# import streamlit as st # # # @st.cache_resource # # def init_PE(): # # data = {"Persona Pattern":{"Intuition":"","Format":2,"Examples":3 }, # # "Question Refinement":{"Intuition":,"Format":,"Examples": }, # # "Cognitive Verifier":{"Intuition":,"Format":,"Examples": }, # # "Audience Persona":{"Intuition":,"Format":,"Examples": }, # # "Flipped Interaction":{"Intuition":,"Format":,"Examples": }, # # "Few-Shot Prompting":{"Intuition":,"Format":,"Examples": }, # # "Chain-Of-Thought":{"Intuition":,"Format":,"Examples": }, # # "Reason+Act Prompting":{"Intuition":,"Format":,"Examples": }, # # "Gameplay Pattern":{"Intuition":,"Format":,"Examples": }, # # "Template Pattern":{"Intuition":,"Format":,"Examples": }, # # "Meta Language":{"Intuition":,"Format":,"Examples": }, # # "Alternative Approach":{"Intuition":,"Format":,"Examples": }, # # "Outline Expansion":{"Intuition":,"Format":,"Examples": }} # st.title("Prompt Engineering Techniques") # st.markdown( # """ # Welcome to the prompt engineering section! Here # we aim to introduce some common techniques used to generate # consistent outputs from large language models like GPT and LlaMA. # """ # ) # PE_options = st.multiselect("Select which Prompt Engineering options you are interested in",["Persona Pattern","Question Refinement","Cognitive Verifier", # "Audience Persona","Flipped Interaction", "Few-Shot Prompting","Chain-Of-Thought", # "Reason+Act Prompting","Gameplay Pattern","Template Prompting", # "Meta Language Creation","Recipe Prompting","Alternative Approach", # "Outline Expansion"]) # c11,c21 = st.columns([1,1]) # with c11: # st.markdown( # """ # ### Persona Pattern # """ # ) # with st.expander("View Explanation and Examples"): # st.markdown( # """ # **1. Intuition ** # Tell the LLM to act as a specific person,object or entity and then # provide them with a relevant task. # **2. Format ** # "Act as entity X, perform task Y." # **3. Example** # "Act as a expert AI Engineer, explain to me how back-propagation works." # """, # unsafe_allow_html=True # ) # # with c21: # st.markdown( # """ # ### Question Refinement # """ # ) # with st.expander("View Explanation and Examples"): # st.markdown( # """ # **1. Intuition **
# To ensure that the LLM can suggest # potentially better or more refined questions for the user to ask.
# **2. Format **
# "Whenever I ask a question, suggest a # better question and ask me if I would like to use it instead.
# **3. Example**
# Just enter this prompt into the chat before asking your question
# """, # unsafe_allow_html=True # # ) # c21,c22 = st.columns([1,1]) # with c21: # st.markdown( # """ # ### Cognitive Verifier # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition ** # To force the LLM to subdivide the original question # into multiple questions and use the answers to all those questions to fit into the final answer # **2. Format ** # "When you are asked a question,follow these rules:
Generate a number of additional questions that would help more accurately answer the question.
# Combine the answers to the individual questions to produce the final answer to the overall question." # **3. Example** # Just enter this prompt into the chat before asking your question. # """, # unsafe_allow_html=True # ) # # with c22: # st.markdown( # """ # ### Audience Persona # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Intuition is for the LLM to know your level of # expertise so that it can better tailor it's answers to your needs
# **2. Format **
# "Explain X to me. Assume I am persona Y."
# **3. Example**
# "Explain the self-attention mechanism to me. # Assume I am a beginner with 0 knowledge." # """, # unsafe_allow_html=True # ) # # c31,c32 = st.columns([1,1]) # with c31: # st.markdown( # """ # ### Flipped Interaction # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# For the LLM to be like a diagnoser and ask the # user questions until a result is met.
# **2. Format **
# "I would like you to ask me questions to help me # achieve X."
# **3. Example**
# "I would like you to ask me questions to help me create variations of my marketing materials. You should ask questions until you have sufficient information about my # current draft messages, audience, and goals. Ask me the first question."
# """, # unsafe_allow_html=True # ) # # with c32: # st.markdown( # """ # ### Few-Shot Prompting # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# To give the LLM some input and output # pairs and hopefully it can learn and generate the expected output # from given input. Very similar to conventional training paradigm minus # weight updates.
# **2. Format **
# "Input:X, Output: Y"(Simple)
# "Situation:X, Think_1:Y,Action_1:Z,Think_2: A, Action_2: B"(Step by step)
# **3. Example**
# "1. Review: "The film was absolutely fantastic, with a gripping storyline and excellent acting." # Classification: Positive
2. Review: "I found the movie to be a complete waste of time, with poor plot development and bad acting." # Classification: Negative"
# """, # unsafe_allow_html=True # ) # # c41,c42 = st.columns([1,1]) # # with c41: # st.markdown( # """ # ### Chain-Of-Thought # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Similar to few-shot prompting except # now we provide reasoning for the output as well.
# **2. Format **
# "Question, step by step solution and then solution"
# **3. Example**
# "Solve the following problem step-by-step: # # Problem: What is the result of 8 multiplied by 7 plus 6? # # Step-by-step solution: # 1. First, calculate the multiplication: 8 * 7 = 56 # 2. Then, add 6 to the result: 56 + 6 = 62 # # Answer: 62"
# """, # unsafe_allow_html=True # ) # # with c42: # st.markdown( # """ # ### Reason+Act Prompting # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Very similar to Chain-Of-Thought except now # we also teach the LLM to use external tools to get information.
# **2. Format **
# "Question,Think,Action,Result"
# **3. Example**
# "**Question:** Aside from the apple remote, what other # device can control the program apple remote?
# **Task:** I need to find out search Apple Remote and find out the devices it was originally programmed to interact with
# **Action:** Search [Apple Remote](https://en.wikipedia.org/wiki/Apple_Remote_Desktop)
# **Result:** Apple Remote Desktop (ARD) is a Macintosh application produced by Apple Inc., first released on March 14, 2002, that replaced a similar product called Apple Network Assistant"
# """, # unsafe_allow_html=True # ) # # c51,c52 = st.columns([1,1]) # with c51: # st.markdown( # """ # ### Gameplay Pattern # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Imagine you want to learn about a new topic # , you can format it as a game and play with the LLM.
# **2. Format **
# Create a game about X topic. Describe the rules.
# **3. Example**
# "Create a game about prompt engineering. Ask me a series of questions # about prompt engineering and see how many I get right. If I get it wrong correct me."
# """, # unsafe_allow_html=True # ) # # with c52: # st.markdown( # """ # ### Template Prompting # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Basically give a template of the output that you want the # LLM to follow.
# **2. Format **
# Task, template
# **3. Example**
# "Create a random strength workout for me today with complementary exercises. I am going to provide a template for your output . CAPITALIZED WORDS are my placeholders for content. Try to fit the output into one or more of the placeholders that I list. # Please preserve the formatting and overall template that I provide. # This is the template: NAME, REPS @ SETS, MUSCLE GROUPS WORKED, DIFFICULTY SCALE 1-5, FORM NOTES"
# """, # unsafe_allow_html=True # ) # # c61,c62 = st.columns([1,1]) # # with c61: # st.markdown( # """ # ### Meta Language Creation # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Basically teaching the LLM your own # secret language like when you say X you mean Y.
# **2. Format **
# "When I say X, I mean Y (or would like you to do Y)"
# **3. Example**
# "When I say "variations of companies", I mean give me ten different variations of tech companies"
# """ # ) # # with c62: # st.markdown( # """ # ### Recipe Prompting # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Asking a question to the LLM and also # letting it know that there exists intermediate steps required.
# **2. Format **
# I would like to achieve X. # I know that I need to perform steps A,B,C. Please provide me with the # necessary steps as well as any missing steps.
# **3. Example**
# "I would like to drive to MBS from Jurong. I know that I want to go through AYR and I don't want to drive more than 300 miles per day. # Provide a complete sequence of steps for me. Fill in any missing steps."
# """, # unsafe_allow_html=True # ) # # c71,c72 = st.columns([1,1]) # # with c71: # st.markdown( # """ # ### Alternative Approach # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# To allow the LLM to return users # alternative approaches to solve a problem.
# **2. Format **
# "If there are alternative ways to accomplish a task X that I give you, list the best alternate approaches "
# **3. Example**
# Just input the above prompt before asking your question or task.
# """, # unsafe_allow_html=True # ) # # with c72: # st.markdown( # """ # ### Outline Expansion # """ # ) # with st.expander("View Explanations and Examples"): # st.markdown( # """ # **1. Intuition **
# Give the LLM a topic to provide # an outline on and then proceed to ask it to expand on a certain part.
# **2. Format **
# "Act as an outline expander. # Generate a bullet point outline based on the input that I give you and then ask me for which bullet point you should expand on. # Create a new outline for the bullet point that I select. # At the end, ask me for what bullet point to expand next."
# **3. Example**
# "Act as an outline expander. Generate a bullet point outline based on the input that I give you and then ask me for which bullet point you should expand on. Each bullet can have at most 3-5 sub bullets. The bullets should be numbered using the pattern [A-Z].[i-v].[* through ****]. Create a new outline for the bullet point that I select. At the end, ask me for what bullet point to expand next. Ask me for what to outline."
# """, # unsafe_allow_html=True # ) #