Upload 7 files

.env.example

@@ -0,0 +1,2 @@
+OPENAI_API_KEY=
+HUGGINGFACEHUB_API_TOKEN=

.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

.python-version

@@ -0,0 +1 @@
+3.9.13

app.py

@@ -0,0 +1,99 @@
+import streamlit as st
+from dotenv import load_dotenv 
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chat_models import ChatOpenAI
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from langchain.llms import HuggingFaceHub
+from html_template import css, bot_template, user_template
+
+
+def get_pdf_text(pdf_docs):
+    text = ''
+    for pdf in pdf_docs:
+        reader = PdfReader(pdf)
+        for page in reader.pages:
+            text += page.extract_text()
+    return text
+
+def get_text_chuks(raw_text):
+    text_splitter = CharacterTextSplitter(
+        separator = '\n',
+        chunk_size = 1000,
+        chunk_overlap  = 200,
+        length_function = len
+    )
+    chunks = text_splitter.split_text(raw_text)
+    return chunks
+
+def get_vector_store(text_chunks):
+    # embeddings = OpenAIEmbeddings()
+    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    vector_store = FAISS.from_texts(text_chunks, embeddings)
+    return vector_store
+
+def get_conversation_chain(vectorstore):
+    llm = ChatOpenAI(temperature=0.2)
+    # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.2, "max_length":512})
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+    conversation_chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=vectorstore.as_retriever(),
+        memory=memory,
+        # retriever_kwargs={"k": 1},
+    )
+    return conversation_chain
+
+def handle_user_question(user_question):
+    response = st.session_state.conversation({"question": user_question})
+    st.session_state.chat_history = response['chat_history']
+
+    for i, message in enumerate(st.session_state.chat_history):
+        if i % 2 == 0:
+            st.write(user_template.replace(
+                "{{MSG}}", message.content), unsafe_allow_html=True)
+        else:
+            st.write(bot_template.replace(
+                "{{MSG}}", message.content), unsafe_allow_html=True)
+
+def main():
+  load_dotenv()
+  st.set_page_config(page_title='Chat with your PDFs', page_icon='📂', layout='wide')
+  st.header('Chat with multiple PDFs :books:')
+  
+#   st.write(bot_template.replace('{{MSG}}', 'hello user'), unsafe_allow_html=True)
+#   st.write(user_template.replace('{{MSG}}', 'hello bot'), unsafe_allow_html=True)
+
+  
+  
+  st.write(css, unsafe_allow_html=True)
+
+  if 'conversation' not in st.session_state:
+    st.session_state.conversation = None
+  if "chat_history" not in st.session_state:
+    st.session_state.chat_history = None
+
+  with st.sidebar:
+    st.subheader('Document')
+    pdf_docs = st.file_uploader('Upload your PDFs here and click on Process', accept_multiple_files=True)
+    
+    if st.button('Process'):
+      with st.spinner('Processing...'):
+        # get pdf text
+        raw_text = get_pdf_text(pdf_docs)
+        # get the text chunks
+        text_chunks = get_text_chuks(raw_text)
+        # create vector store
+        vectorstore = get_vector_store(text_chunks)
+        # create conversation chain
+        st.session_state.conversation = get_conversation_chain(vectorstore)
+
+  user_question = st.text_input('Ask a question about your pdf')
+  if user_question:
+     handle_user_question(user_question)
+
+if __name__ == '__main__':
+  main()

html_template.py

@@ -0,0 +1,44 @@
+css = '''
+<style>
+.chat-message {
+    padding: 1.5rem; border-radius: 0.5rem; margin-bottom: 1rem; display: flex
+}
+.chat-message.user {
+    background-color: #2b313e
+}
+.chat-message.bot {
+    background-color: #475063
+}
+.chat-message .avatar {
+  width: 20%;
+}
+.chat-message .avatar img {
+  max-width: 78px;
+  max-height: 78px;
+  border-radius: 50%;
+  object-fit: cover;
+}
+.chat-message .message {
+  width: 80%;
+  padding: 0 1.5rem;
+  color: #fff;
+}
+'''
+
+bot_template = '''
+<div class="chat-message bot">
+    <div class="avatar">
+        <img src="https://is1-ssl.mzstatic.com/image/thumb/Purple116/v4/b4/fd/80/b4fd8051-7763-fbb1-4577-d2aba243f312/AppIcon-1x_U007emarketing-0-10-0-85-220.png/512x512bb.jpg" style="max-height: 78px; max-width: 78px; border-radius: 50%; object-fit: cover;">
+    </div>
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+user_template = '''
+<div class="chat-message user">
+    <div class="avatar">
+        <img src="https://tulipbot.com/img/av-1.png">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''