Commit graph

112 commits

Author SHA1 Message Date
0efbe93910 modified: app.py 2024-01-19 08:59:11 -05:00
f256d65391 modified: app.py 2024-01-13 11:06:41 -05:00
2f8a6c502d hacked in ability to run local llama2 models like mistral
modified:   app.py
	new file:   install-llama.sh
	modified:   requirements.txt
2024-01-13 10:05:02 -05:00
6a42dacf65 localhost openchat is working. lol
I replaced gpt-3.5-turbo workloads with openchat a local GPU powered inference server

The openchat inference server supports using the latest and official openai python client.

This means you can replace both standard and streaming workloads with an "offline" LLM.

	modified:   README.rst
	modified:   app.py
2024-01-07 14:57:40 -05:00
560d0a1ae5 small refactor 2024-01-06 11:34:53 -05:00
47d0b24fc4 add a link to the docs
modified:   templates/chat.html
2024-01-06 08:37:46 -05:00
6f70dcfc42 allow cancel on all LLMs
modified:   app.py
2024-01-06 08:12:54 -05:00
c40f961fc3
Update README.rst 2023-12-29 14:12:36 -05:00
Russell Ballestrini
d666efb162 implement together/solar
modified:   README.rst
	modified:   app.py
2023-12-29 13:28:53 -05:00
79cc174b28 modified: app.py 2023-12-22 09:05:01 -05:00
Russell Ballestrini
12abd02978 modified: README.rst 2023-12-20 09:18:35 -05:00
Russell Ballestrini
e38c565eaa add other mistralai models
modified:   app.py
2023-12-20 09:17:12 -05:00
Russell Ballestrini
c95f2722e9 modified: README.rst 2023-12-20 08:11:54 -05:00
71f8d9d15c make openchat a math assistant
modified:   app.py
2023-12-20 06:30:54 -05:00
Russell Ballestrini
12f1abc4b7 together ai integration
modified:   app.py
	modified:   requirements.txt
2023-12-19 12:55:13 -05:00
efbb6d7c26
Update README.rst 2023-12-16 11:40:00 -05:00
5918295320
Update README.rst 2023-12-16 11:38:54 -05:00
65e904b286 don't duplicate previous messages if they already exist (reconnects)
modified:   templates/chat.html
2023-12-16 08:25:01 -05:00
9c3bbe169f don't scroll when users join.
modified:   templates/chat.html
2023-12-15 10:33:56 -05:00
2b7999a857 fix claude
modified:   app.py
2023-12-15 10:00:20 -05:00
Russell Ballestrini
6c0a09e0c2 modified: README.rst 2023-12-14 14:21:08 -05:00
Russell Ballestrini
d42234f407 mistralai api support
modified:   app.py
	modified:   requirements.txt
2023-12-14 13:42:16 -05:00
Russell Ballestrini
caa4cd234f consolidate around data.content instead of message
modified:   app.py
	modified:   templates/chat.html
2023-12-12 13:52:05 -05:00
Russell Ballestrini
b778c7e53c modified: templates/chat.html 2023-12-12 12:14:13 -05:00
Russell Ballestrini
31a2f306e1 allow edits of streamed message chunks
modified:   templates/chat.html
2023-12-12 11:28:46 -05:00
Russell Ballestrini
bc378ce0dd Edit button, with save and cancel.
modified:   app.py
	modified:   templates/chat.html
2023-12-12 10:28:05 -05:00
Russell Ballestrini
434db03ab0 show less for large blocks 2023-12-11 13:30:18 -05:00
7d6fe1b27b fix dall-e-3 don't try to run marked on base64 images.
modified:   app.py
	modified:   templates/chat.html
2023-12-10 10:50:30 -05:00
Russell Ballestrini
8a626501b3 install-ubuntu.sh use a separate application user instead of root
fix memory leak where were didn't clean up cancellation_requests

	modified:   app.py
	modified:   install-ubuntu.sh
2023-12-08 12:14:53 -05:00
Russell Ballestrini
0b1a09c6f1 remove sudo assume running as root.
modified:   install-ubuntu.sh
2023-12-08 07:06:13 -05:00
Russell Ballestrini
dfbdbe9b0e sqlite3 for ubuntu deploys 2023-12-08 06:55:29 -05:00
Russell Ballestrini
c2aaac9768 make count_tokens public on Message
modified:   app.py
	modified:   migrations/versions/190d5ef26e20_add_token_count_to_message.py
2023-12-07 13:01:42 -05:00
Russell Ballestrini
caf4c76ceb deleted: migrate.py 2023-12-07 10:13:49 -05:00
43317fb1a6 modified: app.py
new file:   migrate.py
	modified:   requirements.txt
2023-12-07 10:09:57 -05:00
06a0867161 token count to message object
modified:   app.py
	new file:   migrations/versions/190d5ef26e20_add_token_count_to_message.py
2023-12-07 09:33:35 -05:00
Russell Ballestrini
243bd4084f modified: .gitignore 2023-12-06 12:48:56 -05:00
Russell Ballestrini
7369b6c25f reorder
modified:   app.py
2023-12-06 12:16:35 -05:00
Russell Ballestrini
30e5442fed better error logging when completions fail
modified:   app.py
2023-12-06 12:06:16 -05:00
42b91a28da
Update README.rst 2023-12-05 18:30:46 -05:00
Russell Ballestrini
7838178ec4 read access on bucket to start.
modified:   template.yaml
2023-12-05 11:17:20 -05:00
Russell Ballestrini
f3ab7e7a4b claude is working on AWS now.
modified:   install-ubuntu.sh
	modified:   template.yaml
2023-12-05 10:15:36 -05:00
Russell Ballestrini
c074dad677 modified: install-ubuntu.sh 2023-12-05 09:51:42 -05:00
Russell Ballestrini
954aa91200 some deployment examples on AWS and Ubuntu 22.04 LTS
new file:   install-ubuntu.sh
	modified:   template.yaml
2023-12-05 09:39:50 -05:00
Russell Ballestrini
9f5ee42e73 instance profile and permission to run claude
modified:   template.yaml
2023-12-05 08:24:53 -05:00
Russell Ballestrini
29acdd9a3c new file: template.yaml
modified:   templates/chat.html
2023-12-05 07:33:02 -05:00
f41e9e5bd9 dall-e-3
modified:   README.rst
	modified:   app.py
	new file:   flask-socketio-llm-completions-2.png
2023-12-04 08:39:13 -05:00
d5db3b274b dall-e-3 support
modified:   app.py
2023-12-04 08:19:45 -05:00
4ca8724d79 modified: templates/chat.html 2023-12-03 16:05:08 -05:00
34a1381f1c black 2023-12-03 15:39:27 -05:00
ae2e39beac /s3 ls * command
modified:   README.rst
	modified:   app.py
2023-12-03 15:34:22 -05:00