History log of /plugin/aichat/ (Results 176 – 200 of 247)
Revision Date Author Comments
(<<< Hide modified files)
(Show modified files >>>)
962f9fb008-Nov-2023 splitbrain <splitbrain@users.noreply.github.com>

�� Automatic code style fixes

441edf8408-Nov-2023 Andreas Gohr <andi@splitbrain.org>

fixed overlong lines

30b9cbc708-Nov-2023 splitbrain <splitbrain@users.noreply.github.com>

�� Automatic code style fixes

5e6dd16e08-Nov-2023 Andreas Gohr <andi@splitbrain.org>

Added ChromaDB vector storage support

dc355d5706-Nov-2023 Andreas Gohr <andi@splitbrain.org>

added chunk dumping to CLI page command

527fda2610-Oct-2023 Andreas Gohr <andi@splitbrain.org>

Version upped

28b91a9410-Oct-2023 Andreas Gohr <andi@splitbrain.org>

added minphp to plugin info

2164293213-Sep-2023 Andreas Gohr <andi@splitbrain.org>

Version upped

f8d5ae0113-Sep-2023 Andreas Gohr <andi@splitbrain.org>

codesniffer cleanups

7ebc789513-Sep-2023 splitbrain <splitbrain@users.noreply.github.com>

�� Automatic code style fixes

b377ce3013-Sep-2023 Andreas Gohr <andi@splitbrain.org>

add default test workflows

ae1e222d31-Aug-2023 Andreas Gohr <andi@splitbrain.org>

Version upped

adfc542929-Aug-2023 Andreas Gohr <andi@splitbrain.org>

generate clusters only if more than 3 clusters would be created

e33a1d7a28-Aug-2023 Andreas Gohr <andi@splitbrain.org>

optionally search one language only

754b839424-Aug-2023 Andreas Gohr <andi@splitbrain.org>

keep last question/answer as additional context

This should help with questions relating to the last anwser when they
haven't been rephrased well enough

8bb3d0cd16-Aug-2023 Andreas Gohr <andi@splitbrain.org>

Version upped

219268b116-Aug-2023 Andreas Gohr <andi@splitbrain.org>

option to prefer a configured language instead of guessing

8c8b7ba616-Aug-2023 Andreas Gohr <andi@splitbrain.org>

Added dumping of TSV files to SQLite store

This allows visualizing the embed vectors

2ad4d15816-Aug-2023 Andreas Gohr <andi@splitbrain.org>

finish similar pages feature

376b909c15-Aug-2023 Andreas Gohr <andi@splitbrain.org>

Version upped

3379af0915-Aug-2023 Andreas Gohr <andi@splitbrain.org>

use a k-means based cluster approach to speed up similarity searches

35555bac15-Aug-2023 Andreas Gohr <andi@splitbrain.org>

simplify cosine distance calculation

Since all OpenAI vectors are normalized, only the dotproduct needs to be
calculated for the distance. This saves a couple of floating point ops
per chunk, but do

simplify cosine distance calculation

Since all OpenAI vectors are normalized, only the dotproduct needs to be
calculated for the distance. This saves a couple of floating point ops
per chunk, but doesn't make a huge difference overall.

show more ...

e33f142314-Aug-2023 Andreas Gohr <andi@splitbrain.org>

Version upped

aee9b38314-Aug-2023 Andreas Gohr <andi@splitbrain.org>

output info on similar chunk fetching

helps with figuring out how fast the store is

01f0693210-Aug-2023 Andreas Gohr <andi@splitbrain.org>

First go at syntax to display similar pages

12345678910