Duplicate from arnold-anand/chat-with-pdf

Co-authored-by: Arnold Anand P <[email protected]>

.env

@@ -0,0 +1 @@
+OPENAI_API_KEY= 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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
+*.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

.gitignore

@@ -0,0 +1 @@
+.env

README.md

@@ -0,0 +1,14 @@
+---
+title: Chat With Pdf
+emoji: 🚀
+colorFrom: indigo
+colorTo: purple
+sdk: streamlit
+sdk_version: 1.21.0
+app_file: app.py
+pinned: false
+license: gpl-3.0
+duplicated_from: arnold-anand/chat-with-pdf
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,77 @@
+import streamlit as st
+import streamlit as st
+from dotenv import load_dotenv
+from PyPDF2 import PdfReader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.chat_models import ChatOpenAI
+from langchain.embeddings import OpenAIEmbeddings, HuggingFaceInstructEmbeddings
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+# from langchain.llms import HuggingFaceHub
+from streamlit_chat import message
+def get_pdf_text(pdfs):
+  text=""
+  for pdf in pdfs:
+    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 = HuggingFaceHub(repo_id="google/flan-t5-xxl")
+    llm = ChatOpenAI()
+    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 user_input(user_question):
+  response = st.session_state.conversation({'question':user_question})
+  st.session_state.chat_history = response['chat_history']
+  for i, messages in enumerate(st.session_state.chat_history):
+      if i % 2 == 0:
+          message(messages.content, is_user=True)
+      else:
+          message(messages.content)
+def main():
+  load_dotenv()
+  st.set_page_config(page_title="Chat with PDF")
+  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 PDF")
+  user_question = st.text_input("Ask a question about your documents...")
+  if user_question:
+    user_input(user_question)
+  with st.sidebar:
+    st.subheader("Your Documents")
+    pdfs = st.file_uploader("Upload here", accept_multiple_files=True)
+    if st.button("Process"):
+      with st.spinner("Processing"):
+        raw_text = get_pdf_text(pdfs)
+#         print(raw_text)
+        chunks = get_text_chunks(raw_text)
+        vectorstore = get_vectorstore(chunks)
+        st.session_state.conversation = get_conversation_chain(vectorstore)
+        st.success("Processing Complete !")
+
+if __name__ == '__main__':
+  main()

requirements.txt

@@ -0,0 +1,8 @@
+langchain==0.0.222
+PyPDF2==3.0.1
+python-dotenv==1.0.0
+streamlit==1.24.0
+streamlit_chat==0.1.1
+openai==0.27.8
+tiktoken==0.4.0
+faiss-cpu