File size: 6,179 Bytes
255d5ac de20926 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac d85e8ac 255d5ac |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 |
import os
import streamlit as st
from dotenv import load_dotenv
from PyPDF2 import PdfReader
from langchain_community.llms import llamacpp
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler
from langchain.vectorstores import Chroma
from langchain.chat_models import ChatOpenAI
from langchain_community.chat_message_histories.streamlit import StreamlitChatMessageHistory
from langchain.prompts import PromptTemplate,SystemMessagePromptTemplate,ChatPromptTemplate
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain.chains import create_history_aware_retriever, create_retrieval_chain, ConversationalRetrievalChain
from langchain.text_splitter import TokenTextSplitter,RecursiveCharacterTextSplitter
from langchain_core.runnables.history import RunnableWithMessageHistory
from langchain_community.document_loaders.directory import DirectoryLoader
from langchain.document_loaders import PyPDFLoader
from htmlTemplates import css, bot_template, user_template
from langchain.memory import ConversationBufferMemory
from langchain.chains import ConversationalRetrievalChain
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain import hub
lang_api_key = os.getenv("lang_api_key")
os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_ENDPOINT"] = "https://api.langchain.plus"
os.environ["LANGCHAIN_API_KEY"] = lang_api_key
os.environ["LANGCHAIN_PROJECT"] = "Chat with multiple PDFs"
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 = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
chunk_size=250, chunk_overlap=50,
separators=["\n \n \n", "\n \n", "\n1", "(?<=\. )", " ", ""],
)
chunks = text_splitter.split_text(text)
return chunks
def get_vectorstore(text_chunks):
model_name = "Alibaba-NLP/gte-base-en-v1.5"
model_kwargs = {'device': 'cpu',
"trust_remote_code" : 'True'}
encode_kwargs = {'normalize_embeddings': True}
embeddings = HuggingFaceEmbeddings(
model_name=model_name,
model_kwargs=model_kwargs,
encode_kwargs=encode_kwargs
)
vectorstore = Chroma.from_texts(
texts=text_chunks, embedding=embeddings, persist_directory="docs/chroma/")
return vectorstore
def get_conversation_chain():
callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
llm = llamacpp.LlamaCpp(
model_path="qwen2-0_5b-instruct-q8_0.gguf",
n_gpu_layers=0,
temperature=0.1,
top_p = 0.9,
n_ctx=20000,
n_batch=2000,
max_tokens = 300,
repeat_penalty=1.9,
last_n_tokens_size = 300,
#callback_manager=callback_manager,
verbose=False,
)
prompt = hub.pull("rlm/rag-prompt")
rag_chain = prompt | llm | StrOutputParser()
return rag_chain
def main():
st.set_page_config(page_title="Chat with multiple PDFs", page_icon=":books:")
st.write(css, unsafe_allow_html=True)
st.header("Chat with multiple PDFs :books:")
st.subheader("Your documents")
pdf_docs = st.file_uploader("For Chatbot to get alive, upload your PDFs here and click on 'Process'", accept_multiple_files=True)
if st.button("Process"):
if pdf_docs:
# 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
conversation = get_conversation_chain()
st.success("Files have been processed into a vector store.")
return vectorstore , conversation
if conversation not None:
st.subheader("Chat Bot")
if user_question := st.text_input("Ask a question about your documents:"):
handle_userinput(user_question, vectorstore, conversation)
def handle_userinput(user_question,vectorstore,conversation ):
if "chat_history" not in st.session_state:
st.session_state["chat_history"] = [
{"role": "assistant", "content": "Hi, I'm a Q&A chatbot who is based on your imported pdf documents . How can I help you?"}
]
st.session_state.chat_history.append({"role": "user", "content": user_question})
retriever = vectorstore.as_retriever(search_type = 'mmr', search_kwargs={"k": 7})
docs = retriever.invoke(user_question)
with st.sidebar:
st.subheader("Your documents")
with st.spinner("Processing"):
for doc in docs:
st.write(f"Document: {doc}")
doc_txt = [doc.page_content for doc in docs]
# Invoke conversation chain
response = conversation.invoke({"context": docs, "question": user_question})
st.session_state.chat_history.append({"role": "assistant", "content": response})
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)
# if 'source_documents' in response:
# st.subheader("Retrieved Documents")
# for doc in response['source_documents']:
# st.write(f"Document: {doc.metadata['source']}")
# st.write(doc.page_content)
if __name__ == '__main__':
main()
|