agent: add sampling parameters (temperature, top_p, top_k)
Move temperature from a per-call parameter to an Agent field, add top_p and top_k. All three are sent to the API via a new SamplingParams struct, displayed on the F5 thalamus screen. Defaults: temperature=0.6, top_p=0.95, top_k=20 (Qwen3.5 defaults). Also adds top_p and top_k to ChatRequest so they're sent in the API payload. Previously only temperature was sent. UI controls for adjusting these at runtime are not yet implemented. Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
parent
22f955ad9f
commit
dd009742ef
7 changed files with 53 additions and 8 deletions
|
|
@ -76,12 +76,17 @@ pub async fn call_api_with_tools(
|
|||
let mut msg_opt = None;
|
||||
let mut usage_opt = None;
|
||||
for attempt in 0..5 {
|
||||
let sampling = crate::agent::api::SamplingParams {
|
||||
temperature: temperature.unwrap_or(0.6),
|
||||
top_p: 0.95,
|
||||
top_k: 20,
|
||||
};
|
||||
match client.chat_completion_stream_temp(
|
||||
&messages,
|
||||
Some(&tool_defs),
|
||||
&ui_tx,
|
||||
&reasoning,
|
||||
temperature,
|
||||
sampling,
|
||||
Some(priority),
|
||||
).await {
|
||||
Ok((msg, usage)) => {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue