f8972ec3bb
Format Python code with psf/black push
2 years ago
2cf163248e
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
2 years ago
965ad37087
search pre-processor for query refining for google custom search
2 years ago
42822e89e3
Format Python code with psf/black push
2 years ago
1f400208d7
minor fixes
2 years ago
01fb514a9b
Pagination for gpt responses, max tokens 4096
2 years ago
6a87248a0a
Format Python code with psf/black push
2 years ago
a2a79afb18
search improvements
2 years ago
1d2a2c8eae
default search scope to 2, 5 as a default is way too expensive.
2 years ago
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
02b2bb97d8
Change backoff handling to be more verbose
2 years ago
5de0fd37da
Conversation command now has a model option
...
Added model autocomplete
2 years ago
64ce627bb7
Update filetypes
2 years ago
0555cf8b33
Some async changes
2 years ago
9052bc2d80
Added gpt-index commands
2 years ago
f8d797f3a8
Format Python code with psf/black push
2 years ago
f473342bff
move overrides into class
2 years ago
595feaf539
persistent settings
2 years ago
b4ddee81f7
welcome message off by default
2 years ago
32726ecba1
Merge pull request #119 from duckdoom4/main
...
Fix spelling mistakes
2 years ago
774cf9423b
Format Python code with psf/black push
2 years ago
8d5dd77f2c
remove print
2 years ago
50e6f59ab5
change token limit when the text model changes
2 years ago
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
ac11d9f2a4
Remove hardcoded 'magic values'
2 years ago
5de2e79b3b
Add missing models
2 years ago
980f0f3dd4
Fix spelling mistakes
2 years ago
5841171106
slightly reduce pretext, improve minimal pretext, add support for >2 temperature
2 years ago
7779e44a2c
Format Python code with psf/black push
2 years ago
11f563e16a
Add Paraphrase
2 years ago
7e5d9266d5
Format Python code with psf/black push
2 years ago
4df4096f02
speed up moderations and smoothen translations
2 years ago
7260ab7b6b
Add stop in conversation, some formatting
...
Added ping on thread open
Removed extra newlines from ask formatting
2 years ago
f0860d1f66
Format Python code with psf/black push
2 years ago
2ff7cb1a3b
add approve button to moderations, add reset
2 years ago
4c08ab8820
Format Python code with psf/black push
2 years ago
7cb19039a1
custom bot name, beautify responses
2 years ago
50a9f7c469
custom bot name, beautify responses
2 years ago
02762fd61c
Add formality param to translations
2 years ago
8c1f492243
reorder language list
2 years ago
d125668d25
Format Python code with psf/black push
2 years ago
3627d32e54
Translations with DeepL
2 years ago
ea5f95800b
Format Python code with psf/black push
2 years ago
e947e030fb
more autocomplete
2 years ago
ca0fa419f9
change some defaults
2 years ago
207df295f0
Even more
2 years ago
7e5dace02b
Docs, fixes and linting
2 years ago
ba3ea3231b
a big refactor
2 years ago
1652c0be47
Merge remote-tracking branch 'Remote_Origin/main' into embeds
2 years ago
99bb6200aa
Format Python code with psf/black push
2 years ago
2cf6f22d4f
Merge pull request #92 from Hikari-Haru/edit-endpoint
...
Add the edit endpoint
2 years ago
cf7f3f9ba4
Fix paginated edits, fix ask edit passing in redos prompt
2 years ago
91e84dddf6
Added the possibility to configure SQLITE db path
...
Now, the SQLITE db path for the user API keys can be configured through the USER_KEY_DB_PATH env variable
Signed-off-by: Alessandro Bellia <casildaserrano@yahoo.it>
2 years ago
deee0b328d
Codex redo
2 years ago
61a2a19191
Redo work
2 years ago
baa37f65fd
Merge remote-tracking branch 'Remote_Origin/main' into edit-endpoint
2 years ago
5dcd493c67
Format Python code with psf/black push
2 years ago
709382b8da
api backoff
2 years ago
8ab7257cac
adjust warn thresholds..
2 years ago
8fe9772db3
add reaction to warned messages
2 years ago
c9359bb17a
update moderations delete thresholds
2 years ago
429ea37a44
Update moderations delete hate threshold
2 years ago
e401927dcd
Add support for permanent custom model in threads
...
No current way to set it yourself
2 years ago
b261aa6df4
Add codex to the edit command
2 years ago
4efb82a033
Add edit endpoint
2 years ago
4aa20f832f
Format Python code with psf/black push
2 years ago
6b99f57fdf
Merge remote-tracking branch 'Remote_Origin/main' into override_threads
2 years ago
585638c457
Format Python code with psf/black push
2 years ago
6bff3b2cb5
Stabilize pinecone conversations
2 years ago
7ecc56f0ae
Made the json parsin more robust and fixed bugs
2 years ago
fbdc03b8dd
Enable json openers with overrides
2 years ago
b47d52f217
Format Python code with psf/black push
2 years ago
eda7e66f02
Merge branch 'main' into multi-tenancy
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
2 years ago
051fc3a2ff
remove api key prints
2 years ago
cfb7eb0903
Multi tenancy api key support
2 years ago
ead677d558
Format Python code with psf/black push
2 years ago
0b2d4c95b7
fix bugs with conversations, some slight improvements
2 years ago
2566eb2dc3
Format Python code with psf/black push
2 years ago
be18022dd8
merge
2 years ago
43fc228376
fix some moderation bugs
2 years ago
2e0e96a205
Format Python code with psf/black push
2 years ago
4c11843fbc
fix weird merge error
2 years ago
0c6272d933
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
2 years ago
893cf11e84
improve moderations service
2 years ago
db5e13a9cd
Format Python code with psf/black push
2 years ago
7b42bc4afe
Upgrade moderations service, double thresholds, admin options
2 years ago
99e1e3b11d
Format Python code with psf/black push
2 years ago
a6ded5ab81
fix opener file loading
2 years ago
1e7b5b97a3
change path constructor
2 years ago
d1d1b062f2
Merge branch 'main' into feat/docker-env
2 years ago
105afa0354
non docker case
2 years ago
7f1a8e30f8
Format Python code with psf/black push
2 years ago
720fad0ee7
permanent memory with pinecone ready for alpha
2 years ago
a8b209c212
draft
2 years ago
fe54b250f6
fix img prompt optimizer redo bug
2 years ago
f4f53cf3cf
Format Python code with psf/black push
2 years ago
79c44fb0a0
Merge branch 'main' into rekey-conversation
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
2 years ago
903c91497d
Format Python code with psf/black push
2 years ago
9896051a7b
fine tune moderations a bit, fix Redo
2 years ago
55f0db7f8b
Changed more name handling
2 years ago
c0e0d8ba8b
Changed conversations to be keyed by thread
...
The one starting it is the thread owner
Can only own one thread but can converse in multiple
Added a check dmchannel for the message edit moderation
Gave an error when opening a conversation then ending it
2 years ago
github-actions
Kaveen Kumarasinghe
Hikari Haru
Kaveen Kumarasinghe
duckdoom4
Alessandro Bellia
Justin McPherson