Skip to content

Fix potential crashes due to uninitialized variables in Gemini and ConversableAgent #7197

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
RinZ27 wants to merge 1 commit into
base: fix_fs
Choose a base branch
from
+6 −1
Open

Fix potential crashes due to uninitialized variables in Gemini and ConversableAgent #7197

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions autogen/agentchat/conversable_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2229,6 +2229,7 @@ def execute_function(self, func_call, verbose: bool = False) -> Tuple[bool, Dict
func = self._function_map.get(func_name, None)

is_exec_success = False
arguments = None
if func is not None:
# Extract arguments from a json-like string and put it into a dict.
input_string = self._format_json_str(func_call.get("arguments", "{}"))
Expand Down Expand Up @@ -2288,6 +2289,7 @@ async def a_execute_function(self, func_call):
func = self._function_map.get(func_name, None)

is_exec_success = False
arguments = None
if func is not None:
# Extract arguments from a json-like string and put it into a dict.
input_string = self._format_json_str(func_call.get("arguments", "{}"))
Expand Down
5 changes: 4 additions & 1 deletion autogen/oai/gemini.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -176,6 +176,9 @@ def create(self, params: Dict) -> ChatCompletion:
if n_response > 1:
warnings.warn("Gemini only supports `n=1` for now. We only generate one response.", UserWarning)

ans = None
prompt_tokens = completion_tokens = 0

if "vision" not in model_name:
# A. create and call the chat model.
gemini_messages = self._oai_messages_to_gemini_messages(messages)
Expand Down Expand Up @@ -214,7 +217,7 @@ def create(self, params: Dict) -> ChatCompletion:

prompt_tokens = model.count_tokens(chat.history[:-1]).total_tokens
completion_tokens = model.count_tokens(ans).total_tokens
elif model_name == "gemini-pro-vision":
else:
# B. handle the vision model
if self.use_vertexai:
model = GenerativeModel(
Expand Down