primera version de app

.gitignore

@@ -0,0 +1,176 @@
+# Created by https://www.toptal.com/developers/gitignore/api/python
+# Edit at https://www.toptal.com/developers/gitignore?templates=python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+# End of https://www.toptal.com/developers/gitignore/api/python

app.py

@@ -0,0 +1,102 @@
+import streamlit as st
+import base64
+import os
+from io import BytesIO
+from pypdf import PdfReader
+from langchain.schema import Document
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain_pinecone import PineconeVectorStore
+from pinecone import Pinecone as PineconeClient, ServerlessSpec
+
+# Configuración de las variables de entorno
+hf_token = os.getenv("HUGGINGFACE_TOKEN")
+pinecone_api_key = os.getenv("PINECONE_API_KEY")
+
+st.set_page_config(page_title="Clasificador de CVs", layout="wide")
+st.title("🎯 Clasificador de CVs por Puesto de Trabajo")
+
+# Inputs
+titulo_puesto = st.text_input("🧑‍💼 Título del puesto", placeholder="Ej: Desarrollador Backend Senior")
+descripcion_puesto = st.text_area("📝 Descripción del puesto", height=200)
+uploaded_files = st.file_uploader("📎 Subir CVs (PDF)", type="pdf", accept_multiple_files=True)
+
+if st.button("📊 Procesar CVs"):
+    if not uploaded_files:
+        st.warning("Primero sube al menos un CV.")
+    elif not descripcion_puesto.strip():
+        st.warning("Debes escribir una descripción del puesto.")
+    else:
+        # Inicializar Pinecone
+        pc = PineconeClient(api_key=pinecone_api_key)
+        index_name = "cv-index"
+
+        if index_name not in pc.list_indexes().names():
+            pc.create_index(
+                name=index_name,
+                dimension=384,
+                metric='cosine',
+                spec=ServerlessSpec(cloud='aws', region='us-east-1')
+            )
+        index = pc.Index(index_name)
+
+        # Inicializar modelo de embeddings
+        embedding = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+        # Vector store
+        vector_store = PineconeVectorStore(index=index, embedding=embedding)
+
+        # Crear diccionario de archivos en memoria
+        archivos_en_memoria = {file.name: BytesIO(file.read()) for file in uploaded_files}
+
+        # Procesar archivos y crear documentos
+        documents = []
+        for filename, buffer in archivos_en_memoria.items():
+            buffer.seek(0)
+            reader = PdfReader(buffer)
+            text = ""
+            for page in reader.pages:
+                page_text = page.extract_text()
+                if page_text:
+                    text += page_text + "\n"
+
+            doc = Document(
+                page_content=text.strip(),
+                metadata={"filename": filename, "titulo_puesto": titulo_puesto}
+            )
+            documents.append(doc)
+
+        # Subir documentos a Pinecone
+        vector_store.add_documents(documents)
+
+        # Búsqueda por similitud
+        results = vector_store.similarity_search_with_score(descripcion_puesto, k=len(documents))
+        st.success(f"{len(results)} CV(s) procesado(s).")
+
+        # Mostrar resultados
+        for doc, score in results:
+            st.markdown("---")
+            col1, col2 = st.columns([2, 1])
+
+            filename = doc.metadata.get("filename")
+            file_buffer = archivos_en_memoria.get(filename)
+
+            with col1:
+                if file_buffer:
+                    file_buffer.seek(0)
+                    base64_pdf = base64.b64encode(file_buffer.read()).decode("utf-8")
+                    pdf_display = f"""
+                    <iframe src="data:application/pdf;base64,{base64_pdf}" width="100%" height="500" type="application/pdf"></iframe>
+                    """
+                    st.markdown("#### 👀 Visualizador del PDF", unsafe_allow_html=True)
+                    st.markdown(pdf_display, unsafe_allow_html=True)
+                else:
+                    st.warning(f"No se encontró el archivo `{filename}` en memoria.")
+
+            with col2:
+                st.markdown("#### 📄 Información del CV")
+                st.write(f"**Nombre del archivo:** `{filename}`")
+                st.write(f"**Score de similitud:** `{score * 100:.2f}%`")
+
+        # Eliminar todos los vectores del índice (vaciar)
+        index.delete(delete_all=True)
+        st.success("🧹 Todos los vectores han sido eliminados del índice de Pinecone.")