From 6e2f55c86da6fd85e88264a4ab6b1d111d3eb427 Mon Sep 17 00:00:00 2001 From: vtempest <1274452+vtempest@users.noreply.github.com> Date: Wed, 28 Aug 2024 17:47:07 -0700 Subject: [PATCH] video --- readme.md | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/readme.md b/readme.md index 31c386f..cae887c 100644 --- a/readme.md +++ b/readme.md @@ -14,8 +14,9 @@ ## [Live Demo (qwksearch.com)](https://qwksearch.com/) - -* NPM Tests -- `npm run test` to run many tests custom to your data +* [SEEKTOPIC Sample Output](https://github.com/vtempest/ai-research-agent/blob/master/test/data/) +* NPM Tests -- `npm run test` to run many tests custom to your data + > Being is Becoming: Whatever the future of research can be, that is what it must become. @@ -50,11 +51,10 @@

- +

- [SEEKTOPIC Sample Output](https://github.com/vtempest/ai-research-agent/blob/master/test/data/) SEEKTOPIC can be used to find unique, domain-specific keyphrases using noun Ngrams. The user can click on keyphrases or LLM can suggest questions based on them. The user can see highlighted just the most important sentences that centralize and tie in the core topics. It is possible to vectorize and compare the dot product similarity of query to keyphrases which are then mapped to parts of the document like section labels. This is more in line with how humans think of article organization into section headings and lead sentences which tie in concepts from others.