├── .gitignore ├── README.md ├── app.py └── requirements.txt /.gitignore: -------------------------------------------------------------------------------- 1 | # Byte-compiled / optimized / DLL files 2 | __pycache__/ 3 | *.py[cod] 4 | *$py.class 5 | 6 | # C extensions 7 | *.so 8 | 9 | # Distribution / packaging 10 | .Python 11 | build/ 12 | develop-eggs/ 13 | dist/ 14 | downloads/ 15 | eggs/ 16 | .eggs/ 17 | lib/ 18 | lib64/ 19 | parts/ 20 | sdist/ 21 | var/ 22 | wheels/ 23 | share/python-wheels/ 24 | *.egg-info/ 25 | .installed.cfg 26 | *.egg 27 | MANIFEST 28 | 29 | # PyInstaller 30 | # Usually these files are written by a python script from a template 31 | # before PyInstaller builds the exe, so as to inject date/other infos into it. 32 | *.manifest 33 | *.spec 34 | 35 | # Installer logs 36 | pip-log.txt 37 | pip-delete-this-directory.txt 38 | 39 | # Unit test / coverage reports 40 | htmlcov/ 41 | .tox/ 42 | .nox/ 43 | .coverage 44 | .coverage.* 45 | .cache 46 | nosetests.xml 47 | coverage.xml 48 | *.cover 49 | *.py,cover 50 | .hypothesis/ 51 | .pytest_cache/ 52 | cover/ 53 | 54 | # Translations 55 | *.mo 56 | *.pot 57 | 58 | # Django stuff: 59 | *.log 60 | local_settings.py 61 | db.sqlite3 62 | db.sqlite3-journal 63 | 64 | # Flask stuff: 65 | instance/ 66 | .webassets-cache 67 | 68 | # Scrapy stuff: 69 | .scrapy 70 | 71 | # Sphinx documentation 72 | docs/_build/ 73 | 74 | # PyBuilder 75 | .pybuilder/ 76 | target/ 77 | 78 | # Jupyter Notebook 79 | .ipynb_checkpoints 80 | 81 | # IPython 82 | profile_default/ 83 | ipython_config.py 84 | 85 | # pyenv 86 | # For a library or package, you might want to ignore these files since the code is 87 | # intended to run in multiple environments; otherwise, check them in: 88 | # .python-version 89 | 90 | # pipenv 91 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control. 92 | # However, in case of collaboration, if having platform-specific dependencies or dependencies 93 | # having no cross-platform support, pipenv may install dependencies that don't work, or not 94 | # install all needed dependencies. 95 | #Pipfile.lock 96 | 97 | # poetry 98 | # Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control. 99 | # This is especially recommended for binary packages to ensure reproducibility, and is more 100 | # commonly ignored for libraries. 101 | # https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control 102 | #poetry.lock 103 | 104 | # pdm 105 | # Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control. 106 | #pdm.lock 107 | # pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it 108 | # in version control. 109 | # https://pdm.fming.dev/#use-with-ide 110 | .pdm.toml 111 | 112 | # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm 113 | __pypackages__/ 114 | 115 | # Celery stuff 116 | celerybeat-schedule 117 | celerybeat.pid 118 | 119 | # SageMath parsed files 120 | *.sage.py 121 | 122 | # Environments 123 | .env 124 | .venv 125 | env/ 126 | venv/ 127 | ENV/ 128 | env.bak/ 129 | venv.bak/ 130 | 131 | # Spyder project settings 132 | .spyderproject 133 | .spyproject 134 | 135 | # Rope project settings 136 | .ropeproject 137 | 138 | # mkdocs documentation 139 | /site 140 | 141 | # mypy 142 | .mypy_cache/ 143 | .dmypy.json 144 | dmypy.json 145 | 146 | # Pyre type checker 147 | .pyre/ 148 | 149 | # pytype static type analyzer 150 | .pytype/ 151 | 152 | # Cython debug symbols 153 | cython_debug/ 154 | 155 | # PyCharm 156 | # JetBrains specific template is maintained in a separate JetBrains.gitignore that can 157 | # be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore 158 | # and can be added to the global gitignore or merged into this file. For a more nuclear 159 | # option (not recommended) you can uncomment the following to ignore the entire idea folder. 160 | #.idea/ 161 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | 2 | # 📚🗨️ preguntaDOC: Convierte tus documentos en conversaciones con chatGPT 3 | 4 | :link: [Web demo](https://nechubm-preguntadoc-app-tutorial-ct21ps.streamlit.app/) 5 | 6 | 🚀 [Tutorial en Español | Youtube](https://youtu.be/iDrpdkIHMq8) 7 | 8 | ¿Sabías que chatGPT puede tener conversaciones con documentos? ¡En este taller de Python, descubriremos cómo hacerlo posible! Olvídate de las limitaciones, ahora podrás chatear y explorar tus documentos de una manera completamente nueva. 9 | 10 | 11 | ## Introduccion 12 | 📄🧠 Con preguntaDOC, en menos de 50 líneas de código, aprenderás a aprovechar todo el potencial de chatGPT y convertir tus documentos en conversaciones interactivas. No más lecturas aburridas o búsquedas tediosas, ahora podrás hacer preguntas directamente a tus documentos y obtener respuestas de chatGPT. 13 | Para desarrollar esta aplicación en menos de 50 líneas de código necesitaremos: 14 | * ChatGPT API 15 | * Streamlit 16 | 17 | 18 | ## ¿Cómo funciona? 19 | 1. Divide documento en cachos (o chunks) 20 | 2. Crea los embeddings de los cachos de texto 21 | 3. Guarda los cachos y los embeddings en una base de conocimiento 22 | 4. Busca los cachos más similares a la pregunta del usuario gracias a los embeddings. 23 | 5. Pasa los cachos más similares junto a la pregunta a chatGPT que genera la respuesta 24 | 25 | 26 | ## Instalar preguntaDOC 27 | ¡Usar preguntaDOC es fácil! Aquí están los pasos: 28 | 1. Clone o descargue el repositorio en su máquina local. 29 | 2. Instale las bibliotecas requeridas ejecutando el siguiente comando en su terminal: 30 | ```console 31 | pip install -r requirements.txt 32 | ``` 33 | 3. Ejecute la aplicación con el siguiente comando: 34 | ```console 35 | streamlit run app.py 36 | ``` 37 | 4. Obtenga una clave API de OpenAI para usar su API ChatGPT. 38 | 5. Suba un documento a la aplicación. 39 | 6. Escriba su pregunta y disfrute de la magia. 40 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | import os 3 | 4 | from PyPDF2 import PdfReader 5 | from langchain.text_splitter import RecursiveCharacterTextSplitter 6 | from langchain.embeddings import HuggingFaceEmbeddings 7 | from langchain.vectorstores import FAISS 8 | from langchain.chat_models import ChatOpenAI 9 | from langchain.chains.question_answering import load_qa_chain 10 | 11 | st.set_page_config('preguntaDOC') 12 | st.header("Pregunta a tu PDF") 13 | OPENAI_API_KEY = st.text_input('OpenAI API Key', type='password') 14 | pdf_obj = st.file_uploader("Carga tu documento", type="pdf", on_change=st.cache_resource.clear) 15 | 16 | @st.cache_resource 17 | def create_embeddings(pdf): 18 | pdf_reader = PdfReader(pdf) 19 | text = "" 20 | for page in pdf_reader.pages: 21 | text += page.extract_text() 22 | 23 | text_splitter = RecursiveCharacterTextSplitter( 24 | chunk_size=800, 25 | chunk_overlap=100, 26 | length_function=len 27 | ) 28 | chunks = text_splitter.split_text(text) 29 | 30 | embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2") 31 | knowledge_base = FAISS.from_texts(chunks, embeddings) 32 | 33 | return knowledge_base 34 | 35 | if pdf_obj: 36 | knowledge_base = create_embeddings(pdf_obj) 37 | user_question = st.text_input("Haz una pregunta sobre tu PDF:") 38 | 39 | if user_question: 40 | os.environ["OPENAI_API_KEY"] = OPENAI_API_KEY 41 | docs = knowledge_base.similarity_search(user_question, 3) 42 | llm = ChatOpenAI(model_name='gpt-3.5-turbo') 43 | chain = load_qa_chain(llm, chain_type="stuff") 44 | respuesta = chain.run(input_documents=docs, question=user_question) 45 | 46 | st.write(respuesta) -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | openai==0.28.1 2 | langchain==0.0.324 3 | faiss-cpu==1.7.4 4 | streamlit==1.28.0 5 | PyPDF2==3.0.1 6 | sentence-transformers==2.2.2 --------------------------------------------------------------------------------