aljaz/Auto-GPT
1
0
Fork 0
mirror of https://github.com/aljazceru/Auto-GPT.git synced 2026-01-05 15:24:23 +01:00
Code Issues Packages Projects Releases Wiki Activity

windows docs make workspace if not there (#25)

Browse Source 
* windows docs make workspace if not there

* small fixes
This commit is contained in:
Douglas Schonholtz
2023-04-22 19:17:28 -04:00
committed by GitHub
parent ef5c4f8a11
commit b8c7c05dd5
2 changed files with 24 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
README.md
View File

@@ -13,54 +13,53 @@ documented.
Clone the repo with:
`git clone git@github.com:Significant-Gravitas/Auto-GPT-Benchmarks.git`
`cd Auto-GPT-Benchmarks`
git clone git@github.com:Significant-Gravitas/Auto-GPT-Benchmarks.git
cd Auto-GPT-Benchmarks
Create a venv with
`python3.9 -m venv venv`
python3.9 -m venv venv
Activate it with
On MaxOS/Linux Activate it with
`source venv/bin/activate`
source venv/bin/activate
On Windows:
venv/scripts/activate
Install the requirements with:
`pip install -r requirements.txt`
pip install -r requirements.txt
If you haven't already clone the AutoGPT repo somewhere else on your machine.
DO NOT CLONE IT INTO A SUBDIR OF THIS REPO.
`cd somewhere/else`
`git clone git@github.com:Significant-Gravitas/Auto-GPT.git`
cd somewhere/else
git clone git@github.com:Significant-Gravitas/Auto-GPT.git
cd Auto-GPT
git checkout stable # Or the branch you want to benchmark
You will need to update the .env file in the Auto-GPT repo to have your OpenAI api key. The file in question is at:
You will need to update the .env file in the Auto-GPT repo to have your OpenAI api key. The file in question is at. This should becopied from the .env.template as described in the Auto-GPT README.md
`Auto-GPT/.env`
Auto-GPT/.env
Finally, we assume you have a docker container built from the Dockerfile in the Auto-GPT repo.
Build this with:
`cd Auto-GPT`
`docker build -t autogpt .`
If you want to run with redis as your memory system, you can stand up a redis image in the AutoGPT repo with
`docker compose up`
Then you will need to adjust some variables in your .env file to use the redis memory backend.
See the AutoGPT docs on how to do that.
cd Auto-GPT
docker build -t autogpt .
Run your first eval with:
`cd Auto-GPT-Benchmarks`
`python3 auto_gpt_benchmarking test-match --auto-gpt-path /your/path/to/Auto-GPT`
cd Auto-GPT-Benchmarks
python3 auto_gpt_benchmarking test-match --auto-gpt-path /your/path/to/Auto-GPT
You should only need to use the --auto-gpt-path flag the first time you run it. Afterwards, that will be saved in
`auto_gpt_benchmarking/completion_fns/auto_gpt_completion_fn.yaml`.
auto_gpt_benchmarking/completion_fns/auto_gpt_completion_fn.yaml.
To see a full list of available flags you can use run `python3 -m auto_gpt_benchmarking --help`
Some of these are inherited from the openAI evals framework and do not work quite as intended as they are not applicable

3
auto_gpt_benchmarking/AutoGPTAgent.py
View File

@@ -108,6 +108,9 @@ class AutoGPTAgent:
def __init__(self, prompt, auto_gpt_path: str):
self.auto_gpt_path = Path(auto_gpt_path)
self.auto_workspace = self.auto_gpt_path / "auto_gpt_workspace"
# if the workspace doesn't exist, create it
if not self.auto_workspace.exists():
self.auto_workspace.mkdir()
self.prompt_file = self.auto_workspace / "prompt.txt"
self.output_file = self.auto_workspace / "output.txt"
self.file_logger = self.auto_workspace / "file_logger.txt"