Merge branch 'dev' into feat/add_bardapi

Farama-Foundation · Jun 5, 2023 · 04d7d07 · 04d7d07
2 parents 06c7d85 + a823b10
commit 04d7d07
Show file tree

Hide file tree

Showing 6 changed files with 90 additions and 69 deletions.
diff --git a/.gitignore b/.gitignore
@@ -50,10 +50,6 @@ coverage.xml
 *.py,cover
 .hypothesis/
 .pytest_cache/
-<<<<<<< HEAD
-cover/
-=======
->>>>>>> c8585d9ea9ca5043d8ec786b798f6c85356bc96f
 
 # Translations
 *.mo
@@ -76,10 +72,7 @@ instance/
 docs/_build/
 
 # PyBuilder
-<<<<<<< HEAD
 .pybuilder/
-=======
->>>>>>> c8585d9ea9ca5043d8ec786b798f6c85356bc96f
 target/
 
 # Jupyter Notebook
@@ -90,13 +83,9 @@ profile_default/
 ipython_config.py
 
 # pyenv
-<<<<<<< HEAD
 #   For a library or package, you might want to ignore these files since the code is
 #   intended to run in multiple environments; otherwise, check them in:
-# .python-version
-=======
 .python-version
->>>>>>> c8585d9ea9ca5043d8ec786b798f6c85356bc96f
 
 # pipenv
 #   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
@@ -105,7 +94,6 @@ ipython_config.py
 #   install all needed dependencies.
 #Pipfile.lock
 
-<<<<<<< HEAD
 # poetry
 #   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
 #   This is especially recommended for binary packages to ensure reproducibility, and is more
@@ -122,9 +110,6 @@ ipython_config.py
 .pdm.toml
 
 # PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
-=======
-# PEP 582; used by e.g. github.com/David-OConnor/pyflow
->>>>>>> c8585d9ea9ca5043d8ec786b798f6c85356bc96f
 __pypackages__/
 
 # Celery stuff
@@ -159,7 +144,6 @@ venv.bak/
 dmypy.json
 
 # Pyre type checker
-<<<<<<< HEAD
 .pyre/
 
 # pytype static type analyzer
@@ -173,11 +157,9 @@ cython_debug/
 #  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
 #  and can be added to the global gitignore or merged into this file.  For a more nuclear
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
-#.idea/
-=======
+.idea/
+
 .DS_Store
-.pyre/
-.idea
 hf-spaces/
 etc/
->>>>>>> c8585d9ea9ca5043d8ec786b798f6c85356bc96f
+.conda
diff --git a/README.md b/README.md
@@ -63,13 +63,26 @@ To use GPT-3 as an LLM agent, set your OpenAI API key:
 export OPENAI_API_KEY="your_api_key_here"
 ```
 
+#### Optional Dependencies
+
+By default `pip install chatarena` will only install dependencies necessary for ChatArena's core functionalities.
+You can install optional dependencies with the following commands:
+```bash
+pip install chatarena[all_backends] # install dependencies for all supported backends: anthropic, cohere, huggingface, etc.
+pip install chatarena[all_envs]     # install dependencies for all environments, such as pettingzoo
+pip install chatarena[all]          # install all optional dependencies for full functionality
+```
+
 ### Launch the Demo Locally
 
 The quickest way to see ChatArena in action is via the demo Web UI.
-To launch the demo on your local machine, you first need to git clone the repository and install it from source
-(see above instruction). Then run the following command in the root directory of the repository:
+To launch the demo on your local machine, you first pip install chatarena with extra gradio dependency, then git clone
+this repository to your local folder, and finally call the `app.py` in the root directory of the repository:
 
 ```shell
+pip install chatarena[gradio]
+git clone https://github.com/chatarena/chatarena.git
+cd chatarena
 gradio app.py
 ```
 
@@ -82,10 +95,12 @@ This will launch a demo server for ChatArena, and you can access it from your br
 Check out this video to learn how to use Web UI: [![Webui demo video](https://img.shields.io/badge/WebUI%20Demo%20Video-Vimeo-blue?logo=vimeo)](https://vimeo.com/816979419)
 
 ## For Developers
+
 For a introduction to the ChatArena framework, please refer to [this document](docs/devdoc/design.md).
-Here we provide a compact guide on minimal setup to run the game and some general advice on customization. 
+Here we provide a compact guide on minimal setup to run the game and some general advice on customization.
 
 ### Key Concepts
+
 1. **Arena**: Arena encapsulates an environment and a collection of players. It drives the main loop of the game and
    provides HCI utilities like webUI, CLI, configuration loading and data storage.
 2. **Environment**: The environment stores the game state and executes game logics to make transitions between game
@@ -97,6 +112,7 @@ Here we provide a compact guide on minimal setup to run the game and some genera
    mapping from observations to actions.
 
 ### Run the Game with Python API
+
 Load `Arena` from a config file -- here we use `examples/nlp-classroom-3players.json` in this repository as an example:
 
 ```python
@@ -112,7 +128,8 @@ arena.launch_cli()
 
 Check out this video to learn how to use
 CLI: [![cli demo video](https://img.shields.io/badge/CLI%20Demo%20Video-Vimeo-blue?logo=vimeo)](https://vimeo.com/816989884)
-A more detailed guide about how to run the main interaction loop with finer-grained control can be found [here](docs/devdoc/mainloop.md)
+A more detailed guide about how to run the main interaction loop with finer-grained control can be
+found [here](docs/devdoc/mainloop.md)
 
 ### General Custimization Advice
 
@@ -196,7 +213,8 @@ The objective in the game depends on the role of the player:
 A two-player chess game environment that uses the PettingZoo Chess environment.
 
 ### [PettingZooTicTacTeo](chatarena/environments/pettingzoo_tictactoe.py)
-A two-player tic-tac-toe game environment that uses the PettingZoo TicTacToe environment. Differing from the 
+
+A two-player tic-tac-toe game environment that uses the PettingZoo TicTacToe environment. Differing from the
 `Moderator Conversation` environment, this environment is driven by hard-coded rules rather than a LLM moderator.
 
 ## Contributing

diff --git a/chatarena/pettingzoo_compatibility.py b/chatarena/pettingzoo_compatibility.py
@@ -15,6 +15,7 @@
 
 CHAR_SET = string.printable
 
+
 class PettingZooCompatibilityV0(pettingzoo.AECEnv):
     """This compatibility wrapper converts a ChatArena environment into a PettingZoo environment.
 
@@ -28,14 +29,14 @@ class PettingZooCompatibilityV0(pettingzoo.AECEnv):
     }
 
     def __init__(
-        self,
-        env: chatarena.arena.Arena | None = None,
-        arena_name: str | None = None,
-        string_observation: bool | None = True,
-        max_turns: int | None = 25,
-        render_mode: str | None = None,
+            self,
+            env: chatarena.arena.Arena | None = None,
+            arena_name: str | None = None,
+            string_observation: bool | None = True,
+            max_turns: int | None = 25,
+            render_mode: str | None = None,
     ):
-        """Wrapper to convert a OpenSpiel environment into a PettingZoo environment.
+        """Wrapper to convert a ChatArena environment into a PettingZoo environment.
 
         Args:
             env (chatarena.arena.Arena): chatarena arena to wrap
@@ -52,12 +53,11 @@ def __init__(
         else:
             raise ValueError("Arena not specified, please us env or arena_name arguments.")
 
-        self._env.reset() # this resets the underlying arena as well as each player
+        self._env.reset()  # this resets the underlying arena as well as each player
 
         self.possible_agents = list(self._env.name_to_player.keys())
         self.name_to_player_mapping = self._env.name_to_player
 
-
         self.string_observation = string_observation
         self.max_turns = max_turns
         self.render_mode = render_mode
@@ -67,7 +67,6 @@ def __init__(
         self.rewards = {}
         self.infos = {a: {} for a in self.possible_agents}
 
-
     @functools.lru_cache(maxsize=None)
     def observation_space(self, agent: AgentID):
         """observation_space.
@@ -128,12 +127,13 @@ def observe(self, agent: AgentID) -> ObsType:
         Returns:
             observation
         """
-        messages = self._env.environment.get_observation(agent) # this will only return the messages this agent can see
+        messages = self._env.environment.get_observation(agent)  # this will only return the messages this agent can see
         if len(messages) > 0:
             self.current_turn = messages[-1].turn
         else:
             self.current_turn = 0
-        new_messages = [m for m in messages if m.turn == self.current_turn] # we only send the current timestep messages
+        new_messages = [m for m in messages if
+                        m.turn == self.current_turn]  # we only send the current timestep messages
 
         # string observation
         if self.string_observation == True:
@@ -149,7 +149,6 @@ def observe(self, agent: AgentID) -> ObsType:
 
         return observation
 
-
     def close(self):
         """close."""
         pass
@@ -161,7 +160,8 @@ def _unravel_timestep(self, timestep: chatarena.arena.TimeStep):
             self.current_turn = messages[-1].turn
         else:
             self.current_turn = 0
-        new_messages = [m for m in messages if m.turn == self.current_turn]  # we only send the current timestep messages
+        new_messages = [m for m in messages if
+                        m.turn == self.current_turn]  # we only send the current timestep messages
 
         # string observation
         if self.string_observation == True:
@@ -173,7 +173,6 @@ def _unravel_timestep(self, timestep: chatarena.arena.TimeStep):
         else:
             observation = {m.agent_name: m.content for m in new_messages}
 
-
         # get rewards
         rewards = timestep.reward
 
@@ -186,15 +185,16 @@ def _unravel_timestep(self, timestep: chatarena.arena.TimeStep):
         # get info
         player_idx = self.possible_agents.index(self.agent_selection)
         player_obj = self._env.players[player_idx]
-        info = {"turn": self.current_turn, "global_prompt": player_obj.global_prompt, "agent_desc": player_obj.role_desc}
+        info = {"turn": self.current_turn, "global_prompt": player_obj.global_prompt,
+                "agent_desc": player_obj.role_desc}
 
         return observation, rewards, termination, truncation, info
 
     def reset(
-        self,
-        return_info: bool | None = False,
-        seed: int | None = None,
-        options: dict | None = None,
+            self,
+            return_info: bool | None = False,
+            seed: int | None = None,
+            options: dict | None = None,
     ):
         """reset.
 
@@ -239,8 +239,8 @@ def step(self, action: str):
             action (str): action
         """
         if (
-            self.terminations[self.agent_selection]
-            or self.truncations[self.agent_selection]
+                self.terminations[self.agent_selection]
+                or self.truncations[self.agent_selection]
         ):
             return self._was_dead_step(action)
 
@@ -262,6 +262,3 @@ def step(self, action: str):
 
         if self.render_mode == "human":
             self.render()
-
-
-
diff --git a/docs/tutorials/pettingzoo_wrapper.md b/docs/tutorials/pettingzoo_wrapper.md
@@ -22,8 +22,8 @@ print("ACT SPACE: ", env.action_space(env.agent_selection))
 3. **Run the environment**
 ```python
 agent_player_mapping = {agent: player_obj
-                         for agent in env.possible_agents
-                         for player_obj in env._env.players}
+                        for agent in env.possible_agents
+                        for player_obj in env._env.players}
 
 for agent in env.agent_iter():
     observation, reward, termination, truncation, info = env.last()

diff --git a/pyproject.toml b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "chatarena"
-version = "0.1.10"
+version = "0.1.10.2"
 authors = [
     { name = "Yuxiang Wu", email = "yuxiang.cs@gmail.com" },
 ]
@@ -19,4 +19,14 @@ classifiers = [
 
 [project.urls]
 "Homepage" = "https://github.com/chatarena/chatarena"
-"Bug Tracker" = "https://github.com/chatarena/chatarena/issues"
+"Bug Tracker" = "https://github.com/chatarena/chatarena/issues"
+
+[project.optional-dependencies]
+anthropic = ["anthropic>=0.2.8"]
+cohere = ["cohere>=4.3.1"]
+huggingface = ["transformers>=4.27.4"]
+gradio = ["gradio==3.20.0"]
+pettingzoo = ["pettingzoo==1.23.0", "chess==1.9.4"]
+all_backends = ["anthropic>=0.2.8", "cohere>=4.3.1", "transformers>=4.27.4"]
+all_envs = ["pettingzoo==1.23.0", "chess==1.9.4"]
+all = ["anthropic>=0.2.8", "cohere>=4.3.1", "transformers>=4.27.4", "gradio==3.20.0", "pettingzoo==1.23.0", "chess==1.9.4"]
diff --git a/setup.py b/setup.py
@@ -1,27 +1,31 @@
 from setuptools import setup, find_packages
 
-_deps = [
-    "openai==0.27.2",
-    "anthropic==0.2.8",
-    "cohere==4.3.1",
-    "transformers>=4.27.4",
+with open("README.md", "r") as f:
+    long_description = f.read()
+
+base_requirements = [
+    "openai>=0.27.2",
     "tenacity==8.2.2",
-    "gradio==3.20.0",
     "rich==13.3.3",
     "prompt_toolkit==3.0.38",
-    "pettingzoo==1.23.0",
-    "chess==1.9.4",
-    "bardapi==0.1.11",
+
 ]
+anthropic_requirements = ["anthropic>=0.2.8"]
+cohere_requirements = ["cohere>=4.3.1"]
+hf_requirements = ["transformers>=4.27.4"]
+bard_requirements = ["bardapi==0.1.11"]
+gradio_requirements = ["gradio==3.20.0"]
+pettingzoo_requirements = ["pettingzoo==1.23.0", "chess==1.9.4"]
 
-with open("README.md", "r") as f:
-    long_description = f.read()
 
-requirements = _deps
+all_backends = anthropic_requirements + cohere_requirements + hf_requirements + bard_requirements
+all_envs = pettingzoo_requirements
+all_requirements = anthropic_requirements + cohere_requirements + hf_requirements + \
+                   gradio_requirements + pettingzoo_requirements + bard_requirements
 
 setup(
     name="chatarena",
-    version="0.1.10",
+    version="0.1.10.2",
     author="Yuxiang Wu",
     author_email="yuxiang.cs@gmail.com",
     description="",
@@ -35,5 +39,15 @@
         "Topic :: Scientific/Engineering :: Artificial Intelligence",
     ],
     python_requires=">=3.7",
-    install_requires=requirements,
+    install_requires=base_requirements,
+    extras_require={
+        "anthropic": anthropic_requirements,
+        "cohere": cohere_requirements,
+        "huggingface": hf_requirements,
+        "bard": bard_requirements,
+        "pettingzoo": pettingzoo_requirements,
+        "gradio": gradio_requirements,
+        "all_backends": all_backends,
+        "all": all_requirements,
+    },
 )