7db4e4254d
Format Python code with psf/black push
2 years ago
b4b7646fb2
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
2 years ago
feff0df5bd
account for different token types
2 years ago
fed556a076
Format Python code with psf/black push
2 years ago
bea1ff903d
more token usage captures for indexes
2 years ago
946d95e3ff
default back to 1 search node
2 years ago
6a60d386c9
forgot embeddings in one place
2 years ago
d1ab9aa374
I'm stupid
2 years ago
8584fad048
merge
2 years ago
d9454283d1
fix typo
2 years ago
f02bf87e6e
Format Python code with psf/black push
2 years ago
b4b654828c
Full usage metrics reporting, nodes param for search, default 2 for search
2 years ago
0c862901f0
Format Python code with psf/black push
2 years ago
434cbdfc6d
bump version, bugfixes
2 years ago
8e94277f2b
bugfixes
2 years ago
55fddbc37b
Format Python code with psf/black push
2 years ago
d780235d8d
Merge pull request #142 from Hikari-Haru/index-fixes
...
Various gpt-index fixes
2 years 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.
2 years ago
f556c94b6a
Format Python code with psf/black push
2 years ago
05fdf2d784
a bit of error catching for search
2 years ago
91a5a98370
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
2 years ago
3eaee2f041
some early search adjustments
2 years ago
4f97ea1e4e
Format Python code with psf/black push
2 years ago
827216f272
enable /search alpha
2 years 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
2 years ago
73390b262c
Format Python code with psf/black push
2 years ago
cd8d0624a9
Merge branch 'main' into gpt-index
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
2 years ago
319ae34318
composability improvements
2 years ago
fd2ab04d93
More composability
2 years ago
258a87945c
composability
2 years ago
c93bcfa59a
update readme
2 years ago
464f332915
csv, powerpoint, image, mp3 support
2 years ago
3ed55b556f
Support youtube videos
2 years ago
b60bcfd68d
reset indexes command
2 years ago
22ba80c469
Multi-index support
2 years ago
c7271ab525
Format Python code with psf/black push
2 years ago
5f62b1fa2e
Merge branch 'main' into set-conversation-model
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
2 years ago
33e68588ee
Merge branch 'main' into gpt-index
2 years ago
5d5ec3dbb1
Format Python code with psf/black push
2 years ago
c7e6a447d3
Role checks
2 years ago
e63c6227dd
initial link loading
2 years ago
5d406b666b
remove .cleanup() for temp_path (it gets auto cleaned up its ok
2 years ago
842c7241a3
Removed some imports
2 years ago
c6a6245e00
Added server index backup and loading
2 years ago
dd9cb0ce4c
Add option for response mode on queries
2 years 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
2 years ago
f48deab320
Forgot to remove extra models
2 years ago
669e3f0191
Changed how max tokens are fetched
...
lowered from 4024 to 2024 if max tokens can't be gotten
2 years ago
71125ce65d
Add ephemeral option to ask and edit
2 years ago
95dd054f1c
Remove finetune stuff
2 years ago
github-actions
Kaveen Kumarasinghe
Hikari Haru
Kaveen Kumarasinghe