props>\n")
+            dumpxml(out, obj.attrs)
+            out.write("\n</props>\n")
+            if codec == "text":
+                data = obj.get_data()
+                out.write('<data size="%d">%s</data>\n' % (len(data), escape(data)))
+            out.write("</stream>")
+        return
+
+    if isinstance(obj, PDFObjRef):
+        out.write('<ref id="%d" />' % obj.objid)
+        return
+
+    if isinstance(obj, PSKeyword):
+        # Likely bug: obj.name is bytes, not str
+        out.write("<keyword>%s</keyword>" % obj.name)  # type: ignore [str-bytes-safe]
+        return
+
+    if isinstance(obj, PSLiteral):
+        # Likely bug: obj.name may be bytes, not str
+        out.write("<literal>%s</literal>" % obj.name)  # type: ignore [str-bytes-safe]
+        return
+
+    if isnumber(obj):
+        out.write("<number>%s</number>" % obj)
+        return
+
+    raise TypeError(obj)
+
+
+def dumptrailers(
+    out: TextIO, doc: PDFDocument, show_fallback_xref: bool = False
+) -> None:
+    for xref in doc.xrefs:
+        if not isinstance(xref, PDFXRefFallback) or show_fallback_xref:
+            out.write("<trailer>\n")
+            dumpxml(out, xref.get_trailer())
+            out.write("\n</trailer>\n\n")
+    no_xrefs = all(isinstance(xref, PDFXRefFallback) for xref in doc.xrefs)
+    if no_xrefs and not show_fallback_xref:
+        msg = (
+            "This PDF does not have an xref. Use --show-fallback-xref if "
+            "you want to display the content of a fallback xref that "
+            "contains all objects."
+        )
+        logger.warning(msg)
+    return
+
+
+def dumpallobjs(
+    out: TextIO,
+    doc: PDFDocument,
+    codec: Optional[str] = None,
+    show_fallback_xref: bool = False,
+) -> None:
+    visited = set()
+    out.write("<pdf>")
+    for xref in doc.xrefs:
+        for objid in xref.get_objids():
+            if objid in visited:
+                continue
+            visited.add(objid)
+            try:
+                obj = doc.getobj(objid)
+                if obj is None:
+                    continue
+                out.write('<object id="%d">\n' % objid)
+                dumpxml(out, obj, codec=codec)
+                out.write("\n</object>\n\n")
+            except PDFObjectNotFound as e:
+                print("not found: %r" % e)
+    dumptrailers(out, doc, show_fallback_xref)
+    out.write("</pdf>")
+    return
+
+
+def dumpoutline(
+    outfp: TextIO,
+    fname: str,
+    objids: Any,
+    pagenos: Container[int],
+    password: str = "",
+    dumpall: bool = False,
+    codec: Optional[str] = None,
+    extractdir: Optional[str] = None,
+) -> None:
+    fp = open(fname, "rb")
+    parser = PDFParser(fp)
+    doc = PDFDocument(parser, password)
+    pages = {
+        page.pageid: pageno
+        for (pageno, page) in enumerate(PDFPage.create_pages(doc), 1)
+    }
+
+    def resolve_dest(dest: object) -> Any:
+        if isinstance(dest, (str, bytes)):
+            dest = resolve1(doc.get_dest(dest))
+        elif isinstance(dest, PSLiteral):
+            dest = resolve1(doc.get_dest(dest.name))
+        if isinstance(dest, dict):
+            dest = dest["D"]
+        if isinstance(dest, PDFObjRef):
+            dest = dest.resolve()
+        return dest
+
+    try:
+        outlines = doc.get_outlines()
+        outfp.write("<outlines>\n")
+        for (level, title, dest, a, se) in outlines:
+            pageno = None
+            if dest:
+                dest = resolve_dest(dest)
+                pageno = pages[dest[0].objid]
+            elif a:
+                action = a
+                if isinstance(action, dict):
+                    subtype = action.get("S")
+                    if subtype and repr(subtype) == "/'GoTo'" and action.get("D"):
+                        dest = resolve_dest(action["D"])
+                        pageno = pages[dest[0].objid]
+            s = escape(title)
+            outfp.write('<outline level="{!r}" title="{}">\n'.format(level, s))
+            if dest is not None:
+                outfp.write("<dest>")
+                dumpxml(outfp, dest)
+                outfp.write("</dest>\n")
+            if pageno is not None:
+                outfp.write("<pageno>%r</pageno>\n" % pageno)
+            outfp.write("</outline>\n")
+        outfp.write("</outlines>\n")
+    except PDFNoOutlines:
+        pass
+    parser.close()
+    fp.close()
+    return
+
+
+LITERAL_FILESPEC = LIT("Filespec")
+LITERAL_EMBEDDEDFILE = LIT("EmbeddedFile")
+
+
+def extractembedded(fname: str, password: str, extractdir: str) -> None:
+    def extract1(objid: int, obj: Dict[str, Any]) -> None:
+        filename = os.path.basename(obj.get("UF") or cast(bytes, obj.get("F")).decode())
+        fileref = obj["EF"].get("UF") or obj["EF"].get("F")
+        fileobj = doc.getobj(fileref.objid)
+        if not isinstance(fileobj, PDFStream):
+            error_msg = (
+                "unable to process PDF: reference for %r is not a "
+                "PDFStream" % filename
+            )
+            raise PDFValueError(error_msg)
+        if fileobj.get("Type") is not LITERAL_EMBEDDEDFILE:
+            raise PDFValueError(
+                "unable to process PDF: reference for %r "
+                "is not an EmbeddedFile" % (filename)
+            )
+        path = os.path.join(extractdir, "%.6d-%s" % (objid, filename))
+        if os.path.exists(path):
+            raise IOError("file exists: %r" % path)
+        print("extracting: %r" % path)
+        os.makedirs(os.path.dirname(path), exist_ok=True)
+        out = open(path, "wb")
+        out.write(fileobj.get_data())
+        out.close()
+        return
+
+    with open(fname, "rb") as fp:
+        parser = PDFParser(fp)
+        doc = PDFDocument(parser, password)
+        extracted_objids = set()
+        for xref in doc.xrefs:
+            for objid in xref.get_objids():
+                obj = doc.getobj(objid)
+                if (
+                    objid not in extracted_objids
+                    and isinstance(obj, dict)
+                    and obj.get("Type") is LITERAL_FILESPEC
+                ):
+                    extracted_objids.add(objid)
+                    extract1(objid, obj)
+    return
+
+
+def dumppdf(
+    outfp: TextIO,
+    fname: str,
+    objids: Iterable[int],
+    pagenos: Container[int],
+    password: str = "",
+    dumpall: bool = False,
+    codec: Optional[str] = None,
+    extractdir: Optional[str] = None,
+    show_fallback_xref: bool = False,
+) -> None:
+    fp = open(fname, "rb")
+    parser = PDFParser(fp)
+    doc = PDFDocument(parser, password)
+    if objids:
+        for objid in objids:
+            obj = doc.getobj(objid)
+            dumpxml(outfp, obj, codec=codec)
+    if pagenos:
+        for (pageno, page) in enumerate(PDFPage.create_pages(doc)):
+            if pageno in pagenos:
+                if codec:
+                    for obj in page.contents:
+                        obj = stream_value(obj)
+                        dumpxml(outfp, obj, codec=codec)
+                else:
+                    dumpxml(outfp, page.attrs)
+    if dumpall:
+        dumpallobjs(outfp, doc, codec, show_fallback_xref)
+    if (not objids) and (not pagenos) and (not dumpall):
+        dumptrailers(outfp, doc, show_fallback_xref)
+    fp.close()
+    if codec not in ("raw", "binary"):
+        outfp.write("\n")
+    return
+
+
+def create_parser() -> ArgumentParser:
+    parser = ArgumentParser(description=__doc__, add_help=True)
+    parser.add_argument(
+        "files",
+        type=str,
+        default=None,
+        nargs="+",
+        help="One or more paths to PDF files.",
+    )
+
+    parser.add_argument(
+        "--version",
+        "-v",
+        action="version",
+        version="pdfminer.six v{}".format(pdfminer.__version__),
+    )
+    parser.add_argument(
+        "--debug",
+        "-d",
+        default=False,
+        action="store_true",
+        help="Use debug logging level.",
+    )
+    procedure_parser = parser.add_mutually_exclusive_group()
+    procedure_parser.add_argument(
+        "--extract-toc",
+        "-T",
+        default=False,
+        action="store_true",
+        help="Extract structure of outline",
+    )
+    procedure_parser.add_argument(
+        "--extract-embedded", "-E", type=str, help="Extract embedded files"
+    )
+
+    parse_params = parser.add_argument_group(
+        "Parser", description="Used during PDF parsing"
+    )
+    parse_params.add_argument(
+        "--page-numbers",
+        type=int,
+        default=None,
+        nargs="+",
+        help="A space-seperated list of page numbers to parse.",
+    )
+    parse_params.add_argument(
+        "--pagenos",
+        "-p",
+        type=str,
+        help="A comma-separated list of page numbers to parse. Included for "
+        "legacy applications, use --page-numbers for more idiomatic "
+        "argument entry.",
+    )
+    parse_params.add_argument(
+        "--objects",
+        "-i",
+        type=str,
+        help="Comma separated list of object numbers to extract",
+    )
+    parse_params.add_argument(
+        "--all",
+        "-a",
+        default=False,
+        action="store_true",
+        help="If the structure of all objects should be extracted",
+    )
+    parse_params.add_argument(
+        "--show-fallback-xref",
+        action="store_true",
+        help="Additionally show the fallback xref. Use this if the PDF "
+        "has zero or only invalid xref's. This setting is ignored if "
+        "--extract-toc or --extract-embedded is used.",
+    )
+    parse_params.add_argument(
+        "--password",
+        "-P",
+        type=str,
+        default="",
+        help="The password to use for decrypting PDF file.",
+    )
+
+    output_params = parser.add_argument_group(
+        "Output", description="Used during output generation."
+    )
+    output_params.add_argument(
+        "--outfile",
+        "-o",
+        type=str,
+        default="-",
+        help='Path to file where output is written. Or "-" (default) to '
+        "write to stdout.",
+    )
+    codec_parser = output_params.add_mutually_exclusive_group()
+    codec_parser.add_argument(
+        "--raw-stream",
+        "-r",
+        default=False,
+        action="store_true",
+        help="Write stream objects without encoding",
+    )
+    codec_parser.add_argument(
+        "--binary-stream",
+        "-b",
+        default=False,
+        action="store_true",
+        help="Write stream objects with binary encoding",
+    )
+    codec_parser.add_argument(
+        "--text-stream",
+        "-t",
+        default=False,
+        action="store_true",
+        help="Write stream objects as plain text",
+    )
+
+    return parser
+
+
+def main(argv: Optional[List[str]] = None) -> None:
+    parser = create_parser()
+    args = parser.parse_args(args=argv)
+
+    if args.debug:
+        logging.getLogger().setLevel(logging.DEBUG)
+
+    if args.outfile == "-":
+        outfp = sys.stdout
+    else:
+        outfp = open(args.outfile, "w")
+
+    if args.objects:
+        objids = [int(x) for x in args.objects.split(",")]
+    else:
+        objids = []
+
+    if args.page_numbers:
+        pagenos = {x - 1 for x in args.page_numbers}
+    elif args.pagenos:
+        pagenos = {int(x) - 1 for x in args.pagenos.split(",")}
+    else:
+        pagenos = set()
+
+    password = args.password
+
+    if args.raw_stream:
+        codec: Optional[str] = "raw"
+    elif args.binary_stream:
+        codec = "binary"
+    elif args.text_stream:
+        codec = "text"
+    else:
+        codec = None
+
+    for fname in args.files:
+        if args.extract_toc:
+            dumpoutline(
+                outfp,
+                fname,
+                objids,
+                pagenos,
+                password=password,
+                dumpall=args.all,
+                codec=codec,
+                extractdir=None,
+            )
+        elif args.extract_embedded:
+            extractembedded(fname, password=password, extractdir=args.extract_embedded)
+        else:
+            dumppdf(
+                outfp,
+                fname,
+                objids,
+                pagenos,
+                password=password,
+                dumpall=args.all,
+                codec=codec,
+                extractdir=None,
+                show_fallback_xref=args.show_fallback_xref,
+            )
+
+    outfp.close()
+
+
+if __name__ == "__main__":
+    main()

venv/bin/f2py

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy.f2py.f2py2e import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/f2py3

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy.f2py.f2py2e import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/f2py3.11

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from numpy.f2py.f2py2e import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/filetype

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from filetype.__main__ import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/fonttools

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from fontTools.__main__ import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/gradio

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from gradio.cli import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli())

venv/bin/httpx

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from httpx import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/huggingface-cli

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from huggingface_hub.commands.huggingface_cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/humanfriendly

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from humanfriendly.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/ipython

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from IPython import start_ipython
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(start_ipython())

venv/bin/ipython3

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from IPython import start_ipython
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(start_ipython())

venv/bin/isympy

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from isympy import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/jsonschema

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from jsonschema.cli import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/langchain-server

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from langchain.server import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/langsmith

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from langsmith.cli.main import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/markdown-it

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from markdown_it.cli.parse import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/nltk

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from nltk.cli import cli
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli())

venv/bin/normalizer

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from charset_normalizer.cli.normalizer import cli_detect
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(cli_detect())

venv/bin/onnxruntime_test

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from onnxruntime.tools.onnxruntime_test import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/openai

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from openai._openai_scripts import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/pai

@@ -0,0 +1,8 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+# -*- coding: utf-8 -*-
+import re
+import sys
+from pai.__main__ import main
+if __name__ == '__main__':
+    sys.argv[0] = re.sub(r'(-script\.pyw|\.exe)?$', '', sys.argv[0])
+    sys.exit(main())

venv/bin/pdf2txt.py

@@ -0,0 +1,317 @@
+#!/home/draco/PycharmProjects/customChatBotDemo/venv/bin/python
+"""A command line tool for extracting text and images from PDF and
+output it to plain text, html, xml or tags."""
+import argparse
+import logging
+import sys
+from typing import Any, Container, Iterable, List, Optional
+
+import pdfminer.high_level
+from pdfminer.layout import LAParams
+from pdfminer.utils import AnyIO
+
+logging.basicConfig()
+
+OUTPUT_TYPES = ((".htm", "html"), (".html", "html"), (".xml", "xml"), (".tag", "tag"))
+
+
+def float_or_disabled(x: str) -> Optional[float]:
+    if x.lower().strip() == "disabled":
+        return None
+    try:
+        return float(x)
+    except ValueError:
+        raise argparse.ArgumentTypeError("invalid float value: {}".format(x))
+
+
+def extract_text(
+    files: Iterable[str] = [],
+    outfile: str = "-",
+    laparams: Optional[LAParams] = None,
+    output_type: str = "text",
+    codec: str = "utf-8",
+    strip_control: bool = False,
+    maxpages: int = 0,
+    page_numbers: Optional[Container[int]] = None,
+    password: str = "",
+    scale: float = 1.0,
+    rotation: int = 0,
+    layoutmode: str = "normal",
+    output_dir: Optional[str] = None,
+    debug: bool = False,
+    disable_caching: bool = False,
+    **kwargs: Any
+) -> AnyIO:
+    if not files:
+        raise ValueError("Must provide files to work upon!")
+
+    if output_type == "text" and outfile != "-":
+        for override, alttype in OUTPUT_TYPES:
+            if outfile.endswith(override):
+                output_type = alttype
+
+    if outfile == "-":
+        outfp: AnyIO = sys.stdout
+        if sys.stdout.encoding is not None:
+            codec = "utf-8"
+    else:
+        outfp = open(outfile, "wb")
+
+    for fname in files:
+        with open(fname, "rb") as fp:
+            pdfminer.high_level.extract_text_to_fp(fp, **locals())
+    return outfp
+
+
+def create_parser() -> argparse.ArgumentParser:
+    parser = argparse.ArgumentParser(description=__doc__, add_help=True)
+    parser.add_argument(
+        "files",
+        type=str,
+        default=None,
+        nargs="+",
+        help="One or more paths to PDF files.",
+    )
+
+    parser.add_argument(
+        "--version",
+        "-v",
+        action="version",
+        version="pdfminer.six v{}".format(pdfminer.__version__),
+    )
+    parser.add_argument(
+        "--debug",
+        "-d",
+        default=False,
+        action="store_true",
+        help="Use debug logging level.",
+    )
+    parser.add_argument(
+        "--disable-caching",
+        "-C",
+        default=False,
+        action="store_true",
+        help="If caching or resources, such as fonts, should be disabled.",
+    )
+
+    parse_params = parser.add_argument_group(
+        "Parser", description="Used during PDF parsing"
+    )
+    parse_params.add_argument(
+        "--page-numbers",
+        type=int,
+        default=None,
+        nargs="+",
+        help="A space-seperated list of page numbers to parse.",
+    )
+    parse_params.add_argument(
+        "--pagenos",
+        "-p",
+        type=str,
+        help="A comma-separated list of page numbers to parse. "
+        "Included for legacy applications, use --page-numbers "
+        "for more idiomatic argument entry.",
+    )
+    parse_params.add_argument(
+        "--maxpages",
+        "-m",
+        type=int,
+        default=0,
+        help="The maximum number of pages to parse.",
+    )
+    parse_params.add_argument(
+        "--password",
+        "-P",
+        type=str,
+        default="",
+        help="The password to use for decrypting PDF file.",
+    )
+    parse_params.add_argument(
+        "--rotation",
+        "-R",
+        default=0,
+        type=int,
+        help="The number of degrees to rotate the PDF "
+        "before other types of processing.",
+    )
+
+    la_params = LAParams()  # will be used for defaults
+    la_param_group = parser.add_argument_group(
+        "Layout analysis", description="Used during layout analysis."
+    )
+    la_param_group.add_argument(
+        "--no-laparams",
+        "-n",
+        default=False,
+        action="store_true",
+        help="If layout analysis parameters should be ignored.",
+    )
+    la_param_group.add_argument(
+        "--detect-vertical",
+        "-V",
+        default=la_params.detect_vertical,
+        action="store_true",
+        help="If vertical text should be considered during layout analysis",
+    )
+    la_param_group.add_argument(
+        "--line-overlap",
+        type=float,
+        default=la_params.line_overlap,
+        help="If two characters have more overlap than this they "
+        "are considered to be on the same line. The overlap is specified "
+        "relative to the minimum height of both characters.",
+    )
+    la_param_group.add_argument(
+        "--char-margin",
+        "-M",
+        type=float,
+        default=la_params.char_margin,
+        help="If two characters are closer together than this margin they "
+        "are considered to be part of the same line. The margin is "
+        "specified relative to the width of the character.",
+    )
+    la_param_group.add_argument(
+        "--word-margin",
+        "-W",
+        type=float,
+        default=la_params.word_margin,
+        help="If two characters on the same line are further apart than this "
+        "margin then they are considered to be two separate words, and "
+        "an intermediate space will be added for readability. The margin "
+        "is specified relative to the width of the character.",
+    )
+    la_param_group.add_argument(
+        "--line-margin",
+        "-L",
+        type=float,
+        default=la_params.line_margin,
+        help="If two lines are close together they are considered to "
+        "be part of the same paragraph. The margin is specified "
+        "relative to the height of a line.",
+    )
+    la_param_group.add_argument(
+        "--boxes-flow",
+        "-F",
+        type=float_or_disabled,
+        default=la_params.boxes_flow,
+        help="Specifies how much a horizontal and vertical position of a "
+        "text matters when determining the order of lines. The value "
+        "should be within the range of -1.0 (only horizontal position "
+        "matters) to +1.0 (only vertical position matters). You can also "
+        "pass `disabled` to disable advanced layout analysis, and "
+        "instead return text based on the position of the bottom left "
+        "corner of the text box.",
+    )
+    la_param_group.add_argument(
+        "--all-texts",
+        "-A",
+        default=la_params.all_texts,
+        action="store_true",
+        help="If layout analysis should be performed on text in figures.",
+    )
+
+    output_params = parser.add_argument_group(
+        "Output", description="Used during output generation."
+    )
+    output_params.add_argument(
+        "--outfile",
+        "-o",
+        type=str,
+        default="-",
+        help="Path to file where output is written. "
+        'Or "-" (default) to write to stdout.',
+    )
+    output_params.add_argument(
+        "--output_type",
+        "-t",
+        type=str,
+        default="text",
+        help="Type of output to generate {text,html,xml,tag}.",
+    )
+    output_params.add_argument(
+        "--codec",
+        "-c",
+        type=str,
+        default="utf-8",
+        help="Text encoding to use in output file.",
+    )
+    output_params.add_argument(
+        "--output-dir",
+        "-O",
+        default=None,
+        help="The output directory to put extracted images in. If not given, "
+        "images are not extracted.",
+    )
+    output_params.add_argument(
+        "--layoutmode",
+        "-Y",
+        default="normal",
+        type=str,
+        help="Type of layout to use when generating html "
+        "{normal,exact,loose}. If normal,each line is"
+        " positioned separately in the html. If exact"
+        ", each character is positioned separately in"
+        " the html. If loose, same result as normal "
+        "but with an additional newline after each "
+        "text line. Only used when output_type is html.",
+    )
+    output_params.add_argument(
+        "--scale",
+        "-s",
+        type=float,
+        default=1.0,
+        help="The amount of zoom to use when generating html file. "
+        "Only used when output_type is html.",
+    )
+    output_params.add_argument(
+        "--strip-control",
+        "-S",
+        default=False,
+        action="store_true",
+        help="Remove control statement from text. "
+        "Only used when output_type is xml.",
+    )
+
+    return parser
+
+
+def parse_args(args: Optional[List[str]]) -> argparse.Namespace:
+    parsed_args = create_parser().parse_args(args=args)
+
+    # Propagate parsed layout parameters to LAParams object
+    if parsed_args.no_laparams:
+        parsed_args.laparams = None
+    else:
+        parsed_args.laparams = LAParams(
+            line_overlap=parsed_args.line_overlap,
+            char_margin=parsed_args.char_margin,
+            line_margin=parsed_args.line_margin,
+            word_margin=parsed_args.word_margin,
+            boxes_flow=parsed_args.boxes_flow,
+            detect_vertical=parsed_args.detect_vertical,
+            all_texts=parsed_args.all_texts,
+        )
+
+    if parsed_args.page_numbers:
+        parsed_args.page_numbers = {x - 1 for x in parsed_args.page_numbers}
+
+    if parsed_args.pagenos:
+        parsed_args.page_numbers = {int(x) - 1 for x in parsed_args.pagenos.split(",")}
+
+    if parsed_args.output_type == "text" and parsed_args.outfile != "-":
+        for override, alttype in OUTPUT_TYPES:
+            if parsed_args.outfile.endswith(override):
+                parsed_args.output_type = alttype
+
+    return parsed_args
+
+
+def main(args: Optional[List[str]] = None) -> int:
+    parsed_args = parse_args(args)
+    outfp = extract_text(**vars(parsed_args))
+    outfp.close()
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())