Code added

.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 @@
+3.11.4

app.py

@@ -0,0 +1,104 @@
+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 htmlTemplates import css, bot_template, user_template, hide_st_style, footer
+from langchain.llms import HuggingFaceHub
+from matplotlib import style
+
+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 = 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):
+    if st.session_state.conversation is None:
+        st.error("Please upload PDF data before starting the chat.")
+        return
+
+    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="Ask to your Own AI",
+                    page_icon="icon.png")
+    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 AI with Custom Data 🚀")
+    user_question = st.text_input("Ask a question about your Data:  ^_^")
+
+    with st.sidebar:
+        st.subheader("Your documents")
+        pdf_docs = st.file_uploader(
+            "Upload your Data here  in PDF format and click on 'Process'", accept_multiple_files=True, type=['pdf'])
+
+        if st.button("Process"):
+            if pdf_docs is None:
+                st.error("Please upload at least one PDF file.")
+            else:
+                with st.spinner("Processing"):
+                    raw_text = get_pdf_text(pdf_docs)
+                    text_chunks = get_text_chunks(raw_text)
+                    vectorstore = get_vectorstore(text_chunks)
+                    st.session_state.conversation = get_conversation_chain(vectorstore)
+                    st.success("Your Data has been processed successfully")
+
+    if user_question:
+        handle_userinput(user_question)
+
+    st.markdown(hide_st_style, unsafe_allow_html=True)
+    st.markdown(footer, unsafe_allow_html=True)
+
+if __name__ == '__main__':
+    main()

example.env

@@ -0,0 +1,2 @@
+OPENAI_API_KEY='PASTE YOUR API HERE'
+HUGGINGFACEHUB_API_TOKEN='PASTE YOUT API HERE'

htmlTemplates.py

@@ -0,0 +1,80 @@
+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;
+}
+.footer {
+    position: fixed;
+    left: 0;
+    bottom: 0;
+    width: 100%;
+    background-color: #2b313e;
+    color: white;
+    text-align: right;
+}
+
+.footer p {
+    margin: 0;
+    padding: 1rem;
+}
+
+a:link {
+        color: #64feda;
+        background-color: transparent;
+        text-decoration: none;
+        }
+
+</style>
+'''
+
+bot_template = '''
+<div class="chat-message bot">
+    <div class="avatar">
+        <img src="https://pub-f858c7e521464395920779af297fb1bd.r2.dev/240 YesbhautikX Fevicon.png" style="max-height: 78px; max-width: 78px; border-radius: 20%; object-fit: cover;">
+    </div>
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+user_template = '''
+<div class="chat-message user">
+    <div class="avatar">
+        <img src="https://youareunique.co.in/wp-content/uploads/2023/04/Bhautik-Bavadiya-Yesbhautik-Yesbhautik-Youareunique.png" style="max-height: 78px; max-width: 78px; border-radius: 20%; object-fit: cover;">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''
+
+hide_st_style = """
+            <style>
+            MainMenu {visibility: hidden;}
+            footer {visibility: hidden;}
+            </style>
+"""
+
+footer = """
+        <div class="footer">
+        <p>Made with <a href="https://streamlit.io" style="color:#36AE7C;">Streamlit</a> by <a href="https://yesbhautik.co.in" style="color:#64feda;">Yesbhautik</a></p>
+        </div>
+"""
+        

requirements.txt

@@ -0,0 +1,14 @@
+langchain
+PyPDF2
+python-dotenv
+streamlit
+openai
+faiss-cpu
+altair
+tiktoken
+# uncomment to use huggingface llms
+# huggingface-hub==0.14.1
+
+# uncomment to use instructor embeddings
+# InstructorEmbedding==1.0.1
+# sentence-transformers==2.2.2