├── README.md ├── LICENSE ├── streamlit_app.py └── .gitignore /README.md: -------------------------------------------------------------------------------- 1 | # LaMini-LM-Summarization-Streamlit-App 2 | A Streamlit application that summarizes documents using LaMini-LM. 3 | -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- 1 | MIT License 2 | 3 | Copyright (c) 2023 AI Anytime 4 | 5 | Permission is hereby granted, free of charge, to any person obtaining a copy 6 | of this software and associated documentation files (the "Software"), to deal 7 | in the Software without restriction, including without limitation the rights 8 | to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 | copies of the Software, and to permit persons to whom the Software is 10 | furnished to do so, subject to the following conditions: 11 | 12 | The above copyright notice and this permission notice shall be included in all 13 | copies or substantial portions of the Software. 14 | 15 | THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR 16 | IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, 17 | FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE 18 | AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 | LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 | OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE 21 | SOFTWARE. 22 | -------------------------------------------------------------------------------- /streamlit_app.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | from langchain.text_splitter import RecursiveCharacterTextSplitter 3 | from langchain.document_loaders import PyPDFLoader, DirectoryLoader 4 | from langchain.chains.summarize import load_summarize_chain 5 | from transformers import T5Tokenizer, T5ForConditionalGeneration 6 | from transformers import pipeline 7 | import torch 8 | import base64 9 | 10 | #model and tokenizer loading 11 | checkpoint = "LaMini-Flan-T5-248M" 12 | tokenizer = T5Tokenizer.from_pretrained(checkpoint) 13 | base_model = T5ForConditionalGeneration.from_pretrained(checkpoint, device_map='auto', torch_dtype=torch.float32) 14 | 15 | #file loader and preprocessing 16 | def file_preprocessing(file): 17 | loader = PyPDFLoader(file) 18 | pages = loader.load_and_split() 19 | text_splitter = RecursiveCharacterTextSplitter(chunk_size=200, chunk_overlap=50) 20 | texts = text_splitter.split_documents(pages) 21 | final_texts = "" 22 | for text in texts: 23 | print(text) 24 | final_texts = final_texts + text.page_content 25 | return final_texts 26 | 27 | #LLM pipeline 28 | def llm_pipeline(filepath): 29 | pipe_sum = pipeline( 30 | 'summarization', 31 | model = base_model, 32 | tokenizer = tokenizer, 33 | max_length = 500, 34 | min_length = 50) 35 | input_text = file_preprocessing(filepath) 36 | result = pipe_sum(input_text) 37 | result = result[0]['summary_text'] 38 | return result 39 | 40 | @st.cache_data 41 | #function to display the PDF of a given file 42 | def displayPDF(file): 43 | # Opening file from file path 44 | with open(file, "rb") as f: 45 | base64_pdf = base64.b64encode(f.read()).decode('utf-8') 46 | 47 | # Embedding PDF in HTML 48 | pdf_display = F'' 49 | 50 | # Displaying File 51 | st.markdown(pdf_display, unsafe_allow_html=True) 52 | 53 | #streamlit code 54 | st.set_page_config(layout="wide") 55 | 56 | def main(): 57 | st.title("Document Summarization App using Langauge Model") 58 | 59 | uploaded_file = st.file_uploader("Upload your PDF file", type=['pdf']) 60 | 61 | if uploaded_file is not None: 62 | if st.button("Summarize"): 63 | col1, col2 = st.columns(2) 64 | filepath = "data/"+uploaded_file.name 65 | with open(filepath, "wb") as temp_file: 66 | temp_file.write(uploaded_file.read()) 67 | with col1: 68 | st.info("Uploaded File") 69 | pdf_view = displayPDF(filepath) 70 | 71 | with col2: 72 | summary = llm_pipeline(filepath) 73 | st.info("Summarization Complete") 74 | st.success(summary) 75 | 76 | 77 | 78 | if __name__ == "__main__": 79 | main() -------------------------------------------------------------------------------- /.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 | --------------------------------------------------------------------------------