7a433bfccb
pass activity_state.json_metadata to feedback for additional context.
...
modified: app.py
modified: research/activity17-choose-adventure.yaml
2024-08-04 11:01:31 -04:00
36abf1590e
/activity info on --local-activities
...
modified: app.py
modified: research/activity17-choose-adventure.yaml
2024-08-04 10:42:14 -04:00
90964f2800
prize room and offering pit
...
new file: research/activity17-choose-adventure.yaml
2024-08-04 09:02:13 -04:00
7ceb9303ea
metadata_add and metadata_remove to allow for items to be consumed.
...
modified: app.py
modified: research/activity14-choose-adventure.yaml
modified: research/activity15-choose-adventure.yaml
modified: research/activity16.yaml
2024-08-04 08:33:55 -04:00
7198f2109e
a prize room for fun.
...
modified: app.py
modified: research/activity15-choose-adventure.yaml
2024-08-03 18:21:43 -04:00
847f609b4a
supply username to feedback routine so llm knows that context
...
remove dupe content and unessasary ai_feedback from different paths.
modified: app.py
modified: research/activity15-choose-adventure.yaml
2024-08-03 14:55:43 -04:00
018671a8c1
remove print debug statement
...
modified: app.py
2024-08-03 13:07:42 -04:00
8cca256c89
prompt engineering activity 15
...
modified: app.py
modified: research/activity15-choose-adventure.yaml
2024-08-03 09:29:53 -04:00
65404a4ecd
now you can load local activities via --local-activities
...
modified: app.py
modified: research/activity15-choose-adventure.yaml
2024-08-03 09:03:32 -04:00
257e5a6a04
/activity metadata
...
modified: README.rst
modified: app.py
modified: research/activity16.yaml
2024-08-02 18:49:50 -04:00
ea082ad1ff
migrate all activities, there should always be a step without a question
...
as last step.
modified: research/activity.yaml
modified: research/activity2.yaml
modified: research/activity4.yaml
modified: research/activity5.yaml
modified: research/activity6.yaml
modified: research/activity7.yaml
2024-08-01 18:03:00 -04:00
ade6bfed18
fix guarded_ai feedback issue
2024-07-31 17:15:07 -04:00
7953815e9d
fix missing fstring ai tokens now actually sent to ai during feedback!
2024-07-31 09:08:06 -04:00
a6d188f3c7
this activity16 lets student explore 3 topics and exit after doing all 3
...
to the end.
new file: research/activity16.yaml
2024-07-31 08:22:22 -04:00
63b9bb18b5
display ending info when activity finishes
...
modified: app.py
2024-07-31 07:40:22 -04:00
7fe320a958
refactor looping until a question is found to reduce code duplication
...
modified: app.py
2024-07-30 22:20:18 -04:00
78f369d917
get rid of redundant content_block transitions
2024-07-30 21:10:41 -04:00
75812a8f37
this version of the safe room has secret items and rooms.
...
modified: app.py
new file: research/activity15-choose-adventure.yaml
2024-07-30 20:48:36 -04:00
645a48a2dd
allow open source to work with vllm
...
modified: app.py
2024-07-29 10:26:49 -04:00
dbe7e0bd6a
some steps don't have questions, try to do the right thing.
...
modified: app.py
modified: research/activity0.yaml
2024-07-29 07:38:52 -04:00
94283a0377
Merge pull request #2 from russellballestrini/ai-guarded
...
Ai guarded
2024-07-29 06:34:51 -04:00
9f3c5fb3a7
hcanges per rabbit feedback
...
modified: app.py
modified: research/guarded_ai.py
2024-07-29 06:34:05 -04:00
dd13bce82b
Update research/guarded_ai.py
...
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
2024-07-29 06:17:48 -04:00
aa783ded70
modified: guarded_ai.py
2024-07-28 20:53:00 -04:00
602039ca71
play tested and working
...
modified: app.py
2024-07-28 20:37:31 -04:00
5d10296f1f
escape room mechanics with json_metadata for temporarily collecting data
...
based on where the user has went we can for example set a key: true if
they collected a key needed to access a section's steps.
modified: app.py
new file: migrations/versions/d737de68d6fa_add_metadata_field_to_activitystate.py
new file: research/activity14-choose-adventure.yaml
2024-07-28 19:14:54 -04:00
e3b3ddb007
allow player to go back if they change their minds, less "rails".
...
modified: research/activity13-choose-adventure.yaml
2024-07-28 15:07:34 -04:00
2fc774d85c
/activity cancel
...
modified: README.rst
modified: app.py
2024-07-28 13:59:25 -04:00
0462de7368
Activity Mode documented
2024-07-28 13:13:57 -04:00
8d771e8b06
allow user to ask question and explore longer
...
instead of 3 turns per step allow for 30
2024-07-28 12:54:32 -04:00
684f3df38e
fix defect/regression with linear activities
...
modified: guarded_ai.py
2024-07-28 11:59:40 -04:00
7e7b226fb1
print content blocks and skip the llm logic if no question in step.
...
modified: research/guarded_ai.py
2024-07-28 11:28:44 -04:00
02c97beebe
fix defect when step has no question.
...
modified: app.py
modified: research/activity13-choose-adventure.yaml
2024-07-28 11:04:30 -04:00
cfa5d77a42
Allowing for non-linear progression depending on buckets category
...
new field in the transitions is next_section_and_step which is optional
and defaults to None but also can be "section_3:step_1"
modified: app.py
new file: research/activity0.yaml
new file: research/activity13-choose-adventure.yaml
modified: research/guarded_ai.py
2024-07-28 10:36:09 -04:00
7e97acf477
content_blocks and questions support markdown values.
...
modified: research/activity10.yaml
2024-07-27 15:49:19 -04:00
93f274ef39
modified: app.py
2024-07-27 15:37:29 -04:00
692e34d090
repeat the question if not correct, after AI feedback
...
modified: app.py
2024-07-27 14:14:34 -04:00
ee5721a1fb
default rubric for grading and scoring trivia.
...
displays at the end of game or when running `/activity info`.
modified: app.py
2024-07-27 13:56:20 -04:00
5583e34e51
prompt engineering.
...
modified: research/guarded_ai.py
2024-07-27 12:22:51 -04:00
6dff9dc6e9
Integrated gaurded ai via websocket frontend.
...
modified: app.py
new file: migrations/versions/d04950c5a624_add_activitystate_table2.py
new file: migrations/versions/d3631b8bb652_add_activitystate_table.py
2024-07-27 10:30:07 -04:00
15ac4fa015
algo for guarding AI on rails.
...
new file: research/activity.yaml
new file: research/activity10.yaml
new file: research/activity11.yaml
new file: research/activity12.yaml
new file: research/activity2.yaml
new file: research/activity3.yaml
new file: research/activity4.yaml
new file: research/activity5.yaml
new file: research/activity6.yaml
new file: research/activity7.yaml
new file: research/activity8.yaml
new file: research/activity9.yaml
new file: research/guarded_ai.py
2024-07-27 08:57:44 -04:00
Russell Ballestrini
698455fb40
gpt-4o-mini as gpt-mini alias
...
modified: README.rst
modified: app.py
2024-07-18 17:12:05 -04:00
Russell Ballestrini
da5a8cbcfa
gpt-4o for titles and add claude-opus
...
modified: README.rst
modified: app.py
2024-07-08 17:33:12 -04:00
393769bcf7
Merge pull request #1 from russellballestrini/search
...
Keyword search across all chatrooms to find across conversation history
2024-07-04 12:14:58 -04:00
57d8e701f2
remove username and snippet from SERP page
2024-07-04 12:04:46 -04:00
db3c15ea0d
hide snippets pass room list in search page
...
modified: app.py
modified: templates/base.html
modified: templates/search.html
2024-07-04 11:35:22 -04:00
926262cdaa
keep keywords in search form.
...
modified: app.py
modified: templates/base.html
2024-07-04 11:12:21 -04:00
5577821855
save username when searching
...
I CAN program offline without an LLM. ; )
modified: app.py
modified: templates/base.html
modified: templates/search.html
2024-07-04 10:57:30 -04:00
77c2ef1d83
messing around with keyword search working but ugly!
...
modified: app.py
new file: templates/base.html
modified: templates/chat.html
new file: templates/search.html
2024-07-04 10:21:37 -04:00
e5940d3020
Fix Claude consecutive roles issue
...
This commit addresses the issue where the Claude model was throwing an error due to multiple consecutive "user" roles in the chat history. The following changes have been made:
- Implemented a new function `group_consecutive_roles` to group consecutive messages of the same role into one.
- Updated the `chat_claude`, function to use the `group_consecutive_roles` function before sending the chat history to the respective models.
By grouping consecutive messages of the same role, the chat history now alternates between "user" and "assistant" roles, resolving the "roles must alternate between 'user' and 'assistant'" error from the Claude model.
2024-06-22 09:47:04 -04:00
