Deprecated: hierarchical reading

Superseded by gr_read() with reader = "hierarchical". The new reader recurses until the summaries fit the context window; v1 summarised exactly once and overflowed past roughly 32 chunks.

Usage

gpt_read_hierarchical(
  chunks,
  question,
  client = NULL,
  return_json = FALSE,
  ...
)

Arguments

chunks

Character vector of chunks, or a gr_chunks.

question

The question.

client

A gr_client.

return_json

Return the whole answer object, including its trace, as JSON.

...

Passed to gr_read_spec().

Value

A single string when return_json is FALSE; otherwise a json-classed string holding the answer, its notes and the full trace.

See also

gr_read() and reader = "hierarchical", gr_read_spec() for fan_in and max_levels, gr_readers()

Other v1 compatibility: answer_question(), gpt_read_chunked(), gpt_read_multipass(), gpt_read_retrieval(), parse_text()

Examples

cl <- gr_mock_client(function(m, p) "45.2 million dollars")
chunks <- suppressWarnings(parse_text(readgpt_example(), chunk_token_limit = 200))
#> Using cached ingestion for this document + settings.
#> Segmenting with 'paragraph' (cap 200 tokens, overlap 0).
suppressWarnings(gpt_read_hierarchical(chunks, "What was revenue?", client = cl))
#> Using cached ingestion for this document + settings.
#> Reading with 'hierarchical' (all|N+tree+1|tree) over 4 chunk(s).
#> [1] "45.2 million dollars"

# The modern equivalent.
ch <- gr_segment(readgpt_example(), list(method = "paragraph", max_tokens = 200))
#> Using cached ingestion for this document + settings.
#> Segmenting with 'paragraph' (cap 200 tokens, overlap 0).
gr_read(ch, "What was revenue?", gr_mock_client(function(m, p) "45.2 million dollars"),
        "hierarchical")$reader
#> Reading with 'hierarchical' (all|N+tree+1|tree) over 4 chunk(s).
#> [1] "hierarchical"