new_research_paper.py

# import streamlit as st
# import pandas as pd
# import requests
# import json
# import os
# from dotenv import load_dotenv

# # Load environment variables
# load_dotenv()
# PERPLEXITY_API_KEY = os.getenv("PERPLEXITY_API_KEY")
# PERPLEXITY_API_URL = "https://api.perplexity.ai/chat/completions"


# def call_perplexity_api(prompt: str) -> str:
#     """Call Perplexity AI with a prompt, return the text response if successful."""
#     headers = {
#         "Authorization": f"Bearer {PERPLEXITY_API_KEY}",
#         "Content-Type": "application/json",
#     }

#     payload = {
#         "model": "llama-3.1-sonar-small-128k-chat",
#         "messages": [{"role": "user", "content": prompt}],
#         "temperature": 0.3,
#     }

#     try:
#         response = requests.post(PERPLEXITY_API_URL, headers=headers, json=payload)
#         response.raise_for_status()
#         return response.json()["choices"][0]["message"]["content"]
#     except Exception as e:
#         st.error(f"API Error: {str(e)}")
#         return ""


# def generate_research_paper(df: pd.DataFrame) -> dict:
#     """
#     For each column in the DataFrame, generate a research paper section (200-500 words)
#     that addresses the data in that column. Return a dict mapping column -> text.
#     """
#     paper_sections = {}
#     for col in df.columns:
#         # Convert all non-null rows in the column to strings and join them for context
#         col_values = df[col].dropna().astype(str).tolist()
#         # We'll truncate if this is huge
#         sample_text = " | ".join(col_values[:50])  # limit to first 50 rows for brevity
#         prompt = f"""
#         Topic: {col}
#         Data Sample: {sample_text}

#         Generate a professional research paper section for the above column.
#         The section should be at least 100 words and at most 150 words,
#         focusing on key insights, challenges, and potential research angles.
#         Integrate the data samples as context for the content.
#         """
#         section_text = call_perplexity_api(prompt)
#         paper_sections[col] = section_text.strip() if section_text else ""
#     return paper_sections


# def format_paper(paper_dict: dict) -> str:
#     """
#     Format the generated paper into a Markdown string.
#     Each column name is used as a heading, and the text is placed under it.
#     """
#     md_text = "# Generated Research Paper\n\n"
#     for col, content in paper_dict.items():
#         md_text += f"## {col}\n{content}\n\n"
#     return md_text


# def main():
#     st.title("Corpus-based Research Paper Generator")

#     uploaded_file = st.file_uploader("Upload CSV corpus file", type="csv")
#     if uploaded_file:
#         df = pd.read_csv(uploaded_file)
#         st.write("### Preview of Uploaded Data")
#         st.dataframe(df.head())

#         if st.button("Generate Research Paper"):
#             st.info("Generating paper based on the columns of your corpus...")
#             with st.spinner("Calling Perplexity AI..."):
#                 paper = generate_research_paper(df)
#                 if paper:
#                     formatted_paper = format_paper(paper)
#                     st.success("Research Paper Generated Successfully!")
#                     st.write(formatted_paper)

#                     st.download_button(
#                         label="Download Paper as Markdown",
#                         data=formatted_paper,
#                         file_name="research_paper.md",
#                         mime="text/markdown",
#                     )
#                 else:
#                     st.error(
#                         "Paper generation failed. Please check Perplexity API key."
#                     )


# if __name__ == "__main__":
#     main()
import streamlit as st
import pandas as pd
import requests
import json
import os
from dotenv import load_dotenv

# Load environment variables
load_dotenv()
PERPLEXITY_API_KEY = os.getenv("PERPLEXITY_API_KEY")
PERPLEXITY_API_URL = "https://api.perplexity.ai/chat/completions"


def call_perplexity_api(prompt: str) -> str:
    """Call Perplexity AI with a prompt, return the text response if successful."""
    headers = {
        "Authorization": f"Bearer {PERPLEXITY_API_KEY}",
        "Content-Type": "application/json",
    }

    payload = {
        "model": "llama-3.1-sonar-small-128k-chat",
        "messages": [{"role": "user", "content": prompt}],
        "temperature": 0.3,
    }

    try:
        response = requests.post(PERPLEXITY_API_URL, headers=headers, json=payload)
        response.raise_for_status()
        return response.json()["choices"][0]["message"]["content"]
    except Exception as e:
        st.error(f"API Error: {str(e)}")
        return ""


# def generate_research_paper(df: pd.DataFrame) -> dict:
#     """
#     For each column in the DataFrame, generate a research paper section (200-500 words)
#     that addresses the data in that column. Return a dict mapping column -> text.
#     """
#     paper_sections = {}
#     for col in df.columns:
#         # Convert all non-null rows in the column to strings and join them for context
#         col_values = df[col].dropna().astype(str).tolist()
#         # We'll truncate if this is huge
#         sample_text = " | ".join(col_values[:50])  # limit to first 50 rows for brevity
#         prompt = f"""
#         Topic: {col}
#         Data Sample: {sample_text}

#         Generate a professional research paper section for the above column.
#         The section should be at least 100 words and at most 150 words,
#         focusing on key insights, challenges, and potential research angles.
#         Integrate the data samples as context for the content.
#         """
#         section_text = call_perplexity_api(prompt)
#         paper_sections[col] = section_text.strip() if section_text else ""
#     return paper_sections


# def format_paper(paper_dict: dict) -> str:
#     """
#     Format the generated paper into a Markdown string.
#     Each column name is used as a heading, and the text is placed under it.
#     """
#     md_text = "# Generated Research Paper\n\n"
#     for col, content in paper_dict.items():
#         md_text += f"## {col}\n{content}\n\n"
#     return md_text


# def main():
#     st.title("Corpus-based Research Paper Generator")

#     uploaded_file = st.file_uploader("Upload CSV corpus file", type="csv")
#     if uploaded_file:
#         df = pd.read_csv(uploaded_file)
#         st.write("### Preview of Uploaded Data")
#         st.dataframe(df.head())

#         if st.button("Generate Research Paper"):
#             st.info("Generating paper based on the columns of your corpus...")
#             with st.spinner("Calling Perplexity AI..."):
#                 paper = generate_research_paper(df)
#                 if paper:
#                     formatted_paper = format_paper(paper)
#                     st.success("Research Paper Generated Successfully!")
#                     st.write(formatted_paper)

#                     st.download_button(
#                         label="Download Paper as Markdown",
#                         data=formatted_paper,
#                         file_name="research_paper.md",
#                         mime="text/markdown",
#                     )
#                 else:
#                     st.error(
#                         "Paper generation failed. Please check Perplexity API key."
#                     )


# if __name__ == "__main__":
#     main()
#def generate_research_paper(df: pd.DataFrame, gaps_analysis: str, topic: str, journal: str, format: str) -> dict:
    """
    For each column in the DataFrame, generate a research paper section (200-500 words)
    that addresses the data in that column. Return a dict mapping column -> text.
    """
    paper_sections = {}
    for col in df.columns:
        # Convert all non-null rows in the column to strings and join them for context
        col_values = df[col].dropna().astype(str).tolist()
        # We'll truncate if this is huge
        print(col)
        sample_text = " | ".join(col_values[:50])  # limit to first 50 rows for brevity
        prompt = f"""
        Topic: {topic}
        Journal/Conference: {journal}
        Format: {format}
        Gaps Analysis: {gaps_analysis}
        Column: {col}
        Data Sample: {sample_text}

        Generate a professional research paper section for the above column.
        The section should be at least 100 words and at most 150 words,
        focusing on key insights, challenges, and potential research angles.
        Integrate the data samples as context for the content.
        """
        section_text = call_perplexity_api(prompt)
        paper_sections[col] = section_text.strip() if section_text else ""
    return paper_sections


#def format_paper(paper_dict: dict, topic: str, journal: str, format: str) -> str:
    """
    Format the generated paper into a Markdown string.
    Add the topic, journal, and format as the main title, each column name as a heading,
    and the corresponding text as paragraph content.
    """
    md_text = f"# Research Paper on: {topic}\n\n"
    md_text += f"## Journal/Conference: {journal}\n\n"
    md_text += f"## Format: {format}\n\n"
    for col, content in paper_dict.items():
        md_text += f"### {col}\n{content}\n\n"
    return md_text


#def main():
    st.title("Corpus-based Research Paper Generator")

    topic_input = st.text_input("Enter the topic for the research paper:")
    journal_input = st.text_input("Enter the Journal/Conference aimed to publish:")
    format_input = st.text_input("Enter the format of the research paper:")
    gaps_analysis_file = st.file_uploader("Upload Gaps Analysis (.txt file)", type="txt")
    gaps_analysis = ""
    if gaps_analysis_file:
        gaps_analysis = gaps_analysis_file.getvalue().decode("utf-8")

    uploaded_file = st.file_uploader("Upload CSV corpus file", type="csv")
    if uploaded_file:
        df = pd.read_csv(uploaded_file)
        st.write("### Preview of Uploaded Data")
        st.dataframe(df.head())

        if st.button("Generate Research Paper"):
            st.info("Generating paper based on the columns of your corpus...")
            with st.spinner("Calling Perplexity AI..."):
                paper = generate_research_paper(df, gaps_analysis, topic_input, journal_input, format_input)
                if paper:
                    formatted_paper = format_paper(paper, topic_input, journal_input, format_input)
                    st.success("Research Paper Generated Successfully!")
                    st.write(formatted_paper)

                    st.download_button(
                        label="Download Paper as Markdown",
                        data=formatted_paper,
                        file_name="research_paper.md",
                        mime="text/markdown",
                    )
                else:
                    st.error(
                        "Paper generation failed. Please check Perplexity API key."
                    )

def generate_research_paper(df: pd.DataFrame, gaps_analysis: str, topic: str, journal: str, format: str) -> str:
    """
    Generate a research paper based on the entire DataFrame, the topic, journal, and format.
    """
    # Convert the entire DataFrame to a string
    df_string = df.to_string(index=False)

    # Create the prompt
    prompt = f"""
    Topic: {topic}
    Journal/Conference: {journal}
    Format: {format}
    Gaps Analysis: {gaps_analysis}
    Data:
    {df_string}

    Generate a professional research paper based on the above data.
    The paper should be well-structured, focusing on key insights, challenges, and potential research angles.
    Use the Gaps Analysis to identify areas for improvement and future work and fill the gaps in the new paper.
    Use the data as a reference to support your arguments, dont directly copy the data.
    Ensure the paper is formatted according to the specified journal/conference format.
    """

    # Call the Perplexity API
    paper_text = call_perplexity_api(prompt)
    return paper_text.strip() if paper_text else ""

def format_paper(paper_text: str, topic: str, journal: str, format: str) -> str:
    """
    Format the generated paper into a Markdown string.
    Add the topic, journal, and format as the main title, and the paper text as content.
    """
    md_text = f"# Research Paper on: {topic}\n\n"
    md_text += paper_text
    return md_text

def main():
    st.title("Corpus-based Research Paper Generator")

    topic_input = st.text_input("Enter the topic for the research paper:")
    journal_input = st.text_input("Enter the Journal/Conference aimed to publish:")
    format_input = st.text_input("Enter the format of the research paper:")
    gaps_analysis_file = st.file_uploader("Upload Gaps Analysis (.txt file)", type="txt")
    gaps_analysis = ""
    if gaps_analysis_file:
        gaps_analysis = gaps_analysis_file.getvalue().decode("utf-8")

    uploaded_file = st.file_uploader("Upload CSV corpus file", type="csv")
    if uploaded_file:
        df = pd.read_csv(uploaded_file)
        st.write("### Preview of Uploaded Data")
        st.dataframe(df.head())

        if st.button("Generate Research Paper"):
            st.info("Generating paper based on the columns of your corpus...")
            with st.spinner("Calling Perplexity AI..."):
                paper_text = generate_research_paper(df, gaps_analysis, topic_input, journal_input, format_input)
                if paper_text:
                    formatted_paper = format_paper(paper_text, topic_input, journal_input, format_input)
                    st.success("Research Paper Generated Successfully!")
                    st.write(formatted_paper)

                    st.download_button(
                        label="Download Paper as Markdown",
                        data=formatted_paper,
                        file_name="research_paper.md",
                        mime="text/markdown",
                    )
                else:
                    st.error(
                        "Paper generation failed. Please check Perplexity API key."
                    )

if __name__ == "__main__":
    main()