Kaveen Kumarasinghe
ebf83ca8f9
slightly improve search refiner
2 years ago
github-actions
7759d1704e
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
e532e6d758
enable basic search refiner
2 years ago
Rene Teigen
e37f4024c8
Fix bug with searching pdfs and reduced max scope and nodes
2 years ago
github-actions
f8972ec3bb
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
2cf163248e
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
2 years ago
Kaveen Kumarasinghe
965ad37087
search pre-processor for query refining for google custom search
2 years ago
github-actions
42822e89e3
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
1f400208d7
minor fixes
2 years ago
Kaveen Kumarasinghe
01fb514a9b
Pagination for gpt responses, max tokens 4096
2 years ago
github-actions
6a87248a0a
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
a2a79afb18
search improvements
2 years ago
Kaveen Kumarasinghe
1d2a2c8eae
default search scope to 2, 5 as a default is way too expensive.
2 years ago
github-actions
7db4e4254d
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
b4b7646fb2
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
2 years ago
Kaveen Kumarasinghe
feff0df5bd
account for different token types
2 years ago
github-actions
fed556a076
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
bea1ff903d
more token usage captures for indexes
2 years ago
Kaveen Kumarasinghe
946d95e3ff
default back to 1 search node
2 years ago
Kaveen Kumarasinghe
6a60d386c9
forgot embeddings in one place
2 years ago
Kaveen Kumarasinghe
d1ab9aa374
I'm stupid
2 years ago
Kaveen Kumarasinghe
8584fad048
merge
2 years ago
Kaveen Kumarasinghe
d9454283d1
fix typo
2 years ago
github-actions
f02bf87e6e
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
b4b654828c
Full usage metrics reporting, nodes param for search, default 2 for search
2 years ago
github-actions
0c862901f0
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
434cbdfc6d
bump version, bugfixes
2 years ago
Kaveen Kumarasinghe
8e94277f2b
bugfixes
2 years ago
github-actions
55fddbc37b
Format Python code with psf/black push
2 years ago
Hikari Haru
d780235d8d
Merge pull request #142 from Hikari-Haru/index-fixes
...
Various gpt-index fixes
2 years ago
Rene Teigen
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
github-actions
f556c94b6a
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
05fdf2d784
a bit of error catching for search
2 years ago
Kaveen Kumarasinghe
91a5a98370
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
2 years ago
Kaveen Kumarasinghe
3eaee2f041
some early search adjustments
2 years ago
github-actions
4f97ea1e4e
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
827216f272
enable /search alpha
2 years ago
Rene Teigen
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
github-actions
73390b262c
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
cd8d0624a9
Merge branch 'main' into gpt-index
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
2 years ago
Kaveen Kumarasinghe
319ae34318
composability improvements
2 years ago
Kaveen Kumarasinghe
fd2ab04d93
More composability
2 years ago
Kaveen Kumarasinghe
258a87945c
composability
2 years ago
Kaveen Kumarasinghe
c93bcfa59a
update readme
2 years ago
Kaveen Kumarasinghe
464f332915
csv, powerpoint, image, mp3 support
2 years ago
Kaveen Kumarasinghe
3ed55b556f
Support youtube videos
2 years ago
Kaveen Kumarasinghe
b60bcfd68d
reset indexes command
2 years ago
Kaveen Kumarasinghe
22ba80c469
Multi-index support
2 years ago
github-actions
c7271ab525
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
5f62b1fa2e
Merge branch 'main' into set-conversation-model
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
2 years ago
Kaveen Kumarasinghe
33e68588ee
Merge branch 'main' into gpt-index
2 years ago
github-actions
5d5ec3dbb1
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
c7e6a447d3
Role checks
2 years ago
Kaveen Kumarasinghe
e63c6227dd
initial link loading
2 years ago
Kaveen Kumarasinghe
5d406b666b
remove .cleanup() for temp_path (it gets auto cleaned up its ok
2 years ago
Rene Teigen
842c7241a3
Removed some imports
2 years ago
Rene Teigen
c6a6245e00
Added server index backup and loading
2 years ago
Rene Teigen
dd9cb0ce4c
Add option for response mode on queries
2 years ago
Rene Teigen
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
Rene Teigen
f48deab320
Forgot to remove extra models
2 years ago
Rene Teigen
669e3f0191
Changed how max tokens are fetched
...
lowered from 4024 to 2024 if max tokens can't be gotten
2 years ago
Rene Teigen
71125ce65d
Add ephemeral option to ask and edit
2 years ago
Rene Teigen
95dd054f1c
Remove finetune stuff
2 years ago
Rene Teigen
02b2bb97d8
Change backoff handling to be more verbose
2 years ago
Rene Teigen
5de0fd37da
Conversation command now has a model option
...
Added model autocomplete
2 years ago
Rene Teigen
64ce627bb7
Update filetypes
2 years ago
Rene Teigen
0555cf8b33
Some async changes
2 years ago
Rene Teigen
9052bc2d80
Added gpt-index commands
2 years ago
github-actions
f8d797f3a8
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
f473342bff
move overrides into class
2 years ago
Kaveen Kumarasinghe
595feaf539
persistent settings
2 years ago
Kaveen Kumarasinghe
b4ddee81f7
welcome message off by default
2 years ago
Kaveen Kumarasinghe
32726ecba1
Merge pull request #119 from duckdoom4/main
...
Fix spelling mistakes
2 years ago
github-actions
774cf9423b
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
8d5dd77f2c
remove print
2 years ago
Kaveen Kumarasinghe
50e6f59ab5
change token limit when the text model changes
2 years ago
duckdoom4
8982df882e
Fix the default values set to temperature and top p
...
The documentation mentions it's recommended to not alter both
See https://beta.openai.com/docs/api-reference/completions/create#completions/create-temperature
2 years ago
duckdoom4
ac11d9f2a4
Remove hardcoded 'magic values'
2 years ago
duckdoom4
5de2e79b3b
Add missing models
2 years ago
duckdoom4
980f0f3dd4
Fix spelling mistakes
2 years ago
Kaveen Kumarasinghe
5841171106
slightly reduce pretext, improve minimal pretext, add support for >2 temperature
2 years ago
github-actions
7779e44a2c
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
11f563e16a
Add Paraphrase
2 years ago
github-actions
7e5d9266d5
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
4df4096f02
speed up moderations and smoothen translations
2 years ago
Rene Teigen
7260ab7b6b
Add stop in conversation, some formatting
...
Added ping on thread open
Removed extra newlines from ask formatting
2 years ago
github-actions
f0860d1f66
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
2ff7cb1a3b
add approve button to moderations, add reset
2 years ago
github-actions
4c08ab8820
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
7cb19039a1
custom bot name, beautify responses
2 years ago
Kaveen Kumarasinghe
50a9f7c469
custom bot name, beautify responses
2 years ago
Kaveen Kumarasinghe
02762fd61c
Add formality param to translations
2 years ago
Kaveen Kumarasinghe
8c1f492243
reorder language list
2 years ago
github-actions
d125668d25
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
3627d32e54
Translations with DeepL
2 years ago
github-actions
ea5f95800b
Format Python code with psf/black push
2 years ago
Kaveen Kumarasinghe
e947e030fb
more autocomplete
2 years ago
Kaveen Kumarasinghe
ca0fa419f9
change some defaults
2 years ago
Rene Teigen
207df295f0
Even more
2 years ago
Rene Teigen
7e5dace02b
Docs, fixes and linting
2 years ago