This repository has been archived by the owner on Jun 9, 2024. It is now read-only.
Skeleton-plugin Code structure helper #180
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Codecov ReportPatch coverage has no change and project coverage change:
Additional details and impacted files@@ Coverage Diff @@
## master #180 +/- ##
==========================================
- Coverage 58.52% 53.92% -4.61%
==========================================
Files 36 38 +2
Lines 2122 2303 +181
Branches 222 244 +22
==========================================
Hits 1242 1242
- Misses 858 1039 +181
Partials 22 22
☔ View full report in Codecov by Sentry. |
ntindle
reviewed
May 25, 2023
| @@ -78,6 +78,7 @@ You can also see the plugins here: | |||
| | Twitter | Auto-GPT is capable of retrieving Twitter posts and other related content by accessing the Twitter platform via the v1.1 API using Tweepy. | [autogpt_plugins/twitter](https://github.com/Significant-Gravitas/Auto-GPT-Plugins/tree/master/src/autogpt_plugins/twitter) | | |||
| | Wikipedia Search | This allows Auto-GPT to use Wikipedia directly. | [autogpt_plugins/wikipedia_search](https://github.com/Significant-Gravitas/Auto-GPT-Plugins/tree/master/src/autogpt_plugins/wikipedia_search) | | |||
| | WolframAlpha Search | This allows AutoGPT to use WolframAlpha directly. | [autogpt_plugins/wolframalpha_search](https://github.com/Significant-Gravitas/Auto-GPT-Plugins/tree/master/src/autogpt_plugins/wolframalpha_search)| | |||
| | Skeleton Plugin | This allows AutoGPT to use WolframAlpha directly. | [autogpt_plugins/skeleton](https://github.com/Significant-Gravitas/Auto-GPT-Plugins/tree/master/src/autogpt_plugins/skeleton)| | |||
There was a problem hiding this comment.
Put this in the right place alphabetically
ntindle
reviewed
May 25, 2023
ntindle
reviewed
May 25, 2023
| messages=[ | ||
| { | ||
| "role": "system", | ||
| "content": f"You are an assistant that generates descriptions of Python code files. Please describe the following file: {file}", |
There was a problem hiding this comment.
extract this to a easily editable file
SaViGnAnO
reviewed
May 26, 2023
| files = [file for file in files if file not in code_structure] | ||
|
|
||
| model = os.getenv("SKELETON_MODEL", os.getenv("FAST_LLM_MODEL", "gpt-3.5-turbo")) | ||
| max_tokens = os.getenv("SKELETONM_TOKEN_LIMIT", os.getenv("FAST_TOKEN_LIMIT", 1500)) |
There was a problem hiding this comment.
os.getenv("SKELETONM_TOKEN_LIMIT" I think you have a typo here in the variable name
There was a problem hiding this comment.
oh didn't notice, apparently thats why the results were so short
ntindle
suggested changes
May 30, 2023
|
|
||
| By default, the plugin uses whatever your `FAST_LLM_MODEL` environment variable is set to. If none is set it will fall back to `gpt-3.5-turbo`. You can set it individually to a different model by setting the environment variable `SKELETON_MODEL` to the model you want to use (example: `gpt-4`). | ||
|
|
||
| Similarly, the token limit defaults to the `FAST_TOKEN_LIMIT` environment variable. If none is set it will fall back to `1500`. You can set it individually to a different limit for the plugin by setting `SKELETON_TOKEN_LIMIT` to the desired limit (example: `7500`). |
There was a problem hiding this comment.
I'd probably encourage smart over fast, but that's not super clear the results of that
| content: str | ||
|
|
||
|
|
||
| class SkeletonPlugin(AutoGPTPluginTemplate): |
There was a problem hiding this comment.
CodeStructurePlugin seems better and more clear, lets use that everywhere if possible
| model = os.getenv("SKELETON_MODEL", os.getenv("FAST_LLM_MODEL", "gpt-3.5-turbo")) | ||
| max_tokens = os.getenv("SKELETONM_TOKEN_LIMIT", os.getenv("FAST_TOKEN_LIMIT", 1500)) | ||
| temperature = os.getenv("SKELETON_TEMPERATURE", os.getenv("TEMPERATURE", 0.5)) | ||
| prompt_prefix = os.getenv("SKELETON_PROMPT_PREFIX", os.getenv("PROMPT_PREFIX", "You are an assistant that generates descriptions of Python code files. Please describe the following file: {file}")) |
There was a problem hiding this comment.
make the env more clearly tied to the function
|
Will continue in a few days, I got flooded with work outside of this plugin. |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
note: this contains also the telegram changes from the other pr, I am working on both.
This plugin is based on the planner and allows auto-GPT to write and edit coding projects now.