Addition of types #493

huyinan · 2024-03-30T23:08:01Z

Create an extra type: 'ReasonType' as an optional argument. The 'ReasonType' decides how the crucial elements of the message generated by the system is displayed. The default value is 'Reason', making no change to the output message. Another value, 'REACT', split the output message into reasoning and action, with the former part only involving explanation and the latter part involving function calling.

Description

Motivation and Context

Types of changes

What types of changes does your code introduce? Put an x in all the boxes that apply:

Bug fix (non-breaking change which fixes an issue)
[ X] New feature (non-breaking change which adds core functionality)
Breaking change (fix or feature that would cause existing functionality to change)
Documentation (update in the documentation)
Example (update in the folder of example)

Implemented Tasks

Subtask 1
Subtask 2
Subtask 3

Checklist

Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!

[ X] I have read the CONTRIBUTION guide. (required)
My change requires a change to the documentation.
I have updated the tests accordingly. (required for a bug fix or a new feature)
I have updated the documentation accordingly.

Create an extra type: 'ReasonType' as an optional argument. The 'ReasonType' decides how the crucial elements of the message generated by the system is displayed. The default value is 'Reason', making no change to the output message. Another value, 'REACT', split the output message into reasoning and action, with the former part only involving explanation and the latter part involving function calling.

coderabbitai · 2024-03-30T23:08:05Z

Important

Auto Review Skipped

Auto reviews are disabled on this repository.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository.

To trigger a single review, invoke the @coderabbitai review command.

Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media?

Share

Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>.
- Generate unit testing code for this file.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai generate unit testing code for this file.
- @coderabbitai modularize this function.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai generate interesting stats about this repository and render them as a table.
- @coderabbitai show all the console.log statements in this repository.
- @coderabbitai read src/utils.ts and generate unit testing code.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (invoked as PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger a review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai help to get help.

Additionally, you can add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.

CodeRabbit Configration File (`.coderabbit.yaml`)

You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
Please see the configuration documentation for more information.
If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

Wendong-Fan

Hey @huyinan , thanks for the PR! This PR is still in progress and is not ready for review right? If so we can make the status as "draft", when it's ready for review we can reopen it, thanks!

Wendong-Fan · 2024-04-07T06:47:10Z

camel/prompts/ai_society.py

+<YOUR_ACTION> should be directly implementing the examples mentioned before. Always end <YOUR_SOLUTION> with: Next request.""")
+


prompt added here seems not clear, should the assistant always add <YOUR_ACTION> here? In the prompt above action was not mentioned

Wendong-Fan · 2024-04-07T06:51:17Z

camel/prompts/ai_society.py

+ ACTOR_PROMPT (TextPrompt): A system prompt for the AI actor that takes actions (usually search key words)
+ based on the outline of several key words from previous output from ASSISTANT. Then search results are


could you explain what does 'usually search key words' mean here to help me understand? thanks!

Wendong-Fan · 2024-04-07T06:54:59Z

camel/agents/react_embodied_agent.py

+from camel.messages import BaseMessage
+from camel.prompts import TextPrompt
+from camel.types import ModelType, RoleType, ReasonType
+from camel.functions.search_functions import *


I would suggest not using * doing import here

OK. This line has been commented out.

Wendong-Fan · 2024-04-07T07:00:07Z

camel/agents/react_embodied_agent.py

+ role_descriptions_dict (Optional[Dict[str, str]], optional): The
+ descriptions of the roles. (default: :obj:`None`)
+ role_descriptions_dict (Optional[Dict[str, str]], optional): A


repetitive docstring here

Wendong-Fan · 2024-04-07T07:09:30Z

camel/agents/role_assignment_agent.py

@@ -17,7 +17,7 @@
 from camel.agents import ChatAgent
 from camel.messages import BaseMessage
 from camel.prompts import TextPrompt
-from camel.types import ModelType, RoleType
+from camel.types import ModelType, RoleType, ReasonType


why added ReasonType here but not used?

Wendong-Fan · 2024-04-07T07:09:38Z

camel/agents/embodied_agent.py

@@ -23,7 +23,7 @@
 )
 from camel.messages import BaseMessage
 from camel.responses import ChatAgentResponse
-from camel.types import ModelType
+from camel.types import ModelType, ReasonType


why added ReasonType here but not used?

…cement learning framework

ZIYU-DEEP self-requested a review March 31, 2024 02:46

huyinan marked this pull request as draft March 31, 2024 19:36

Merge branch 'master' into master

8d9af9d

huyinan marked this pull request as ready for review March 31, 2024 19:49

huyinan added 5 commits April 2, 2024 18:08

Mimic example of a react agent from deductive agent

b3b5eda

Update test_react_embodied_agent.py

bcdcf97

Merge branch 'master' into master

8eaf8e3

Update react_embodied_agent.py

d6ebb2d

Merge branch 'master' of https://github.com/huyinan/camel

30c5056

Wendong-Fan requested review from Appointat and Wendong-Fan April 6, 2024 14:32

Wendong-Fan assigned huyinan Apr 6, 2024

Wendong-Fan added the enhancement New feature or request label Apr 6, 2024

Wendong-Fan linked an issue Apr 6, 2024 that may be closed by this pull request

[Feature Request] ReAct (Reasoning and Acting) Agent #490

Open

2 tasks

Wendong-Fan reviewed Apr 7, 2024

View reviewed changes

huyinan added 2 commits April 7, 2024 19:17

Adopting LLF-BENCH AS EXAMPLES

2174e56

implentation of llf-bench as a prototype example for REACT in reinfor…

8a4ea2a

…cement learning framework

Wendong-Fan marked this pull request as draft April 13, 2024 07:14

test case

6c8544b

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Addition of types #493

Addition of types #493

huyinan commented Mar 30, 2024 •

edited

coderabbitai bot commented Mar 30, 2024 •

edited

Auto Review Skipped

Chat

CodeRabbit Commands (invoked as PR comments)

CodeRabbit Configration File (`.coderabbit.yaml`)

Documentation and Community

Wendong-Fan left a comment

Wendong-Fan Apr 7, 2024

Wendong-Fan Apr 7, 2024

Wendong-Fan Apr 7, 2024

huyinan Apr 15, 2024

Wendong-Fan Apr 7, 2024

Wendong-Fan Apr 7, 2024

Wendong-Fan Apr 7, 2024

		<YOUR_ACTION> should be directly implementing the examples mentioned before. Always end <YOUR_SOLUTION> with: Next request.""")

		ACTOR_PROMPT (TextPrompt): A system prompt for the AI actor that takes actions (usually search key words)
		based on the outline of several key words from previous output from ASSISTANT. Then search results are

Addition of types #493

Are you sure you want to change the base?

Addition of types #493

Conversation

huyinan commented Mar 30, 2024 • edited

Description

Motivation and Context

Types of changes

Implemented Tasks

Checklist

coderabbitai bot commented Mar 30, 2024 • edited

Auto Review Skipped

Chat

CodeRabbit Commands (invoked as PR comments)

CodeRabbit Configration File (.coderabbit.yaml)

Documentation and Community

Wendong-Fan left a comment

Choose a reason for hiding this comment

Wendong-Fan Apr 7, 2024

Choose a reason for hiding this comment

Wendong-Fan Apr 7, 2024

Choose a reason for hiding this comment

Wendong-Fan Apr 7, 2024

Choose a reason for hiding this comment

huyinan Apr 15, 2024

Choose a reason for hiding this comment

Wendong-Fan Apr 7, 2024

Choose a reason for hiding this comment

Wendong-Fan Apr 7, 2024

Choose a reason for hiding this comment

Wendong-Fan Apr 7, 2024

Choose a reason for hiding this comment

huyinan commented Mar 30, 2024 •

edited

coderabbitai bot commented Mar 30, 2024 •

edited

CodeRabbit Configration File (`.coderabbit.yaml`)