| import streamlit as st | |
| import os | |
| from langchain import PromptTemplate, HuggingFaceHub, LLMChain | |
| st.title("Generating Response with HuggingFace Models") | |
| st.markdown("## Model: `facebook/blenderbot-1B-distill`") | |
| def get_response(question: str) -> dict: | |
| """ | |
| Generate a response to a given question using the Blenderbot Large Language Model. | |
| Args: | |
| question (str): The question to be answered. | |
| Returns: | |
| dict: A dictionary containing the response text and metadata. | |
| """ | |
| template = """Question: {question} | |
| Answer: Let's think step by step.""" | |
| prompt = PromptTemplate(template=template, input_variables=["question"]) | |
| llm_chain = LLMChain(prompt=prompt, | |
| llm=HuggingFaceHub(repo_id="facebook/blenderbot-1B-distill", | |
| model_kwargs={"temperature":0, | |
| "max_length":64})) | |
| response = llm_chain.invoke(question) | |
| return response | |
| question = st.text_area("Enter your question here...") | |
| if st.button("Get Response") and question: | |
| with st.spinner("Generating Response..."): | |
| answer = get_response(question) | |
| if answer is not None: | |
| st.success('Great! Response generated successfully') | |
| st.write(answer) | |
| st.write(answer["text"]) |