From ba9efcd1e6ecdc17d821e21b1ec59e14145fc912 Mon Sep 17 00:00:00 2001 From: Vasudev Pal <120969150+vasudev-pal@users.noreply.github.com> Date: Fri, 19 May 2023 23:49:08 +0530 Subject: [PATCH 1/2] build: update README.md --- README.md | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/README.md b/README.md index 8ce3d0b..8fb58d6 100644 --- a/README.md +++ b/README.md @@ -43,6 +43,14 @@ Please note this is experimental - it will be significantly slower and the quali 5. Output - the summary is displayed on the page and saved as a text file. ![summary](https://i.imgur.com/sUcay6a.gif) + +## Architecture +![Architecture](https://www.google.com/) +The Architecture elaborates the workflow of the model. +1. It takes input Text Document +2. Create Words Embeddings using FAISS[performs similarity search and words that are close in meaning are clustered near to one another in vector space] +3. Taking extracted ebeddings as input and constructing a prompt, and then sending that to the LLM. + Improved support for locally run LLM's is coming. Built using Langchain! This is project was made for fun, and is likely full of bugs. It is not fully optimized. Contributions or bug reports are welcomed! From feb17e1dfacf8fd164c224818ead1cf6e57817af Mon Sep 17 00:00:00 2001 From: Vasudev Pal <120969150+vasudev-pal@users.noreply.github.com> Date: Fri, 19 May 2023 23:59:31 +0530 Subject: [PATCH 2/2] fix: add architecture image --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 8fb58d6..17e7d0c 100644 --- a/README.md +++ b/README.md @@ -45,7 +45,8 @@ Please note this is experimental - it will be significantly slower and the quali ## Architecture -![Architecture](https://www.google.com/) +![Architecture](https://github.com/vasudev-pal/BriefGPT/assets/120969150/687863e4-5a4f-415e-92c8-3354b1fb3f8d) + The Architecture elaborates the workflow of the model. 1. It takes input Text Document 2. Create Words Embeddings using FAISS[performs similarity search and words that are close in meaning are clustered near to one another in vector space]