Spaces:
Sleeping
Sleeping
| import streamlit as st | |
| # from langchain_helper import get_qa_chain, create_vector_db | |
| from langchain.vectorstores import FAISS | |
| from langchain.llms import GooglePalm | |
| from langchain.document_loaders.csv_loader import CSVLoader | |
| from langchain.embeddings import HuggingFaceInstructEmbeddings | |
| from langchain.prompts import PromptTemplate | |
| from langchain.chains import RetrievalQA | |
| from dotenv import load_dotenv | |
| load_dotenv() | |
| import os | |
| # get this free api key from https://makersuite.google.com/ | |
| llm = GooglePalm(google_api_key=os.environ["GOOGLE_API_KEY"], temperature=0.1) | |
| instructor_embeddings = HuggingFaceInstructEmbeddings(model_name="hkunlp/instructor-large") | |
| vectordb_file_path = "faiss_index" | |
| def get_qa_chain(): | |
| # Load the vector database from the local folder | |
| vectordb = FAISS.load_local(vectordb_file_path, instructor_embeddings) | |
| # Create a retriever for querying the vector database | |
| retriever = vectordb.as_retriever(score_threshold=0.7) | |
| prompt_template = """Given the following context and a question, generate an answer based on this context only. | |
| In the answer try to provide as much text as possible from "response" section in the source document context without making much changes. | |
| If the answer is not found in the context, kindly state "I don't know." Don't try to make up an answer. | |
| CONTEXT: {context} | |
| QUESTION: {question}""" | |
| PROMPT = PromptTemplate( | |
| template=prompt_template, input_variables=["context", "question"] | |
| ) | |
| chain = RetrievalQA.from_chain_type(llm=llm, | |
| chain_type="stuff", | |
| retriever=retriever, | |
| input_key="query", | |
| return_source_documents=True, | |
| chain_type_kwargs={"prompt": PROMPT}) | |
| return chain | |
| st.title("Q&A for My Courses ") | |
| # btn = st.button("Create Knowledgebase") | |
| # if btn: | |
| # create_vector_db() | |
| question = st.text_input("Question: ") | |
| if question: | |
| chain = get_qa_chain() | |
| response = chain(question) | |
| st.header("Answer") | |
| st.write(response["result"]) | |