├── README.md ├── requirements.txt ├── app.py └── .gitignore /README.md: -------------------------------------------------------------------------------- 1 | # Introduction 2 | 3 | This is a simple example that develops a PDF Chatbot application with Streamlit and LangChain 4 | -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | aiohttp==3.8.4 2 | aiosignal==1.3.1 3 | altair==5.0.1 4 | async-timeout==4.0.2 5 | attrs==23.1.0 6 | blinker==1.6.2 7 | cachetools==5.3.1 8 | certifi==2023.5.7 9 | charset-normalizer==3.1.0 10 | click==8.1.3 11 | dataclasses-json==0.5.8 12 | decorator==5.1.1 13 | frozenlist==1.3.3 14 | gitdb==4.0.10 15 | GitPython==3.1.31 16 | greenlet==2.0.2 17 | idna==3.4 18 | importlib-metadata==6.6.0 19 | Jinja2==3.1.2 20 | jsonschema==4.17.3 21 | langchain==0.0.198 22 | langchainplus-sdk==0.0.9 23 | markdown-it-py==3.0.0 24 | MarkupSafe==2.1.3 25 | marshmallow==3.19.0 26 | marshmallow-enum==1.5.1 27 | mdurl==0.1.2 28 | multidict==6.0.4 29 | mypy-extensions==1.0.0 30 | numexpr==2.8.4 31 | numpy==1.24.3 32 | openai==0.27.8 33 | openapi-schema-pydantic==1.2.4 34 | packaging==23.1 35 | pandas==2.0.2 36 | Pillow==9.5.0 37 | protobuf==4.23.2 38 | pyarrow==12.0.1 39 | pydantic==1.10.9 40 | pydeck==0.8.1b0 41 | Pygments==2.15.1 42 | Pympler==1.0.1 43 | pyrsistent==0.19.3 44 | python-dateutil==2.8.2 45 | pytz==2023.3 46 | pytz-deprecation-shim==0.1.0.post0 47 | PyYAML==6.0 48 | requests==2.31.0 49 | rich==13.4.2 50 | six==1.16.0 51 | smmap==5.0.0 52 | SQLAlchemy==2.0.16 53 | streamlit==1.23.1 54 | tenacity==8.2.2 55 | toml==0.10.2 56 | toolz==0.12.0 57 | tornado==6.3.2 58 | tqdm==4.65.0 59 | typing-inspect==0.9.0 60 | typing_extensions==4.6.3 61 | tzdata==2023.3 62 | tzlocal==4.3 63 | urllib3==2.0.3 64 | validators==0.20.0 65 | yarl==1.9.2 66 | zipp==3.15.0 67 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import os 2 | import streamlit as st 3 | from langchain.document_loaders import PyMuPDFLoader 4 | from langchain.text_splitter import RecursiveCharacterTextSplitter 5 | from langchain.embeddings.openai import OpenAIEmbeddings 6 | from langchain.vectorstores import Chroma 7 | from langchain.llms import OpenAI 8 | from langchain.chains.question_answering import load_qa_chain 9 | 10 | OPENAI_API_KEY = st.secrets["openai_api_key"] 11 | embeddings = OpenAIEmbeddings(openai_api_key=OPENAI_API_KEY) 12 | persist_directory = 'pdf_persist' 13 | collection_name = 'pdf_collection' 14 | llm = OpenAI(temperature=0, openai_api_key=OPENAI_API_KEY) 15 | chain = load_qa_chain(llm, chain_type="stuff") 16 | vectorstore = None 17 | 18 | def load_pdf(pdf_path): 19 | return PyMuPDFLoader(pdf_path).load() 20 | 21 | st.title("PDF Chatbot") 22 | 23 | with st.container(): 24 | uploaded_file = st.file_uploader("Choose a PDF file", type="pdf") 25 | if uploaded_file is not None: 26 | path = os.path.join('.', uploaded_file.name) 27 | with open(path, 'wb') as f: 28 | f.write(uploaded_file.getbuffer()) 29 | 30 | docs = load_pdf(path) 31 | 32 | text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0) 33 | split_docs = text_splitter.split_documents(docs) 34 | 35 | vectorstore = Chroma.from_documents(split_docs, embeddings, collection_name=collection_name, persist_directory=persist_directory) 36 | vectorstore.persist() 37 | 38 | st.write("Done") 39 | 40 | with st.container(): 41 | question = st.text_input("Question") 42 | if vectorstore is not None and question is not None and question != "": 43 | docs = vectorstore.similarity_search(question, 3, include_metadata=True) 44 | answer = chain.run(input_documents=docs, question=question) 45 | st.write(answer) 46 | 47 | -------------------------------------------------------------------------------- /.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 | .streamlit --------------------------------------------------------------------------------