Retriever¶
This module contains the Retriever class.
Classes¶
- class chemdatawriter.retriever.Retriever(papers)¶
Retriever class for processing and retrieving relevant sections.
- __init__(papers)¶
Initialize the Retriever.
- Parameters:
papers (list) – List of papers to process.
- _write_to_cache(cache_path)¶
Writes papers to cache for processing.
- Parameters:
cache_path (str) – Path to write papers.
- _load_docs_from_cache(cache_path)¶
Loads documents from cache and processes them for retrieval.
- Parameters:
cache_path (str) – Path to load papers.
- retrieve(query, cache_path, chapter_size)¶
Retrieve relevant sections based on the query.
- Parameters:
query (str) – Search query for retrieval.
cache_path (str) – Path to cache.
chapter_size (int) – Number of sections to retrieve.
- Returns:
List of indices of relevant sections.
- Return type:
list