langchain/docs/use_cases/summarization.md
Harrison Chase 956416c150
Harrison/update links1 (#594)
update links to be relative

Co-authored-by: Marc Green <marcgreen@users.noreply.github.com>
2023-01-12 06:29:42 -08:00

1.1 KiB

Summarization

Summarization involves creating a smaller summary of multiple longer documents. This can be useful for distilling long documents into the core pieces of information.

The recommended way to get started using a summarization chain is:

from langchain.chains.summarize import load_summarize_chain
chain = load_summarize_chain(llm, chain_type="map_reduce")
chain.run(docs)

The following resources exist:

Additional related resources include:

  • Utilities for working with Documents: Guides on how to use several of the utilities which will prove helpful for this task, including Text Splitters (for splitting up long documents).
  • CombineDocuments Chains: A conceptual overview of specific types of chains by which you can accomplish this task.
  • Data Augmented Generation: An overview of data augmented generation, which is the general concept of combining external data with LLMs (of which this is a subset).