b60bcfd68d
reset indexes command
1 year ago
22ba80c469
Multi-index support
1 year ago
c7271ab525
Format Python code with psf/black push
1 year ago
5f62b1fa2e
Merge branch 'main' into set-conversation-model
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
1 year ago
33e68588ee
Merge branch 'main' into gpt-index
1 year ago
5d5ec3dbb1
Format Python code with psf/black push
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
f48deab320
Forgot to remove extra models
1 year ago
669e3f0191
Changed how max tokens are fetched
...
lowered from 4024 to 2024 if max tokens can't be gotten
1 year ago
71125ce65d
Add ephemeral option to ask and edit
1 year ago
95dd054f1c
Remove finetune stuff
1 year ago
02b2bb97d8
Change backoff handling to be more verbose
1 year ago
5de0fd37da
Conversation command now has a model option
...
Added model autocomplete
1 year ago
64ce627bb7
Update filetypes
1 year ago
0555cf8b33
Some async changes
1 year ago
9052bc2d80
Added gpt-index commands
1 year ago
f8d797f3a8
Format Python code with psf/black push
1 year ago
f473342bff
move overrides into class
1 year ago
595feaf539
persistent settings
1 year ago
b4ddee81f7
welcome message off by default
1 year ago
32726ecba1
Merge pull request #119 from duckdoom4/main
...
Fix spelling mistakes
1 year ago
774cf9423b
Format Python code with psf/black push
1 year ago
8d5dd77f2c
remove print
1 year ago
50e6f59ab5
change token limit when the text model changes
1 year 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
1 year ago
ac11d9f2a4
Remove hardcoded 'magic values'
1 year ago
5de2e79b3b
Add missing models
1 year ago
980f0f3dd4
Fix spelling mistakes
1 year ago
5841171106
slightly reduce pretext, improve minimal pretext, add support for >2 temperature
1 year ago
7779e44a2c
Format Python code with psf/black push
1 year ago
11f563e16a
Add Paraphrase
1 year ago
7e5d9266d5
Format Python code with psf/black push
1 year ago
4df4096f02
speed up moderations and smoothen translations
1 year ago
7260ab7b6b
Add stop in conversation, some formatting
...
Added ping on thread open
Removed extra newlines from ask formatting
1 year ago
f0860d1f66
Format Python code with psf/black push
1 year ago
2ff7cb1a3b
add approve button to moderations, add reset
1 year ago
4c08ab8820
Format Python code with psf/black push
1 year ago
7cb19039a1
custom bot name, beautify responses
1 year ago
50a9f7c469
custom bot name, beautify responses
1 year ago
02762fd61c
Add formality param to translations
1 year ago
8c1f492243
reorder language list
1 year ago
d125668d25
Format Python code with psf/black push
1 year ago
3627d32e54
Translations with DeepL
1 year ago
ea5f95800b
Format Python code with psf/black push
1 year ago
e947e030fb
more autocomplete
1 year ago
ca0fa419f9
change some defaults
1 year ago
207df295f0
Even more
1 year ago
7e5dace02b
Docs, fixes and linting
1 year ago
ba3ea3231b
a big refactor
1 year ago
1652c0be47
Merge remote-tracking branch 'Remote_Origin/main' into embeds
1 year ago
99bb6200aa
Format Python code with psf/black push
1 year ago
2cf6f22d4f
Merge pull request #92 from Hikari-Haru/edit-endpoint
...
Add the edit endpoint
1 year ago
cf7f3f9ba4
Fix paginated edits, fix ask edit passing in redos prompt
1 year 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>
1 year ago
deee0b328d
Codex redo
1 year ago
61a2a19191
Redo work
1 year ago
baa37f65fd
Merge remote-tracking branch 'Remote_Origin/main' into edit-endpoint
1 year ago
5dcd493c67
Format Python code with psf/black push
1 year ago
709382b8da
api backoff
1 year ago
8ab7257cac
adjust warn thresholds..
1 year ago
8fe9772db3
add reaction to warned messages
1 year ago
c9359bb17a
update moderations delete thresholds
1 year ago
429ea37a44
Update moderations delete hate threshold
1 year ago
e401927dcd
Add support for permanent custom model in threads
...
No current way to set it yourself
1 year ago
b261aa6df4
Add codex to the edit command
1 year ago
4efb82a033
Add edit endpoint
1 year ago
4aa20f832f
Format Python code with psf/black push
1 year ago
6b99f57fdf
Merge remote-tracking branch 'Remote_Origin/main' into override_threads
1 year ago
585638c457
Format Python code with psf/black push
1 year ago
6bff3b2cb5
Stabilize pinecone conversations
1 year ago
7ecc56f0ae
Made the json parsin more robust and fixed bugs
1 year ago
fbdc03b8dd
Enable json openers with overrides
1 year ago
b47d52f217
Format Python code with psf/black push
1 year ago
eda7e66f02
Merge branch 'main' into multi-tenancy
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
1 year ago
051fc3a2ff
remove api key prints
1 year ago
cfb7eb0903
Multi tenancy api key support
1 year ago
ead677d558
Format Python code with psf/black push
1 year ago
0b2d4c95b7
fix bugs with conversations, some slight improvements
1 year ago
2566eb2dc3
Format Python code with psf/black push
1 year ago
be18022dd8
merge
1 year ago
43fc228376
fix some moderation bugs
1 year ago
2e0e96a205
Format Python code with psf/black push
1 year ago
4c11843fbc
fix weird merge error
1 year ago
0c6272d933
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
1 year ago
893cf11e84
improve moderations service
1 year ago
db5e13a9cd
Format Python code with psf/black push
1 year ago
7b42bc4afe
Upgrade moderations service, double thresholds, admin options
1 year ago
99e1e3b11d
Format Python code with psf/black push
1 year ago
a6ded5ab81
fix opener file loading
1 year ago
1e7b5b97a3
change path constructor
1 year ago
d1d1b062f2
Merge branch 'main' into feat/docker-env
1 year ago
105afa0354
non docker case
1 year ago
7f1a8e30f8
Format Python code with psf/black push
1 year ago
720fad0ee7
permanent memory with pinecone ready for alpha
1 year ago
a8b209c212
draft
1 year ago
fe54b250f6
fix img prompt optimizer redo bug
1 year ago
f4f53cf3cf
Format Python code with psf/black push
1 year ago
79c44fb0a0
Merge branch 'main' into rekey-conversation
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
1 year ago
903c91497d
Format Python code with psf/black push
1 year ago
9896051a7b
fine tune moderations a bit, fix Redo
1 year ago
55f0db7f8b
Changed more name handling
1 year 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
1 year ago
7fb849de88
Format Python code with psf/black push
1 year ago
369c836a72
AI Moderation!
1 year ago
db7c400ca4
Format Python code with psf/black push
1 year ago
3775432aae
Merge pull request #58 from Hikari-Haru/autocomplete
...
Autocomplete and changed the way opener files are loaded to use a folder instead
1 year ago
92f902cb15
return message if no opener folder
1 year ago
20bd3a970c
Format Python code with psf/black push
1 year ago
04d1a06a9e
Merge pull request #60 from Hikari-Haru/bigger-images
...
Changed the image resizing to go by the guild filesize limit
1 year ago
4a39685e45
Format Python code with psf/black push
1 year ago
b31bfbe26d
Merge pull request #55 from Hikari-Haru/ask-parameters
...
Added passthrough of gpt3 parameters to /ask
1 year ago
0835d849fc
Add fallback if guild is None
1 year ago
68a20dcc50
Changed the image resizing to go by the guild filesize limit
...
Since boosted servers have higher limits, even for bots
1 year ago
f2033c0fcc
Set autocomplete to limit to 25 options, the max
1 year ago
6cfd2838a5
Added autocompleters to settings and opener files
...
Settings now gets current keys so manual updating of choices isn't required
Changed the way opener files are added to the conversation
Using an opener file also enables minimal starter
Added some example opener files
1 year ago
663fda421c
Make recurring file operations all async, add custom opener file feature
1 year ago
9bbfa2de7a
Format Python code with psf/black push
1 year ago
6cea6da6fe
Proper error messages on an API error
1 year ago
ddc23e7c10
Added some print to send_request and fixed the top_p description
1 year ago
8fbfe952f8
Changed how the overrides are checked to allow "0" input
1 year ago
9e4460c009
Added basic passthrough to /ask
...
Update readme
1 year ago
92f7632095
Format Python code with psf/black push
1 year ago
05a54e28d6
Allow for a way for all users to be granted command access
1 year ago
ab3d0a6868
Format Python code with psf/black push
1 year ago
5218c445af
Merge branch 'main' into slashgroups-refactor
...
Signed-off-by: Kaveen Kumarasinghe <k5kumara@uwaterloo.ca>
1 year ago
0adb5c0e38
fix welcome message
1 year ago
53235e4e1d
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
1 year ago
7d116d2ef3
fix typos
1 year ago
316dcbb023
Format Python code with psf/black push
1 year ago
db1191144d
fix minor typo
1 year ago
f13bd6ea3f
Merge branch 'Kav-K:main' into KarlKennerley-GPT3Discord-Issue#34
1 year ago
566c0ae278
fix error
1 year ago
ddbe356e2a
Changes to environment loading.
...
- Move Some environment loading code to EnvService.
- Attempt loading of env file from multiple locations & names
- Provide a path fetching + fallback function for reading
paths from environment vars.
- For Docker;
- Create /opt/gpt3discord/{etc,bin,shared}
- Copy .txt shared data into shared
- Copy main .py into bin
1 year ago
3a663c244f
Updated get_welcome_message function
...
Updated the get_welcome_message function to fall back on a string saved in a .env file and then to fall back on a simple default string.
1 year ago
357422414a
Added getter and setter for welcome msg setting.
...
Added getter and setter functions to allow for enabling and disabling of welcoming messages.
1 year ago
b48c68e868
A little cleanup and changed the "admin" slash group to "system"
...
So that it's hidden further down on the list
1 year ago
e5eeb035c1
Implemented slash command grouping and more ways to configure who can use what.
...
Refactored /g into /chat and /gpt-chat into /converse
Both have the grouping "gpt" so the full is /gpt chat, and /gpt converse
Added pycord-multicog to the project for easier slash grouping across cogs
Made the role check case insensitive and added some comments to the sample.env
Removed the rest of the discord.ext imports, it's not really used, ymmv
Removed another admin check i had missed in local-size
1 year ago
72c5760479
Format Python code with psf/black push
1 year ago
bfdd8fc29f
black test
1 year ago
17b71059b5
Format Python code with psf/black push
1 year ago
37f2c8c1b4
Make image operations completely async, fix the optimized text length, set best_of=2
1 year ago
49b652bdd3
Added getter for welcome message env variable.
...
Added a getter function for the welcome message environment variable. Fixes issue #34 .
1 year ago
e31df356a9
Changed send_followup to respond
1 year ago
3ddb1056c3
Change way that roles are checked and some formatting
1 year ago
2fc67fc13b
Format Python code with psf/black push
1 year ago
fb5b1f1e93
SLASH COMMANDSgit status! Major Overhaul
1 year ago
57e863167d
Merge branch 'Kav-K:main' into main
1 year ago
d6885b3c35
Add Dockerfile + concept of a DATA_DIR
...
- Add a Dockerfile so people can run this bot in a docker container
- Stuck with recommendation of running with python3.9 for now
- Will later test with 3.11 + supply fixes if I get this working ...
- Added a DATA_DIR env param to use to choose the directory to write data we want persistent across docker container restarts to be written to
- We default to CWD like the code does today - we just explicitly pass it to functions / classes
Test:
- `docker build -t gpt3discord .`
```
crl-m1:GPT3Discord cooper$ docker image ls
REPOSITORY TAG IMAGE ID CREATED SIZE
gpt3discord latest 6d2832af2450 69 seconds ago 356MB
```
- Try run it ... I would guess if I had correct tokens things would work ...
- To do so I plan to bind mount over /bin/.env on my docker container when I run this ...
```
crl-m1:GPT3Discord cooper$ docker run gpt3discord
None of PyTorch, TensorFlow >= 2.0, or Flax have been found. Models won't be available and only tokenizers, configuration and file/data utilities can be used.
Downloading: 100%|██████████| 1.04M/1.04M [00:02<00:00, 516kB/s]
Downloading: 100%|██████████| 456k/456k [00:01<00:00, 319kB/s]
Downloading: 100%|██████████| 1.36M/1.36M [00:03<00:00, 443kB/s]
Downloading: 100%|██████████| 665/665 [00:00<00:00, 740kB/s]
Traceback (most recent call last):
File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 413, in static_login
data = await self.request(Route("GET", "/users/@me"))
File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 366, in request
raise HTTPException(response, data)
discord.errors.HTTPException: 401 Unauthorized (error code: 0): 401: Unauthorized
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "/bin/gpt3discord", line 79, in <module>
asyncio.get_event_loop().run_until_complete(main())
File "/usr/local/lib/python3.9/asyncio/base_events.py", line 647, in run_until_complete
return future.result()
File "/bin/gpt3discord", line 63, in main
await bot.start(os.getenv("DISCORD_TOKEN"))
File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 658, in start
await self.login(token)
File "/usr/local/lib/python3.9/site-packages/discord/client.py", line 514, in login
data = await self.http.static_login(token.strip())
File "/usr/local/lib/python3.9/site-packages/discord/http.py", line 417, in static_login
raise LoginFailure("Improper token has been passed.") from exc
discord.errors.LoginFailure: Improper token has been passed.
Wrote PID to file the file bot.pid
The debug channel and guild IDs are 755420092027633774 and 907974109084942396
Improper token has been passed.
Removing PID file
Unclosed client session
client_session: <aiohttp.client.ClientSession object at 0xffff721a2dc0>
Unclosed connector
connections: ['[(<aiohttp.client_proto.ResponseHandler object at 0xffff718fe0a0>, 170230.336548951)]']
connector: <aiohttp.connector.TCPConnector object at 0xffff721a2fd0>
```
1 year ago
51a7ed7239
API key oopsie ;)
1 year ago
ec38feaa36
Format Python code with psf/black push
1 year ago
193a967d41
REVAMP ASYNC, fully working now, massively improve immage prompt optimizer
1 year ago
46b4c5d685
Format Python code with psf/black push
1 year ago
cdc6e70adb
Fix tempfile giving PermissionError on windows
1 year ago
4de4ab3f6e
bug squash!
1 year ago
1f96dda52a
Merge branch 'main' of https://github.com/Kav-K/GPT3Discord
1 year ago
510f294c76
make bot fully async!
1 year ago
24dce18052
Format Python code with psf/black push
1 year ago
3ea5f544e8
Fix bugs and add end conversation button to convo messages
1 year ago
ffa23155c0
Format Python code with psf/black push
1 year ago
96c69c417f
fix bugs
1 year ago
0ed400a505
Format Python code with psf/black push
1 year ago
bb619e052c
Recursive message summarizationgit add *git add *! Infinite chatgit add *git add *
1 year ago
2c915ddcc3
update convo starter and add set_usage
1 year ago
6001e57c58
Finalize everything and initialize the ci pipeline
1 year ago
c54d2cc349
ironed out bugs
1 year ago
1312a864df
Format Python code with psf/black push
1 year ago
0065f4918a
Add full DALL-E Integration
1 year ago
9e263dc57b
refactor, redo ability for image prompt optimization
1 year ago
165c62c978
Add a command to clear all conversation threads immediately across all servers the bot uses
1 year ago
741abc0555
Close threads when end
1 year ago
825b009aa8
Full refactor to pycord, and cogs
1 year ago
Kaveen Kumarasinghe
github-actions
Kaveen Kumarasinghe
Rene Teigen
duckdoom4
Alessandro Bellia
Justin McPherson
Karl
Cooper Lees