├── .env.example ├── .gitignore ├── .python-version ├── app.py ├── docs └── PDF-LangChain.jpg ├── htmlTemplates.py ├── readme.md └── requirements.txt /.env.example: -------------------------------------------------------------------------------- 1 | OPENAI_API_KEY= 2 | HUGGINGFACEHUB_API_TOKEN= 3 | -------------------------------------------------------------------------------- /.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 -------------------------------------------------------------------------------- /.python-version: -------------------------------------------------------------------------------- 1 | 3.9 2 | -------------------------------------------------------------------------------- /app.py: -------------------------------------------------------------------------------- 1 | import streamlit as st 2 | from dotenv import load_dotenv 3 | from PyPDF2 import PdfReader 4 | from langchain.text_splitter import CharacterTextSplitter 5 | from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings 6 | from langchain.vectorstores import FAISS 7 | from langchain.chat_models import ChatOpenAI 8 | from langchain.memory import ConversationBufferMemory 9 | from langchain.chains import ConversationalRetrievalChain 10 | from htmlTemplates import css, bot_template, user_template 11 | from langchain.llms import HuggingFaceHub 12 | 13 | def get_pdf_text(pdf_docs): 14 | text = "" 15 | for pdf in pdf_docs: 16 | pdf_reader = PdfReader(pdf) 17 | for page in pdf_reader.pages: 18 | text += page.extract_text() 19 | return text 20 | 21 | 22 | def get_text_chunks(text): 23 | text_splitter = CharacterTextSplitter( 24 | separator="\n", 25 | chunk_size=1000, 26 | chunk_overlap=200, 27 | length_function=len 28 | ) 29 | chunks = text_splitter.split_text(text) 30 | return chunks 31 | 32 | 33 | def get_vectorstore(text_chunks): 34 | embeddings = OpenAIEmbeddings() 35 | # embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl") 36 | vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings) 37 | return vectorstore 38 | 39 | 40 | def get_conversation_chain(vectorstore): 41 | llm = ChatOpenAI() 42 | # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512}) 43 | 44 | memory = ConversationBufferMemory( 45 | memory_key='chat_history', return_messages=True) 46 | conversation_chain = ConversationalRetrievalChain.from_llm( 47 | llm=llm, 48 | retriever=vectorstore.as_retriever(), 49 | memory=memory 50 | ) 51 | return conversation_chain 52 | 53 | 54 | def handle_userinput(user_question): 55 | response = st.session_state.conversation({'question': user_question}) 56 | st.session_state.chat_history = response['chat_history'] 57 | 58 | for i, message in enumerate(st.session_state.chat_history): 59 | if i % 2 == 0: 60 | st.write(user_template.replace( 61 | "{{MSG}}", message.content), unsafe_allow_html=True) 62 | else: 63 | st.write(bot_template.replace( 64 | "{{MSG}}", message.content), unsafe_allow_html=True) 65 | 66 | 67 | def main(): 68 | load_dotenv() 69 | st.set_page_config(page_title="Chat with multiple PDFs", 70 | page_icon=":books:") 71 | st.write(css, unsafe_allow_html=True) 72 | 73 | if "conversation" not in st.session_state: 74 | st.session_state.conversation = None 75 | if "chat_history" not in st.session_state: 76 | st.session_state.chat_history = None 77 | 78 | st.header("Chat with multiple PDFs :books:") 79 | user_question = st.text_input("Ask a question about your documents:") 80 | if user_question: 81 | handle_userinput(user_question) 82 | 83 | with st.sidebar: 84 | st.subheader("Your documents") 85 | pdf_docs = st.file_uploader( 86 | "Upload your PDFs here and click on 'Process'", accept_multiple_files=True) 87 | if st.button("Process"): 88 | with st.spinner("Processing"): 89 | # get pdf text 90 | raw_text = get_pdf_text(pdf_docs) 91 | 92 | # get the text chunks 93 | text_chunks = get_text_chunks(raw_text) 94 | 95 | # create vector store 96 | vectorstore = get_vectorstore(text_chunks) 97 | 98 | # create conversation chain 99 | st.session_state.conversation = get_conversation_chain( 100 | vectorstore) 101 | 102 | 103 | if __name__ == '__main__': 104 | main() 105 | -------------------------------------------------------------------------------- /docs/PDF-LangChain.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/alejandro-ao/ask-multiple-pdfs/dc0155b3f909bc8a56b70d91d8ec550ace0fa921/docs/PDF-LangChain.jpg -------------------------------------------------------------------------------- /htmlTemplates.py: -------------------------------------------------------------------------------- 1 | css = ''' 2 |