Upload 16 files

Planner_JarvisFlow.yaml

@@ -49,7 +49,6 @@ subflows_config:
                 Here are some criteria you should consider in order to write a good plan:
                   1. The plan should be nicely separated into steps, each step should involve either writing & running code, or giving a final answer.
                   2. Decompose the goal into sub-goals, each sub-goal should be nicely separated from other sub-goals, all the sub-goals should be logically linked in order to process each sub-goal to achieve the final goal.
-                  3. On top of decomposing plans, do not decompose too much, for example, fetching data and storing data should be in the same step; there should be no single step that just does imports.
                 
                 Performance Evaluation:
                   1. Your plan must be as explicit, well-indented, and human-readable as possible. 

run_Jarvis.py

@@ -100,9 +100,9 @@ if __name__ == "__main__":
     # ~~~ instantiating the flow and input data ~~~
     JarvisFlow = hydra.utils.instantiate(cfg, _recursive_=False, _convert_="partial")
     input_data = {
-        #"goal": "define a calculator that supports addition and multiplication on complex numbers",
-        #"goal": "define a calculator that supports addition on complex numbers"
-        "goal": "fetch google's stock prices using yfinance for the last 6 months and print the first 10 entries"
+        "goal": "fetch a random joke from the internet and send the joke"
+                "from haolongli_neko@outlook.com to leonardli2333@gmail.com, you can find the password of the sender "
+                "email in the environment variable 'EMAIL_PASSWORD'"
     }
     input_message = InputMessage.build(
         data_dict=input_data,