MCPcopy Create free account
hub / github.com/OpenRaiser/PaperFlow / process_paper

Function process_paper

skills/paper-processor/scripts/embed.py:208–228  ·  view source on GitHub ↗

Process a paper completely Args: paper: Paper dictionary Returns: Processed paper dictionary

(paper: Dict)

Source from the content-addressed store, hash-verified

206
207
208def process_paper(paper: Dict) -> Dict:
209 """
210 Process a paper completely
211
212 Args:
213 paper: Paper dictionary
214
215 Returns:
216 Processed paper dictionary
217 """
218 # Clean abstract
219 paper["cleaned_abstract"] = clean_abstract(paper.get("abstract", ""))
220
221 # Extract keywords
222 paper["keywords"] = extract_keywords(paper["cleaned_abstract"], top_k=5)
223
224 # Generate embedding
225 paper["embedding"] = generate_embedding(paper["cleaned_abstract"])
226 paper["embedding_model"] = "text-embedding-3-small"
227
228 return paper
229
230
231def deduplicate_papers(papers: List[Dict]) -> List[Dict]:

Callers

nothing calls this directly

Calls 4

clean_abstractFunction · 0.85
extract_keywordsFunction · 0.85
generate_embeddingFunction · 0.85
getMethod · 0.80

Tested by

no test coverage detected