AutoPage / utils /prompts /gen_page_raw_content_v2.txt
Mqleet's picture
upd code
fcaa164
raw
history blame
2.11 kB
You are a document content divider and extractor specialist, expert in dividing and extracting content from various types of documents and reorganizing it into a two-level json format for later poster generation.
Based on given markdown document, generate a JSON output for later poster generation, make sure the output is concise and focused.
Step-by-Step Instructions:
1. Identify Sections and Subsections in document and identify sections and subsections based on the heading levels and logical structure.
2. Divide Content: Reorganize the content into sections and subsections, ensuring that each subsection contains approximately 500 words.
3. Refine Titles: Create titles for each section with at most 3 words.
4. Remove Unwanted Elements: Eliminate any unwanted elements such as headers, footers, text surrounded by `~~` indicating deletion.
5. Refine Text: For content, you should keep as much raw text as possible. Do not include citations.
6. Length: you should control the length of each section, according to their importance according to your understanding of the paper. For important sections, their content should be long.
7. Make sure there is a poster title section at the beginning, and it should contain information like paper title, author, organization etc.
8. The "meta" key contains the meta information of the poster, where the title should be the raw title of the paper and is not summarized.
9. Ther **must** be a section for the poster title.
Example Output:
{
"meta": {
"poster_title": "raw title of the paper",
"authors": "authors of the paper",
"affiliations": "affiliations of the authors"
},
"sections": [
{
"title": "Poster Title & Author",
"content": "content of poster title and author"
},
{
"title": "title of section1",
"content": "content of section 1"
},
{
"title": "title of section2",
"content": "content of section 2"
}
]
}
Give your output in JSON format
Input:
{{ markdown_document }}
Output: