Duplicate from gli-mrunal/GPT_instruct_chatbot

Co-authored-by: Mrunal <gli-mrunal@users.noreply.huggingface.co>

.env

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

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+images/bot.jpg filter=lfs diff=lfs merge=lfs -text

.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/

README.md

@@ -0,0 +1,14 @@
+---
+title: GPT Instruct Chatbot
+emoji: 🏆
+colorFrom: red
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: gli-mrunal/GPT_instruct_chatbot
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,149 @@
+# GPT Chatbot 
+
+# Create Conda virtual environment
+# conda create --name gpt_chatbot  python=3.9.4
+# conda activate gpt_chatbot
+
+# Installation
+# pip install streamlit pypdf2 langchain python-dotenv faiss-cpu openai huggingface_hub
+# pip install tiktoken 
+
+# pip install InstructorEmbedding sentence_transformers
+
+# Could not import tiktoken python package. This is needed in order to for OpenAIEmbeddings. Please install it with `pip install tiktoken`.
+# run the app using the following command in anaconda VS Code terminal
+# streamlit run app.py
+
+
+
+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 # FAISS instead of PineCone
+from langchain.llms import OpenAI
+from langchain.llms import HuggingFaceHub
+from langchain.chat_models import ChatOpenAI
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from htmlTemplates import css, bot_template, user_template 
+
+def get_pdf_text(pdf_docs):
+    text =""
+    for pdf in pdf_docs:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    return text
+
+def get_text_chunks(text):
+    text_splitter = CharacterTextSplitter(
+        separator="\n",
+        chunk_size=1000,
+        chunk_overlap=200,
+        length_function=len
+    )
+    chunks = text_splitter.split_text(text)
+    return  chunks
+
+def get_vectorstore(text_chunks):
+    # embeddings = OpenAIEmbeddings()
+    embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-xl")
+    vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+    return vectorstore
+
+  
+
+def get_conversation_chain(vectorstore):
+    llm = OpenAI()
+    #llm = ChatOpenAI()
+    #llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "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
+    )
+    return conversation_chain
+
+
+
+def handle_userinput(user_question):
+    # st.session_state.conversation contains all the configuration from our vectorstore and memory.
+    response = st.session_state.conversation({'question': user_question})
+    # st.write(response)
+    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 multiple law journal PDFs",
+                        page_icon=":books:")
+    
+    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
+    
+    st.header("Chat with multiple PDFs :books:")
+
+    user_question = st.text_input("Ask a question about your documents:")
+    if user_question:
+        handle_userinput(user_question)
+
+    #st.write(user_template.replace("{{MSG}}", "hello robot"), unsafe_allow_html=True)
+    #st.write(bot_template.replace("{{MSG}}", "hello human"), unsafe_allow_html=True)
+
+    # "https://i.ibb.co/rdZC7LZ/Photo-logo-1.png"
+    # "https://huggingface.co/spaces/gli-mrunal/GPT_instruct_chatbot/blob/main/images/bot.jpg" 
+    # "https://huggingface.co/spaces/gli-mrunal/GPT_instruct_chatbot/blob/main/images/CSUN_Matadors_logo.svg.png"
+
+    with st.sidebar:
+        st.subheader("Your documents")
+
+        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)
+                #st.write(raw_text)
+
+                # ----------   get the text chunks  -------------------------
+
+                text_chunks = get_text_chunks(raw_text)
+                #st.write(text_chunks)
+
+
+                # --------------   create vector store------------------------
+                # https://openai.com/pricing  --> Embedding Models
+                # Chose to use the best embedding model - intructor_xl ranked higher than OpenAi's embeddings from huggingface leaderboard
+                # https://huggingface.co/spaces/mteb/leaderboard
+
+                vectorstore = get_vectorstore(text_chunks)
+
+                # create conversation chain
+                st.session_state.conversation = get_conversation_chain(vectorstore)
+                #conversation = get_conversation_chain(vectorstore)
+
+    #st.session_state.conversation
+
+
+
+            
+
+if __name__ == '__main__':
+    main()

htmlTemplates.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://github.com/gli-mrunal/test_images/blob/main/gpt.jpg?raw=true" 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://github.com/gli-mrunal/test_images/blob/main/user.png?raw=true">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''

requirements.txt

@@ -0,0 +1,13 @@
+langchain
+PyPDF2==3.0.1
+python-dotenv==1.0.0
+streamlit==1.18.1
+openai==0.27.6
+faiss-cpu==1.7.4
+
+# uncomment to use huggingface llms
+huggingface-hub==0.14.1
+
+# uncomment to use instructor embeddings
+InstructorEmbedding==1.0.1
+sentence-transformers==2.2.2