Skip to content

feat: add configurable allow_parallel_tool_calls to FunctionAgent #18829

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

Merged
merged 2 commits into from
May 26, 2025
Merged

feat: add configurable allow_parallel_tool_calls to FunctionAgent #18829

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4e10085
feat: add configurable allow_parallel_tool_calls to FunctionAgent
May 23, 2025
b77272a
nit
logan-markewich May 26, 2025
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
9 changes: 7 additions & 2 deletions llama-index-core/llama_index/core/agent/workflow/function_agent.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,7 @@
ToolCallResult,
)
from llama_index.core.base.llms.types import ChatResponse
from llama_index.core.bridge.pydantic import BaseModel
from llama_index.core.bridge.pydantic import BaseModel, Field
from llama_index.core.llms import ChatMessage
from llama_index.core.memory import BaseMemory
from llama_index.core.tools import AsyncBaseTool
Expand All @@ -20,6 +20,9 @@ class FunctionAgent(SingleAgentRunnerMixin, BaseWorkflowAgent):
"""Function calling agent implementation."""

scratchpad_key: str = "scratchpad"
allow_parallel_tool_calls: bool = Field(
default=True, description="If True, the agent will call multiple tools in parallel. If False, the agent will call tools sequentially."
)

async def take_step(
self,
Expand All @@ -40,7 +43,9 @@ async def take_step(
)

response = await self.llm.astream_chat_with_tools( # type: ignore
tools, chat_history=current_llm_input, allow_parallel_tool_calls=True
tools=tools,
chat_history=current_llm_input,
allow_parallel_tool_calls=self.allow_parallel_tool_calls,
)
# last_chat_response will be used later, after the loop.
# We initialize it so it's valid even when 'response' is empty
Expand Down