common.py

#Central storage for variables, objects, templates used by both apps
import os

#Importing dependencies
from langchain.chat_models import ChatOpenAI
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain
from langchain.tools import WikipediaQueryRun
from langchain.utilities import WikipediaAPIWrapper

#Prompt variables dictionary: Definitions of 4th grade Common Core Standards according to source provided by Crossover
standard_definition_dict = {
    "CCSS.ELA-LITERACY.W.4.1":"Write opinion pieces on topics or texts, supporting a point of view with reasons and information",
    "CCSS.ELA-LITERACY.W.4.2":"Write informative/explanatory texts to examine a topic and convey ideas and information clearly",
    "CCSS.ELA-LITERACY.W.4.3":"Write narratives to develop real or imagined experiences or events using effective technique, descriptive details, and clear event sequences",
    "CCSS.ELA-LITERACY.W.4.4":"Produce clear and coherent writing in which the development and organization are appropriate to task, purpose, and audience",
    "CCSS.ELA-LITERACY.W.4.5":"Develop and strengthen writing as needed by planning, revising, and editing - with guidance and support from peers and adults",
    "CCSS.ELA-LITERACY.W.4.6":"Use technology, including the Internet, to produce and publish writing as well as to interact and collaborate with others; demonstrate sufficient command of keyboarding skills to type a minimum of one page in a single sitting - with some guidance and support from adults",
    "CCSS.ELA-LITERACY.W.4.7":"Conduct short research projects that build knowledge through investigation of different aspects of a topic",
    "CCSS.ELA-LITERACY.W.4.8":"Recall relevant information from experiences or gather relevant information from print and digital sources; take notes and categorize information, and provide a list of sources",
    "CCSS.ELA-LITERACY.W.4.9":"Draw evidence from literary or informational texts to support analysis, reflection, and research",
    "CCSS.ELA-LITERACY.W.4.10":"Write routinely over extended time frames (time for research, reflection, and revision) and shorter time frames (a single sitting or a day or two) for a range of discipline-specific tasks, purposes, and audiences"   
    }

#Prompt variables dictionary: Definitions on how the AI's FRQ output must be formulated depending on the CCS selected, 
#since a FRQ is not always a question in the grammatical sense
question_or_task_dict = {
    "CCSS.ELA-LITERACY.W.4.1": "writing task",
    "CCSS.ELA-LITERACY.W.4.2": "writing task",
    "CCSS.ELA-LITERACY.W.4.3": "creative writing task",
    "CCSS.ELA-LITERACY.W.4.4": "writing task. Also define the purpose and the supposed audience of the student's writing",
    "CCSS.ELA-LITERACY.W.4.5": "writing task",
    "CCSS.ELA-LITERACY.W.4.6": "research and writing task. The student may use the internet for research and ask adults for some guidance",
    "CCSS.ELA-LITERACY.W.4.7": "research and writing task with the goal of expanding the students knowledge",
    "CCSS.ELA-LITERACY.W.4.8": "scientific writing task",
    "CCSS.ELA-LITERACY.W.4.9": "free response question",
    "CCSS.ELA-LITERACY.W.4.10": "homework writing task"
}

#Rubric dictionary: chooses the rubric to displayed in expander after the evaluation
rubric_dict = {
    "CCSS.ELA-LITERACY.W.4.1":"""
•	Write opinion pieces on topics or texts, 
    supporting a point of view with reasons and information.
•	Introduce a topic or text clearly, state an opinion, and
    create an organizational structure in which related ideas 
    are grouped to support the writer's purpose.
•	Provide reasons that are supported by facts and details.
•	Link opinion and reasons using words and phrases (e.g., 
    for instance, in order to, in addition).
•	Provide a concluding statement or section related to the
    opinion presented.
""",
    "CCSS.ELA-LITERACY.W.4.2":"""
•	Write informative/explanatory texts to examine a topic 
    and convey ideas and information clearly.
•	Introduce a topic clearly and group related information 
    in paragraphs and sections; include formatting (e.g., 
    headings), illustrations, and multimedia when useful to 
    aiding comprehension.
•	Develop the topic with facts, definitions, concrete 
    details, quotations, or other information and examples 
    related to the topic.
•	Link ideas within categories of information using words 
    and phrases (e.g., another, for example, also, because).
•	Use precise language and domain-specific vocabulary to 
    inform about or explain the topic.
•	Provide a concluding statement or section related to the
    information or explanation presented.
""",
    "CCSS.ELA-LITERACY.W.4.3":"""
•	Write narratives to develop real or imagined experiences 
    or events using effective technique, descriptive details, 
    and clear event sequences.
•	Orient the reader by establishing a situation and 
    introducing a narrator and/or characters; organize an 
    event sequence that unfolds naturally.
•	Use dialogue and description to develop experiences and 
    events or show the responses of characters to situations.
•	Use a variety of transitional words and phrases to manage 
    the sequence of events.
•	Use concrete words and phrases and sensory details to 
    convey experiences and events precisely.
•	Provide a conclusion that follows from the narrated 
    experiences or events.
""",
    "CCSS.ELA-LITERACY.W.4.4":"""
    Produce clear and coherent writing in which the development
    and organization are appropriate to task, purpose, and 
    audience. (Grade-specific expectations for writing types 
    are defined in standards 1-3 above.)
    """,
    "CCSS.ELA-LITERACY.W.4.5":"""
    With guidance and support from peers and adults, develop 
    and strengthen writing as needed by planning, revising, 
    and editing. (Editing for conventions should demonstrate 
    command of Language standards 1-3 up to and including 
    grade 4 here.)
    """,
    "CCSS.ELA-LITERACY.W.4.6":"""
    With some guidance and support from adults, use technology,
    including the Internet, to produce and publish writing as 
    well as to interact and collaborate with others; 
    demonstrate sufficient command of keyboarding skills to 
    type a minimum of one page in a single sitting.
    """,
    "CCSS.ELA-LITERACY.W.4.7":"""
    Conduct short research projects that build knowledge 
    through investigation of different aspects of a topic.
    """,
    "CCSS.ELA-LITERACY.W.4.8":"""
    Recall relevant information from experiences or gather 
    relevant information from print and digital sources; take 
    notes and categorize information, and provide a list of 
    sources.
    """,
    "CCSS.ELA-LITERACY.W.4.9":"""
•	Draw evidence from literary or informational texts to 
    support analysis, reflection, and research.
•	Apply grade 4 Reading standards to literature (e.g., 
    "Describe in depth a character, setting, or event in a 
    story or drama, drawing on specific details in the text 
    [e.g., a character's thoughts, words, or actions].").
•	Apply grade 4 Reading standards to informational texts 
    (e.g., "Explain how an author uses reasons and evidence 
    to support particular points in a text").
""",
    "CCSS.ELA-LITERACY.W.4.10":"""
    Write routinely over extended time frames (time for 
    research, reflection, and revision) and shorter time 
    frames (a single sitting or a day or two) for a range of 
    discipline-specific tasks, purposes, and audiences
    """   
    }

#Prompt templates: where the actual prompt engineering is happening. See google doc for further reference
prompt_context = PromptTemplate(
    input_variables=["chosen_topic", "wikitext"],
    template="You are a writer at a school book publishing company. \
        You will be given a certain topic, then your task is to write a school book article about it. \
        Choose your words in accordance to the teachings of Wikipedia, precisely the explanations you find at the end of this prompt. \
        Please do only include full sentences in your answer. \
        The article should have a clearly defined thread that is easy to follow. \
        Please do not give the article a title, only include the body in your answer. \
        Please write in a style that is fun to read and understandable by 12 year old kids. \
        The article should be around 10-15 sentences long. \n\
        \n\
        Topic: {chosen_topic} \n\
        \n\
        Wikipedia: \n\
        {wikitext}"
)
prompt_frq = PromptTemplate(
    input_variables=["context", "standard_definition", "question_or_task"],
    template="You are a 4th grade school teacher. \
        You will be given an input text, which is a short article on a certain topic. \
        Thematizing the content of the input text and adressing a 4th grade student, you will then generate a {question_or_task}. \
        Do not include a title such as 'Question:' or 'Writing task:' in your output. \
        Your output must be formulated in such a way that it can be used to test a person's ability to {standard_definition}. \n\
        \n\
        Input text: \n\
        \n\
        {context}"
)
prompt_evaluation = PromptTemplate(
    input_variables=["context", "rubric", 
        "frq", "chosen_answer"],
    template="You are a 4th grade school teacher. \
        You will be given four inputs: An article on a certain topic. \
        A task or question related to said article, meant to be solved by a 4th grade student. \
        The answer to said task or question, written by one of your students. \
        A standard for evaluating said answer.\
        Your output should be an objective evaluation of the student's answer, taking all inputs into account. \
        Here are your inputs: \n\
        \n\
        The article: \n\
        \n\
        {context} \n\
        \n\
        The task or question: \n\
        \n\
        {frq} \n\
        \n\
        The student's answer: \n\
        \n\
        {chosen_answer} \n\
        \n\
        The standard:\
        \n\
        The student should be able to {rubric}. \n\
        \n\
        Now please take some time to formulate your output, by thoroughly looking at each input. Also think about whether \
        the student has showcased the required ability or not. In other words, whether he passed or failed the test, and why. \
        Structure your output like this: \n\
        \n\
        'PASSED' or 'FAILED'\n\
        Evaluation / Explaination"
)
prompt_topic_rand = PromptTemplate(input_variables=["var"], template="{var} give me a random \
    writing topic in one or maximum two words. Please nothing about sex, drugs, alcohol or violence.")
prompt_answer_good = PromptTemplate(input_variables=["context", "frq", "standard"],
    template="You are a Senior Test Manager at a successful software company and a very smart person. \
        Your job is to test a new educational software. \
        Please read this text presented to you below, then answer the task or question that follows. \
        Please do not simply copy whole sentences from the text. Just behave like you were back in junior high, \
        where you always had the best English grades of the entire school. \
        Please formulate your answer in a way, that shows off your ability to {standard}. \
        The purpose of the software is to measure this ability in a student. \n\n\
        Here is the text: \n\
        {context} \n\n\
        Here is the task or question: \n\
        {frq} \n\n\
        Please take some time to think, then give it your best shot.")
prompt_answer_bad = PromptTemplate(input_variables=["context", "frq"],
    template="You are a 10 year old student taking an English exam. You are not particularly intelligent. \
        Unfortunately you also have troubling focusing on tasks and you happen to get the worst English grades of the entire class. \
        Quit reading and homework does just not feel natural for you. You do not even mind, since you are good at a lot of other things. \
        You are, for example, an incredibly creative person and like to tell stories. \
        Please read this text presented to you below, then answer the task or question that follows. \
        \n\n\
        Here is the text: \n\
        {context} \n\n\
        Here is the task or question: \n\
        {frq} \n\n\
        Please remember: you will NOT perform well on this task. Create a poorly formulated answer, \
        using a bit of bad grammar and also make some logical mistakes. \
        Clearly indicating that you do not possess the skills being tested.\
        You must try hard but still fail at this exam.") 
prompt_qc_run = PromptTemplate(input_variables=["context", "frq", "rubric", \
    "answer_good", "evaluation_good", "answer_bad", "evaluation_bad"], 
    template="You are a Senior Test Manager with 15 years of experience at a successful software company. \
        Your daily business is to test educational KI software. You also have a degree in linguistics and love logic puzzles. \
        Please have a look at 7 pieces of text, which will be given to you at the end of this prompt. \
        Here are the 7 descriptions: \
        1. an article on a certain topic, given by the software \n\
        2. a free-response question on this article, given by the software \n\
        3. a certain educational standard rubric, that is used to evaluate the answer on this free-response question \n\
        4. the answer to the free-response question, given by a strong 4th grade student \n\
        5. the evaluation of the strong answer, given by the software \n\
        6. the answer to the free-response question, given by a weak 4th grade student \n\
        7. the evaluation of the weak answer, given by the software \n\
        Your task today is the following: please have a critical look at the output of the software. \
        Take your time on each of the 7 texts, then give critical feedback on any shortcomings of the software's KI. \
        Give recommendations on how to further improve the quality of texts number 1., 2., 5. and 7., \
        by fine-tuning the KI instructions or prompts. \
        Please be rather critical.\n\n\
        {context}\n\n\
        {frq}\n\n\
        {rubric}\n\n\
        {answer_good}\n\n\
        {evaluation_good}\n\n\
        {answer_bad}\n\n\
        {evaluation_bad}")
prompt_qc_grade = PromptTemplate(input_variables=["qc_report"], 
    template="You will be given a precise report that was written to evaluate a new software's performance. \
        Take a good look at the report and decide on an overall evaluation grade that aligns with the entire report's sentiment. \
        The grade should be a percentage (integer between 1 and 100 with a percent symbol) and correctly represent and support the report. \
        Only give an integer and '%' as an output, nothing else.\n\n\
        Here is the report:\n\n\
        {qc_report}")

#Defining LLMs, sources and Chains
llm = ChatOpenAI(model="gpt-4", temperature=0.5)
precise = ChatOpenAI(model="gpt-4", temperature=0.0)
random = ChatOpenAI(model="gpt-4", temperature=0.9)
wikipedia = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper())
context_chain = LLMChain(llm=llm, prompt=prompt_context)
frq_chain = LLMChain(llm=llm, prompt=prompt_frq, )
evaluation_chain = LLMChain(llm=llm, prompt=prompt_evaluation)
qc_answer_good_chain = LLMChain(llm=precise, prompt=prompt_answer_good)
qc_answer_bad_chain = LLMChain(llm=random, prompt=prompt_answer_bad)
topic_rand = LLMChain(llm=random, prompt=prompt_topic_rand)
var="Please"
qc_run_chain = LLMChain(llm=precise, prompt=prompt_qc_run)
qc_grade_chain = LLMChain(llm=precise, prompt=prompt_qc_grade)

#Tiny helper function that is necessary to keep the wikipedia page metadata and/or 
#unrelated following pages from spilling into the LLM's output
def trim_text(input_string):
    keyword1 = "Summary:"
    keyword2 = "Page:"
    index1 = input_string.find(keyword1)
    if index1 == -1:
        new_string = input_string
    else:
        new_string = input_string[index1 + len(keyword1):].strip()
    index2 = new_string.find(keyword2)
    if index2 == -1:
        return new_string
    else:
        return new_string[:index2].strip()

#Function for detecting the use of copy/pasted parts of the context as answer 
def plagiate(context, answer):
    if answer in context:
        return True
    for i in range(len(answer) - 31):
        substring = answer[i:i + 30]
        if substring in context:
            return True    
    return False