Enhance literature search and research lookup documentation

- Added criteria for identifying high-quality literature, emphasizing the importance of Tier-1 journals and citation counts.
- Updated guidelines for citation finding to prioritize influential papers and reputable authors.
- Revised abstract writing instructions to reflect the preference for flowing paragraphs over structured formats.
- Included best practices for generating AI schematics, specifically regarding figure numbering and content clarity.
This commit is contained in:
Vinayak Agarwal
2026-02-03 14:31:19 -08:00
parent 49024095e3
commit 21801d71b2
8 changed files with 897 additions and 117 deletions

View File

@@ -101,7 +101,7 @@ from openai import OpenAI
client = OpenAI()
md = MarkItDown(
llm_client=client,
llm_model="anthropic/claude-opus-4.5",
llm_model="anthropic/claude-sonnet-4.5",
llm_prompt="Describe this scientific slide, focusing on data and key findings"
)
@@ -143,7 +143,7 @@ Be technical and precise.
md = MarkItDown(
llm_client=client,
llm_model="anthropic/claude-opus-4.5", # recommended for scientific vision
llm_model="anthropic/claude-sonnet-4.5", # recommended for scientific vision
llm_prompt=scientific_prompt
)
@@ -167,14 +167,14 @@ client = OpenAI(
# Scientific papers - use Claude for technical analysis
scientific_md = MarkItDown(
llm_client=client,
llm_model="anthropic/claude-opus-4.5",
llm_model="anthropic/claude-sonnet-4.5",
llm_prompt="Describe scientific figures with technical precision"
)
# Presentations - use GPT-4o for visual understanding
presentation_md = MarkItDown(
llm_client=client,
llm_model="anthropic/claude-opus-4.5",
llm_model="anthropic/claude-sonnet-4.5",
llm_prompt="Summarize slide content and key visual elements"
)