Commit graph

230 commits

Author SHA1 Message Date
0250bf77b1
mistral ai upgrades 2025-02-08 15:48:23 -05:00
748649d98a o3-mini and hermes 8b 8fp!
modified:   README.rst
	modified:   app.py
	modified:   templates/base.html
	modified:   templates/chat.html
2025-02-01 15:58:01 -05:00
0492d5b329 r1 llm support:
modified:   README.rst
	modified:   app.py
	modified:   templates/base.html
	modified:   templates/chat.html
2025-01-25 14:37:26 -05:00
06d5167628 make port configurable for demo2.opencompletion.com 2025-01-25 07:46:11 -05:00
2e7fd18ba1 more openai models
modified:   README.rst
	modified:   app.py
	modified:   templates/base.html
	modified:   templates/chat.html
2024-12-31 12:18:03 -05:00
91d6192192 bunch more models.
modified:   app.py
	modified:   templates/base.html
	modified:   templates/chat.html
2024-12-09 18:25:37 -05:00
b01311a825 inactive uesrs now collected.
modified:   app.py
	new file:   migrations/versions/5d93cdf18549_room_inactive_users_column.py
	modified:   templates/base.html
	modified:   templates/chat.html
2024-11-24 14:16:25 -05:00
96c10fc6d6 announce when a username leaves the room.
modified:   app.py
	modified:   templates/chat.html
2024-11-24 13:32:08 -05:00
5fa37da991 sort active users, validate models and voices, fix room links
modified:   app.py
	modified:   templates/base.html
	modified:   templates/chat.html
2024-11-23 12:04:48 -05:00
0f82305087 feature complete. "sorry for the convenience"
modified:   app.py
	new file:   migrations/versions/1ac5a8e0f577_user_session_table.py
2024-11-23 11:32:49 -05:00
fab40ba60d w00t! active user list working, now we need disconnect to remove logic.
modified:   app.py
	modified:   templates/chat.html
2024-11-23 10:31:38 -05:00
f9f7da6ffc incremental progress
modified:   app.py
	modified:   templates/chat.html
2024-11-23 09:39:39 -05:00
3b3714f527 Fix defect with TTS after stream.
modified:   app.py
	modified:   templates/chat.html
2024-11-23 08:34:23 -05:00
Russell Ballestrini
185ebbcb59 ollama Hermes
ollama run hf.co/NousResearch/Hermes-3-Llama-3.1-8B-GGUF:Q8_0

	modified:   README.rst
	modified:   app.py
2024-11-22 14:15:44 -05:00
c8ffe15e66 fix all openai_client.chat calls to have n=1 for google api
modified:   app.py
2024-11-21 10:33:32 -05:00
b0aee48352 google gemini has entered the chat.
modified:   README.rst
	modified:   app.py
2024-11-21 10:16:46 -05:00
d316831a45 grok-beta
modified:   README.rst
	modified:   app.py
2024-11-21 08:57:29 -05:00
6d008a964f fixes for o1-mini but streaming is not supported...
modified:   app.py
2024-10-01 19:05:29 -04:00
75e637002b download markdown of conversation useful for github or jira
modified:   app.py
	modified:   templates/base.html
	modified:   templates/chat.html
2024-09-18 16:27:40 -04:00
0fae1eb910 hooray for open source! new hermes 3 llama 3.1 tested
http://home.foxhop.net:5001/chat/hermes-3-llama-3.1-chain-of-thought?username=changeme
2024-09-15 17:54:56 -04:00
6086d65f9b uses the openai syntax for the conversation dump including content & role
* user
* system

	modified:   app.py
	modified:   templates/base.html
	modified:   templates/chat.html
2024-09-15 08:57:34 -04:00
Russell Ballestrini
e310217166 gpt-o1-mini and mistral-nemo
You'll have to do `pip install --upgrade -r requirements.txt` to install latest:

* mistralai client
* openai client

	modified:   app.py
2024-09-13 09:04:35 -04:00
ba91cbcb27 modified: research/activity27-tic-tac-toe.yaml
new file:   static/images/tic-tac-toe.png
2024-08-29 06:55:40 -04:00
d1998f9d1c move off message to chat_message but it doesn't fix order issue.
The app seems to queue the category, feedback/content_blocks question

The strange part is the set_background happens in the middle of the
script after category but it comes first and FAST! In about a second
while the other messages take about 4 secs to finally arrive.

	modified:   app.py
	modified:   research/activity29-battleship.yaml
	modified:   templates/chat.html
2024-08-28 07:15:18 -04:00
41dff2865a Easy way to restart an activity without quitting.
modified:   app.py
	modified:   research/activity27-tic-tac-toe.yaml
	modified:   research/activity28-killer-squares.yaml
2024-08-25 10:05:57 -04:00
2e82ddc563 modified: app.py 2024-08-24 20:28:56 -04:00
df54e6b4aa conditionally run processing_script
modified:   app.py
	modified:   research/activity22-odds-or-evens.yaml
	modified:   research/activity24-math-plot.yaml
	modified:   research/activity27-tic-tac-toe.yaml
	modified:   research/guarded_ai.py
2024-08-24 14:31:46 -04:00
691e4ab054 working tic tac toe
modified:   app.py
	modified:   research/activity27-tic-tac-toe.yaml
2024-08-24 13:38:38 -04:00
863cec2e86 modified: app.py
new file:   research/activity26-magic-8-ball.yaml
2024-08-21 08:06:56 -04:00
1095df37e1 modified: app.py
new file:   research/activity25-20-questions.yaml
2024-08-20 17:38:48 -04:00
dc03ce9d5e math plotting!!! try out these equations:
( x^2 - 4x + 3 )
    ( x^2 - 2x + 1 )
    ( 2^x - 1 )

	modified:   app.py
	modified:   requirements.txt
	new file:   research/activity24-math-plot.yaml
2024-08-11 17:03:03 -04:00
fc358036c9 prompt engineering translation llm
modified:   app.py
	new file:   research/activity18.yaml
2024-08-11 14:58:36 -04:00
5c9ef230ae modified: app.py
modified:   research/activity23-math.yaml
2024-08-11 13:39:30 -04:00
f09d24aefc make math progressively more difficult.
modified:   ../app.py
	modified:   activity23-math.yaml
2024-08-11 11:27:32 -04:00
14dd105d03 woot upgraded guarded to support odds-or-evens game.
modified:   ../app.py
	new file:   activity22-odds-or-evens.yaml
	modified:   guarded_ai.py
2024-08-11 08:43:47 -04:00
3902ff48da modified: app.py 2024-08-10 20:21:00 -04:00
f923570f5a prompt engineering
modified:   app.py
	modified:   research/activity19-rock-paper-scissors.yaml
2024-08-10 19:15:19 -04:00
2609ff993d limited_effort should not be treated as correct.
modified:   app.py
	modified:   research/guarded_ai.py
2024-08-10 17:23:04 -04:00
f5df195e9b black and also set_language isn't "correct" anymore.
so it doesn't move the student on.

	modified:   app.py
	modified:   migrations/env.py
	modified:   migrations/versions/190d5ef26e20_add_token_count_to_message.py
	modified:   migrations/versions/a9e886c56482_create_room_table.py
	modified:   migrations/versions/d737de68d6fa_add_metadata_field_to_activitystate.py
	modified:   research/activity21.yaml
	modified:   research/guarded_ai.py
2024-08-10 17:00:52 -04:00
3a6c62cf22 hopefully we get some python examples
modified:   ../app.py
	modified:   activity21.yaml
2024-08-10 15:55:46 -04:00
9a4f2a8b30 violent python activity21.yaml
modified:   ../app.py
	new file:   activity21.yaml
2024-08-10 15:42:31 -04:00
058b0161df allow increment to go backward with n-1 and also support any int c for the
increment or decrement.

	modified:   ../app.py
	modified:   guarded_ai.py
2024-08-10 15:00:28 -04:00
e3d3bf0303 n+1 in yaml to accumulate integers.
modified:   ../app.py
	new file:   activity20-n-plus-1.yaml
	modified:   guarded_ai.py
2024-08-10 14:39:37 -04:00
0d908b65d4 fully functional activity19-rock-paper-scissors.yaml
modified:   ../app.py
	new file:   activity19-rock-paper-scissors.yaml
	modified:   ../templates/base.html
2024-08-10 13:24:26 -04:00
b979d31b40 more help text 2024-08-10 11:15:14 -04:00
920f0e931d /help
modified:   ../app.py
2024-08-10 11:02:05 -04:00
cebb2c2ec7 prompt engineering 2024-08-10 10:22:54 -04:00
4132afe9d1 prompt engineering
modified:   ../app.py
	modified:   activity0.yaml
2024-08-09 19:32:04 -04:00
17777d727d support all the languages!
modified:   app.py
	modified:   research/activity0.yaml
2024-08-09 08:20:48 -04:00
3b542285f6 counts_as_attempt implemented and we caught up guarded_ai to have
metadata

	modified:   app.py
	modified:   research/guarded_ai.py
2024-08-08 08:59:20 -04:00