├── .gitignore ├── README.md ├── images ├── after-upsert.png ├── before-upsert.png ├── liner-pdf-chat.gif ├── openai-vectors.svg └── pinecone-index.png ├── liner-pdf-chat.ipynb └── transformer.pdf /.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 | 162 | *.jpg 163 | .DS_Store 164 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # LINER PDF Chat Tutorial (Simple ver.) 2 | 3 | LINER PDF Chat Tutorial 4 | 5 | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/liner-engineering/liner-pdf-chat-tutorial/blob/master/liner-pdf-chat.ipynb) 6 | 7 |
8 | 9 | ## Stack 10 | 11 | - **ChatGPT** 12 | - **Pinecone** 13 | - **Google OCR** 14 | 15 |
16 | 17 | ## Contributors 18 | 19 | - Luke Kim 20 | - Karter Heo (karter@linercorp.com) 21 | -------------------------------------------------------------------------------- /images/after-upsert.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liner-engineering/liner-pdf-chat-tutorial/e5058ca24ae83f8633d5d44c390c870fe60f8854/images/after-upsert.png -------------------------------------------------------------------------------- /images/before-upsert.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liner-engineering/liner-pdf-chat-tutorial/e5058ca24ae83f8633d5d44c390c870fe60f8854/images/before-upsert.png -------------------------------------------------------------------------------- /images/liner-pdf-chat.gif: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liner-engineering/liner-pdf-chat-tutorial/e5058ca24ae83f8633d5d44c390c870fe60f8854/images/liner-pdf-chat.gif -------------------------------------------------------------------------------- /images/openai-vectors.svg: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /images/pinecone-index.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liner-engineering/liner-pdf-chat-tutorial/e5058ca24ae83f8633d5d44c390c870fe60f8854/images/pinecone-index.png -------------------------------------------------------------------------------- /transformer.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/liner-engineering/liner-pdf-chat-tutorial/e5058ca24ae83f8633d5d44c390c870fe60f8854/transformer.pdf --------------------------------------------------------------------------------