Spaces:
Sleeping
Sleeping
| import os | |
| import getpass | |
| from langchain_community.document_loaders import ConfluenceLoader | |
| from langchain_google_genai import ChatGoogleGenerativeAI, GoogleGenerativeAIEmbeddings | |
| from langchain.text_splitter import RecursiveCharacterTextSplitter | |
| from langchain_community.vectorstores.faiss import FAISS | |
| import google.generativeai as genai | |
| from langchain.prompts import PromptTemplate | |
| from langchain.chains.question_answering import load_qa_chain | |
| import streamlit as st | |
| confluence_api_key = os.environ["CONFLUENCE_API_KEY"] | |
| if "GOOGLE_API_KEY" not in os.environ: | |
| os.environ["GOOGLE_API_KEY"] = getpass.getpass("Please provide Google API Key") | |
| google_api_key = os.environ['GOOGLE_API_KEY'] | |
| genai.configure(api_key=google_api_key) | |
| loader = ConfluenceLoader( | |
| url=os.environ["CONFLUENCE_URL"], space_key=os.environ['SPACE_KEY'], username=os.environ['USERNAME'], api_key=confluence_api_key | |
| ) | |
| conf_docs = loader.load(page_id=os.environ["PAGE_ID"]) | |
| text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000) | |
| chunks = text_splitter.split_text(conf_docs[-1].page_content) | |
| embeddings = GoogleGenerativeAIEmbeddings(model='models/embedding-001') | |
| llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-latest") | |
| vector_store = FAISS.from_texts(chunks, embedding=embeddings) | |
| vector_store.save_local("faiss_index") | |
| #chat_history = [] | |
| def get_response(query, chat_history): | |
| prompt_template = """ | |
| Answer the question as detailed as possible based on the conversation history and the provided context, make sure to provide all the details, if the answer is not in | |
| provided context just say, "I am not able to help. Please contact Platform Support Team at [email protected]", don't provide the wrong answer\n\n | |
| Conversation History:\n {chat_history}\n | |
| Context:\n {context}?\n | |
| Question: \n{question}\n | |
| Answer: | |
| """ | |
| prompt = PromptTemplate(template=prompt_template, input_variables=["chat_history", "context", "question"]) | |
| chain = load_qa_chain(llm, chain_type="stuff", prompt=prompt) | |
| db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True) | |
| docs = db.similarity_search(query) | |
| response = chain({"input_documents" : docs, "question": query, "chat_history": chat_history}, return_only_outputs = True) | |
| return response["output_text"] | |
| if __name__ == '__main__': | |
| st.set_page_config("Chat with Confluence Page") | |
| st.header("Chat with Confluence Page using AI") | |
| if "messages" not in st.session_state: | |
| st.session_state.messages = [] | |
| for message in st.session_state.messages: | |
| with st.chat_message(message["role"]): | |
| st.markdown(message["content"]) | |
| if question := st.chat_input("Ask questions related to login and registration"): | |
| st.session_state.messages.append({"role": "user", "content": question}) | |
| with st.chat_message("user"): | |
| st.markdown(question) | |
| with st.chat_message("assistant"): | |
| answer = get_response(question, st.session_state.messages) | |
| st.write(answer) | |
| st.session_state.messages.append({"role": "assistant", "content": answer}) |