uploaded the files

app.py

@@ -0,0 +1,171 @@
+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
+from langchain.llms import HuggingFaceHub
+import os
+
+OPENAI_API_KEY=os.getenv('OPENAI_API_KEY')
+
+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):
+    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 multiple 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)
+
+    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)
+
+                # get the text chunks
+                text_chunks = get_text_chunks(raw_text)
+
+                # create vector store
+                vectorstore = get_vectorstore(text_chunks)
+
+                # create conversation chain
+                st.session_state.conversation = get_conversation_chain(
+                    vectorstore)
+
+
+if __name__ == '__main__':
+    main()
+
+
+
+
+#     Attempting uninstall: tokenizers
+#     Found existing installation: tokenizers 0.15.2
+#     Uninstalling tokenizers-0.15.2:
+#       Successfully uninstalled tokenizers-0.15.2
+#   Attempting uninstall: faiss-cpu
+#     Found existing installation: faiss-cpu 1.8.0.post1
+#     Uninstalling faiss-cpu-1.8.0.post1:
+#       Successfully uninstalled faiss-cpu-1.8.0.post1
+#   Attempting uninstall: python-dotenv
+#     Found existing installation: python-dotenv 1.0.1
+#     Uninstalling python-dotenv-1.0.1:
+#       Successfully uninstalled python-dotenv-1.0.1
+#   Attempting uninstall: pydantic
+#     Found existing installation: pydantic 2.10.2
+#     Uninstalling pydantic-2.10.2:
+#       Successfully uninstalled pydantic-2.10.2
+#   Attempting uninstall: protobuf
+#     Found existing installation: protobuf 4.25.5
+#     Uninstalling protobuf-4.25.5:
+#       Successfully uninstalled protobuf-4.25.5
+#   Attempting uninstall: torch
+#     Found existing installation: torch 2.1.1
+#     Uninstalling torch-2.1.1:
+#       Successfully uninstalled torch-2.1.1
+#   Attempting uninstall: tiktoken
+#     Found existing installation: tiktoken 0.7.0
+#     Uninstalling tiktoken-0.7.0:
+#       Successfully uninstalled tiktoken-0.7.0
+#   Attempting uninstall: huggingface-hub
+#     Found existing installation: huggingface-hub 0.23.4
+#     Uninstalling huggingface-hub-0.23.4:
+#       Successfully uninstalled huggingface-hub-0.23.4
+#   Attempting uninstall: dataclasses-json
+#     Found existing installation: dataclasses-json 0.6.7
+#     Uninstalling dataclasses-json-0.6.7:
+#       Successfully uninstalled dataclasses-json-0.6.7
+#   Attempting uninstall: transformers
+#     Found existing installation: transformers 4.35.2
+#     Uninstalling transformers-4.35.2:
+#       Successfully uninstalled transformers-4.35.2
+#   Attempting uninstall: openai
+#     Found existing installation: openai 1.57.4
+#     Uninstalling openai-1.57.4:
+#       Successfully uninstalled openai-1.57.4
+#   Attempting uninstall: langchain
+#     Found existing installation: langchain 0.2.5
+#     Uninstalling langchain-0.2.5:
+#       Successfully uninstalled langchain-0.2.5
+#   Attempting uninstall: sentence-transformers
+#     Found existing installation: sentence-transformers 3.0.1
+#     Uninstalling sentence-transformers-3.0.1:
+#       Successfully uninstalled sentence-transformers-3.0.1
+#   Attempting uninstall: altair
+#     Found existing installation: altair 5.5.0
+#     Uninstalling altair-5.5.0:
+#       Successfully uninstalled altair-5.5.0
+#   Attempting uninstall: streamlit
+#     Found existing installation: streamlit 1.41.1
+#     Uninstalling streamlit-1.41.1:
+#       Successfully uninstalled streamlit-1.41.1

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://i.ibb.co/cN0nmSj/Screenshot-2023-05-28-at-02-37-21.png" 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://i.ibb.co/rdZC7LZ/Photo-logo-1.png">
+    </div>    
+    <div class="message">{{MSG}}</div>
+</div>
+'''

requirements.txt

@@ -0,0 +1,95 @@
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.11
+aiosignal==1.3.2
+altair==4.0.0
+async-timeout==4.0.3
+attrs==24.3.0
+blinker==1.9.0
+cachetools==5.5.0
+certifi==2024.12.14
+charset-normalizer==3.4.1
+click==8.1.8
+colorama==0.4.6
+dataclasses-json==0.5.14
+entrypoints==0.4
+faiss-cpu==1.8.0.post1
+filelock==3.16.1
+frozenlist==1.5.0
+fsspec==2024.12.0
+gitdb==4.0.11
+GitPython==3.1.43
+greenlet==3.1.1
+huggingface-hub==0.14.1
+idna==3.10
+importlib_metadata==8.5.0
+InstructorEmbedding==1.0.1
+Jinja2==3.1.5
+joblib==1.4.2
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+langchain==0.0.184
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+marshmallow==3.23.2
+mdurl==0.1.2
+mpmath==1.3.0
+multidict==6.1.0
+mypy-extensions==1.0.0
+networkx==3.2.1
+nltk==3.9.1
+numexpr==2.10.2
+numpy==1.26.4
+openai==0.27.6
+openapi-schema-pydantic==1.2.4
+packaging==24.2
+pandas==2.2.3
+pillow==11.0.0
+propcache==0.2.1
+protobuf==3.20.3
+pyarrow==18.1.0
+pydantic==1.10.19
+pydeck==0.9.1
+Pygments==2.18.0
+Pympler==1.1
+PyPDF2==3.0.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.0
+pytz==2024.2
+pywin32==308
+PyYAML==6.0.2
+referencing==0.35.1
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+rpds-py==0.22.3
+safetensors==0.4.5
+scikit-learn==1.6.0
+scipy==1.13.1
+semver==3.0.2
+sentence-transformers==2.2.2
+sentencepiece==0.2.0
+six==1.17.0
+smmap==5.0.1
+SQLAlchemy==2.0.36
+streamlit==1.18.1
+sympy==1.13.1
+tenacity==8.5.0
+threadpoolctl==3.5.0
+tiktoken==0.4.0
+tokenizers==0.13.3
+toml==0.10.2
+toolz==1.0.0
+torch==2.5.1
+torchvision==0.20.1
+tornado==6.4.2
+tqdm==4.67.1
+transformers==4.31.0
+typing-inspect==0.9.0
+typing_extensions==4.12.2
+tzdata==2024.2
+tzlocal==5.2
+urllib3==2.3.0
+validators==0.34.0
+watchdog==6.0.0
+yarl==1.18.3
+zipp==3.21.0