EvalNames with dates for the eval run filename and compatibility with 0.3.0 (#26)

* EvalNames with dates and the eval run

* Ignore .idea files, update readme to use 3.10, updates for 0.3.0

.gitignore

@@ -129,3 +129,5 @@ dmypy.json
 .pyre/
 
 /data
+
+/.idea

README.md

@@ -18,7 +18,7 @@ Clone the repo with:
 
 Create a venv with
 
-    python3.9 -m venv venv
+    python3.10 -m venv venv
 
 
 On MaxOS/Linux Activate it with 

auto_gpt_benchmarking/AutoGPTAgent.py

@@ -80,15 +80,17 @@ class AutoGPTAgent:
         envs = [
             f"{line.strip()}" for line in open(
                 env_file
-            ) if line.strip() != "" and line.strip()[0] != "#" and line.strip()[0] != "\n"]
+            ) if line.strip() != "" and line.strip()[0] != "#" and line.strip()[0] != "\n" and "=" in line and not line.startswith('SMART_LLM_MODEL')]
+
+        envs.append("SMART_LLM_MODEL=gpt-3.5-turbo")
 
         self.container = client.containers.run(
             image="autogpt",
-            command="--continuous -C '/home/appuser/auto_gpt_workspace/ai_settings.yaml'",
+            command="--continuous -C '/app/auto_gpt_workspace/ai_settings.yaml' --skip-news",
             environment=envs,
             volumes={
-                self.auto_workspace: {"bind": "/home/appuser/auto_gpt_workspace", "mode": "rw"},
-                f"{self.auto_gpt_path}/autogpt": {"bind": "/home/appuser/autogpt", "mode": "rw"},
+                self.auto_workspace: {"bind": "/app/auto_gpt_workspace", "mode": "rw"},
+                f"{self.auto_gpt_path}/autogpt": {"bind": "/app/autogpt", "mode": "rw"},
             },
             stdin_open=True,
             tty=True,
@@ -103,11 +105,12 @@ class AutoGPTAgent:
         """
         while True:
             if self.output_file.exists():
+                print("Output file exists")
                 return self.output_file.read_text()
 
     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"
+        self.auto_workspace = self.auto_gpt_path / "autogpt" / "auto_gpt_workspace"
         # if the workspace doesn't exist, create it
         if not self.auto_workspace.exists():
             self.auto_workspace.mkdir()

auto_gpt_benchmarking/__main__.py

@@ -56,8 +56,7 @@ def parse_args() -> argparse.Namespace:
         "--visible", action=argparse.BooleanOptionalAction, default=None)
     parser.add_argument("--seed", type=int, default=20220722)
     parser.add_argument("--user", type=str, default="")
-    parser.add_argument("--record_path", type=str, default=str(Path(
-        __file__).parent.parent / "data" / f"eval-{datetime.now().strftime('%Y%m%d-%H%M%S')}.jsonl"))
+    parser.add_argument("--record_path", type=str, default=None)
     parser.add_argument(
         "--log_to_file", type=str, default=None,  # default=str(
         #   Path(__file__).parent.parent / "data" / "log" / "log.txt"
@@ -133,6 +132,9 @@ if __name__ == "__main__":
     # Obviously, a top level import would be better. This allows us to set the API key with the env file, as it gets
     # set in the evaluator. We can't set it before the import because the import will fail without an API key.
     from auto_gpt_benchmarking.Evaluator import Evaluator, OAIRunArgs
+    if args.record_path is None:
+        args.record_path = str(Path(
+            __file__).parent.parent / "data" / f"eval-{args.eval}-{datetime.now().strftime('%Y%m%d-%H%M%S')}.jsonl")
     run_args = OAIRunArgs(
         completion_fn=args.completion_fn,
         eval=args.eval,