Hunt Institute for Botanical Documentation
A Research Division of Carnegie Mellon University

Hunt Institute Archives Text Discovery Platform

Search a large and growing portion of our online collections, including handwritten documents.
PROTOTYPE

This prototype uses state-of-the-art artificial intelligence, including a vision-language model (VLM) capable of reading handwritten documents as well as typed and printed text, to create searchable transcriptions of digitized materials in the Hunt Institute Archives. This makes it possible to search the textual contents of individual pages, including material that may not be described in the archival catalog.

Use Keyword search for specific words, names, dates, scientific names, or phrases. Try Semantic search (experimental) to describe a topic, question, or kind of material when you do not know the exact wording used in the documents.

About the AI-generated transcriptions

The transcriptions are generated automatically from page images and may contain errors, especially with difficult handwriting, unusual names, multiple languages, image-quality problems, or complex layouts. They are intended primarily as a discovery aid rather than authoritative transcriptions.

Each result provides the generated transcription and links to the original digitized material and associated archival description so that readings can be checked against the source. The transcription workflow uses AI models run locally by the Hunt Institute.

About Keyword and Semantic search

Keyword search is the default and matches the wording in the transcriptions. Results contain all your terms. Use quotes for an exact phrase. Substring matching is supported, so aceae can find plant-family names ending in -aceae.

Semantic search (experimental) is useful when you know what kind of material you are looking for but do not know the words used in the documents. It ranks transcribed passages by similarity of meaning, so relevant results may not contain the exact words in your query.

Semantic queries can be broad research topics, descriptions of activities or relationships, or natural-language questions. For example:

Semantic search is not a chatbot: a question is used as a search query, and the system returns archival passages that appear conceptually related to it rather than generating an answer or summary. Short descriptions and ordinary research questions generally work better than lists of disconnected keywords. Quotation marks have no special meaning in Semantic mode. Cross-language matching may work in some cases, but it should not be treated as translation.

Keyword and Semantic search are complementary. Keyword search lets you require particular wording; Semantic search can surface differently worded passages about the same subject. Depending on the research question, trying both can reveal different useful material.

Open a result: use the prominent page-and-transcription link to see the metadata, PDF, and full transcription. Keyword-search terms are highlighted in the transcription.

Archives Collections Database (ArchivesSpace): the Collection, Item/Folder, and Digital Object links open the corresponding archival records. Collection-level dates describe the collection as a whole, not necessarily the specific item or page.

If a PDF does not load: on the detail page, use the Digital Object link, click “Go to file” in ArchivesSpace, and navigate to the page number shown here.

Current limitations
  • Automated transcriptions can contain missing or incorrect text or unintended repetition. Difficult handwriting, image quality, unusual layouts, and multiple languages can reduce accuracy. Always consult the original page image when an exact reading matters.
  • Semantic search remains experimental. Its rankings are an additional discovery aid, not a complete or definitive set of relevant results, and highly ranked pages can sometimes be only broadly related.
  • This is an active prototype. Search coverage, transcriptions, functionality, and the interface may continue to change as additional archival material is processed and the system is improved.

← Back to results

Page 20 · DO #4199 · 182_Goodspeed_Bx2FF37_r

Collection
Thomas Harper Goodspeed (1887–1966) papers
Item/Folder
Rockefeller–Rudolph, 1938–1956
Digital Object
DO #4199, page 20
Collection-level dates
1923–1963
Open PDF at page 20 ↗

Page transcription

July 11, 1947

Mr. Harry M. Miller, Jr.
The Rockefeller Foundation
49 West 49th Street
New York 20, New York

Dear Dr. Miller:

Many thanks for your letter of July 1st. I enjoyed your visit a great deal. The opportunity to talk about mutual friends south of the border and to recall places and experiences made me a bit homesick for South America.

As I told you, my accumulation of detailed information concerning the character and distribution of the floras of the Andes, representing products of four botanical expeditions to South America, is one of the most extensive in existence. It consists of over 25,000 different collections of named herbarium specimens, over 3,000 photographs, extensive field notes and distributional maps. Supplementing these field studies are extensive ones made in this Botanical Garden where over 1,000 species of South American plants have been grown from seed, bulbs, etc., Scientific institutions in this country and abroad and private individuals provided $70,000 to make the South American work possible.

To have permanent value the accumulation referred to above must be further organized and analyzed and the results which bear significantly upon problems of plant evolution and distribution on a continental scale must be properly published. Presumably if I do not do the job it will never be done and certainly I should be able to do it better than anyone else.

I have in preparation a volume on the largely South American genus Nicotiana and propose to expand very considerably an article on the plant geography of Chile which is practically ready for publication and to follow it with an account of the vegetation of the Bolivian-Peruvian-Argentine frontiers. Another book which is in first draft deals with the plant resources of Argentina, and I have agreed to write certain sections of the Genera et Species Plantarum Argentinorum and, in addition, an account of the plant geography of Patagonia for the Anales of the Museum in Bariloche. Of special importance will be a volume fully annotated and illustrated on the routes of the four expeditions, the collections made and the environmental factors characteristic of the extensive series of vegetational zones and areas explored -- in effect a botanical reconnaissance of the west coast of South America, the Andes, Bolivia, Argentina and Uruguay. When the current expeditions in the oriente of Colombia and Peru are over and the products assembled a treat-