funtions.py

from exa_py import Exa
from groq import Groq
import os

# Declare the exa search API
exa = Exa(api_key=os.getenv("EXA_API_KEY"))

# Define your API Model and key
client = Groq(api_key=os.getenv("GROQ_API_KEY"))
utilized_model = "llama3-70b-8192"

highlights_options = {
    "num_sentences": 7,  # Length of highlights
    "highlights_per_url": 1,  # Get the best highlight for each URL
}

def call_llm(prompt):
    search_response = exa.search_and_contents(query=prompt, highlights=highlights_options, num_results=3, use_autoprompt=True)
    info = [sr.highlights[0] for sr in search_response.results]
    
    system_prompt = "You are an academic PhD proposal generator. Read the provided contexts and, if relevant, use them to generate a well-structured research proposal."
    user_prompt = f"Sources: {info}\nResearch Prompt: {prompt}"
    
    completion = client.chat.completions.create(
        model=utilized_model,
        messages=[
            {"role": "system", "content": system_prompt},
            {"role": "user", "content": user_prompt},
        ]
    )
    return completion.choices[0].message.content


import requests
from IPython.display import HTML

# Function to upload files to transfer.sh
def upload_files_to_transfer_sh(file_paths):
    urls = []
    html_content = "<form>"
    
    # Iterate over each file and upload to transfer.sh
    for file_path in file_paths:
        with open(file_path, 'rb') as file:
            response = requests.post('https://transfer.sh/', files={'file': file})
            response.raise_for_status()  # Check for any upload errors
            urls.append(response.text)
            html_content += f"<p>File: {file_path} <br> Upload URL: <a href='{response.text}'>{response.text}</a></p>"
    
    html_content += "</form>"
    return urls, html_content
    
def generate_executive_summary(data):
    prompt = f"""
    Generate a concise executive summary for a PhD research proposal based on the following information:
    
    Research Topic: {data["research_topic"]}
    Research Question: {data["research_question"]}
    Objectives: {data["objectives"]}
    Methodology: {data["methodology"]}
    Contribution to the Field: {data["contribution"]}
    Literature Gap: {data["literature_gap"]}
    
    The summary should highlight the research problem, its significance, the approach, and expected contributions.
    """
    return call_llm(prompt)

def generate_literature_review_outline(data):
    prompt = f"""
    Generate a structured outline for the literature review of a PhD thesis on the following topic:
    
    Research Topic: {data["research_topic"]}
    Key Authors: {data["key_authors"]}
    Recent Developments: {data["recent_developments"]}
    Gaps in Literature: {data["literature_gap"]}
    
    The outline should cover key themes, debates, and the relevance of existing work to the proposed research.
    """
    return call_llm(prompt)

def generate_methodology_section(data):
    prompt = f"""
    Write a detailed research methodology section for a PhD proposal based on the following:
    
    Research Topic: {data["research_topic"]}
    Data Collection Methods: {data["data_collection"]}
    Data Analysis Methods: {data["data_analysis"]}
    Justification: {data["justification"]}
    
    The methodology should demonstrate how the research will be conducted reliably and validly.
    """
    return call_llm(prompt)

def generate_research_objectives(data):
    prompt = f"""
    Generate a detailed list of short-term and long-term research objectives for the following PhD thesis topic:
    
    Research Topic: {data["research_topic"]}
    Objectives: {data["objectives"]}
    
    The objectives should follow the SMART criteria (Specific, Measurable, Achievable, Relevant, and Time-bound).
    """
    return call_llm(prompt)

def generate_hypotheses(data):
    prompt = f"""
    Generate research hypotheses based on the following topic:
    
    Research Topic: {data["research_topic"]}
    Research Question: {data["research_question"]}
    
    The hypotheses should clearly predict expected outcomes based on theoretical foundations.
    """
    return call_llm(prompt)

def generate_contribution_statement(data):
    prompt = f"""
    Generate a statement of contribution for the following PhD research proposal:
    
    Research Topic: {data["research_topic"]}
    Contribution to the Field: {data["contribution"]}
    
    The statement should highlight how the research will address existing gaps and advance knowledge in the field.
    """
    return call_llm(prompt)

def generate_research_timeline(data):
    prompt = f"""
    Generate a detailed research timeline for completing a PhD thesis on the following topic:
    
    Research Topic: {data["research_topic"]}
    Total Timeframe: {data["total_timeframe"]}
    
    The timeline should break down tasks into manageable phases (e.g., literature review, data collection, analysis) with deadlines.
    """
    return call_llm(prompt)

def generate_proposal_introduction(data):
    prompt = f"""
    Write an engaging introduction for a PhD proposal on the following research topic:
    
    Research Topic: {data["research_topic"]}
    Research Problem: {data["research_problem"]}
    
    The introduction should provide background, introduce the problem, and explain the significance of the research.
    """
    return call_llm(prompt)

def generate_limitations_section(data):
    prompt = f"""
    Generate a section describing the potential limitations and challenges of the following research:
    
    Research Topic: {data["research_topic"]}
    Methodology: {data["methodology"]}
    
    The limitations should address possible obstacles and suggest ways to mitigate them.
    """
    return call_llm(prompt)

def generate_future_work_section(data):
    prompt = f"""
    Generate a section on future work based on the following research:
    
    Research Topic: {data["research_topic"]}
    Contribution: {data["contribution"]}
    
    The future work section should suggest further areas for research that could build upon the findings.
    """
    return call_llm(prompt)