app_upload

.gitignore

@@ -0,0 +1,160 @@
+# 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/

app.py

@@ -0,0 +1,121 @@
+# AUTOGENERATED! DO NOT EDIT! File to edit: ../drive/MyDrive/Codici/Python/Apps/Gradio_App/Langchain_apps/langchain_summarization_app.ipynb.
+
+# %% auto 0
+__all__ = ['hub_llm', 'title', 'description', 'combine_prompt_template', 'pdf_example_1', 'pdf_example_2', 'prompt_example_1',
+           'prompt_example_2', 'upload_file_input', 'custom_prompt_input', 'custom_chunk_input', 'chunk_size_input',
+           'chunk_overlap_input', 'examples', 'outputs', 'iface', 'summarize']
+
+# %% ../drive/MyDrive/Codici/Python/Apps/Gradio_App/Langchain_apps/langchain_summarization_app.ipynb 3
+from langchain import HuggingFaceHub, PromptTemplate, LLMChain
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains.mapreduce import MapReduceChain
+from langchain.prompts import PromptTemplate
+from langchain.docstore.document import Document
+from langchain.chains.summarize import load_summarize_chain
+from langchain.document_loaders import PyPDFLoader
+
+# %% ../drive/MyDrive/Codici/Python/Apps/Gradio_App/Langchain_apps/langchain_summarization_app.ipynb 5
+hub_llm = HuggingFaceHub(
+    repo_id="facebook/bart-large-cnn", # facebook/bart-large-cnn or "google/flan-t5-base" or "google/pegasus-xsum"
+    model_kwargs={
+        "temperature": 0.01, # Controls randomness (0.0: deterministic, 1.0: very random)
+        "max_new_tokens": 256*2,  # Maximum number of tokens to generate in the summary
+        "min_length": 30,  # Minimum length of the generated summary
+        "repetition_penalty": 1.2,  # Penalizes repeated tokens (higher value = less repetition)
+        "top_k": 50,  # Consider only the top k most likely tokens when generating
+        "top_p": 0.95,  # Consider tokens with cumulative probability up to top_p
+        "early_stopping": True, # Stops generation when a certain condition is met (e.g., end-of-sequence token)
+    }
+)
+
+# %% ../drive/MyDrive/Codici/Python/Apps/Gradio_App/Langchain_apps/langchain_summarization_app.ipynb 15
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+import gradio as gr
+import time
+
+title="PDF Summarizer"
+description="Summarize your PDF using a custom combine prompt."
+
+# Default combine_prompt
+combine_prompt_template = """Write a comprehensive summary of this academic article.
+
+Divide the summary in:
+1. Main Objective of the paper
+2. Results
+
+{text}
+
+SUMMARY:"""
+
+# Example PDF files and prompts
+pdf_example_1 = './ZeroShotDataAug.pdf'
+pdf_example_2 = './bert.pdf'
+prompt_example_1 = """Write a comprehensive summary of this academic article.
+
+Divide the summary in:
+1. Main Objective of the paper
+2. Results
+
+{text}
+
+SUMMARY:"""
+prompt_example_2 = """Summarize the following document focusing on the key findings and methodology.
+
+{text}
+
+Summary:"""
+
+# Implementation
+def summarize(pdf_file, custom_prompt, custom_chunk, chunk_size, chunk_overlap):
+    try:
+        loader = PyPDFLoader(pdf_file.name)
+        if custom_chunk:
+            text_splitter = RecursiveCharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
+            docs = loader.load_and_split(text_splitter=text_splitter)
+        else:
+            docs = loader.load_and_split()
+
+        PROMPT = PromptTemplate(template=custom_prompt, input_variables=['text'])
+        chain = load_summarize_chain(hub_llm, chain_type='map_reduce', combine_prompt=PROMPT)
+
+        # Introduce a delay before calling the API
+        time.sleep(1)
+        summary = chain.run(docs)
+        return summary
+    except Exception as e:
+        return f"An error occurred: {e}"
+
+upload_file_input = gr.File(label="Upload PDF", type="filepath")
+custom_prompt_input = gr.Textbox(label="Custom Prompt",
+                                 lines=10,
+                                 value=combine_prompt_template,
+                                 info="Define your own prompt or leave empty for default.")
+custom_chunk_input = gr.Checkbox(label="Custom Chunk", value=False, info="Recommended to be left unchecked")
+chunk_size_input = gr.Number(label="Chunk Size", value=700,minimum=500,maximum=1000,step=100)
+chunk_overlap_input = gr.Number(label="Chunk Overlap", value=50,minimum=10,maximum=100,step=100)
+
+examples=[
+    [pdf_example_1, prompt_example_1, False, 700, 50],
+    # [pdf_example_2, prompt_example_2, False, 700, 50]
+    ]
+
+outputs = gr.Textbox(label="Summary")
+
+iface = gr.Interface(
+    title=title,
+    description=description,
+    fn=summarize,
+    inputs=[upload_file_input,
+            custom_prompt_input,
+            custom_chunk_input,
+            chunk_size_input,
+            chunk_overlap_input
+            ],
+    outputs=outputs,
+    examples=examples,
+)
+
+iface.launch(
+    debug=False,
+    # share=False,
+    )

requirements.txt

@@ -0,0 +1,16 @@
+gradio==5.8.0
+gradio_client==1.5.1
+geopandas==1.0.1
+pandas==2.2.2
+pandas-datareader==0.10.0
+pandas-gbq==0.24.0
+pandas-stubs==2.2.2.240909
+sklearn-pandas==2.2.0
+sentence-transformers==3.2.1
+transformers==4.46.3
+sentence-transformers==3.2.1
+langchain==0.3.10
+langchain-community==0.3.10
+langchain-core==0.3.22
+langchain-text-splitters==0.3.2
+pypdf==5.1.0