mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
fix: add max_tokens slider to playground tools page (#1958)
# What does this PR do? This PR adds a `max_tokens` slider to playground tools page. I have found that in some instances the llama stack server throws a 500 error if the max_tokens value is not explicitly set in the agent's `sampling_params`. This PR, uses the same implementation of the `max_tokens` slider from the chat page, and includes it on the tools page. ## Test Plan 1. Attempting to call a tool without these changes results in a `500: Internal server error: An unexpected error occurred`. 2. Attempting to call a tool with these changes results in the expected output. Signed-off-by: Michael Clifford <mcliffor@redhat.com>
This commit is contained in:
parent
71ed47ea76
commit
093881071a
1 changed files with 12 additions and 3 deletions
|
@ -56,6 +56,17 @@ def tool_chat_page():
|
|||
st.subheader(f"Active Tools: 🛠 {len(active_tool_list)}")
|
||||
st.json(active_tool_list)
|
||||
|
||||
st.subheader("Chat Configurations")
|
||||
max_tokens = st.slider(
|
||||
"Max Tokens",
|
||||
min_value=0,
|
||||
max_value=4096,
|
||||
value=512,
|
||||
step=1,
|
||||
help="The maximum number of tokens to generate",
|
||||
on_change=reset_agent,
|
||||
)
|
||||
|
||||
@st.cache_resource
|
||||
def create_agent():
|
||||
return Agent(
|
||||
|
@ -63,9 +74,7 @@ def tool_chat_page():
|
|||
model=model,
|
||||
instructions="You are a helpful assistant. When you use a tool always respond with a summary of the result.",
|
||||
tools=toolgroup_selection,
|
||||
sampling_params={
|
||||
"strategy": {"type": "greedy"},
|
||||
},
|
||||
sampling_params={"strategy": {"type": "greedy"}, "max_tokens": max_tokens},
|
||||
)
|
||||
|
||||
agent = create_agent()
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue