b4b654828c
Full usage metrics reporting, nodes param for search, default 2 for search
1 year ago
55fddbc37b
Format Python code with psf/black push
1 year ago
3952842856
Add setting top_k amount to the query command
...
Count LLM tokens for deep compose
Update presentation of cost in the console
Update readme
Set a prompthelper at 500 tokens output up from the default 256 I believe. ~4 characters per token so the discord limit is around 500 tokens.
1 year ago
5a1bd48d94
Fix regression in full discord server indexing
...
Add back response mode, only on vector index queries
Added the llmpredictor to queries
Fix docker build
Update requirements
1 year ago
73390b262c
Format Python code with psf/black push
1 year ago
319ae34318
composability improvements
1 year ago
fd2ab04d93
More composability
1 year ago
258a87945c
composability
1 year ago
c93bcfa59a
update readme
1 year ago
464f332915
csv, powerpoint, image, mp3 support
1 year ago
3ed55b556f
Support youtube videos
1 year ago
b60bcfd68d
reset indexes command
1 year ago
22ba80c469
Multi-index support
1 year ago
c7e6a447d3
Role checks
1 year ago
e63c6227dd
initial link loading
1 year ago
5d406b666b
remove .cleanup() for temp_path (it gets auto cleaned up its ok
1 year ago
842c7241a3
Removed some imports
1 year ago
c6a6245e00
Added server index backup and loading
1 year ago
dd9cb0ce4c
Add option for response mode on queries
1 year ago
37a20a7e37
Added discord channel and whole server indexing
...
A channel index does 1000 messages
Whole server index does 300 messages per channel
Might need to add more restrictions since all the index commands are expensive
1 year ago
64ce627bb7
Update filetypes
1 year ago
0555cf8b33
Some async changes
1 year ago
9052bc2d80
Added gpt-index commands
1 year ago
Kaveen Kumarasinghe
github-actions
Rene Teigen