Integrate Arch-Function-Chat (#449)

This commit is contained in:
Shuguang Chen 2025-04-15 14:39:12 -07:00 committed by GitHub
parent f31aa59fac
commit 7d4b261a68
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 558 additions and 603 deletions

View file

@ -13,8 +13,11 @@ pub const MESSAGES_KEY: &str = "messages";
pub const ARCH_PROVIDER_HINT_HEADER: &str = "x-arch-llm-provider-hint";
pub const CHAT_COMPLETIONS_PATH: [&str; 2] = ["/v1/chat/completions", "/openai/v1/chat/completions"];
pub const HEALTHZ_PATH: &str = "/healthz";
pub const ARCH_STATE_HEADER: &str = "x-arch-state";
pub const ARCH_FC_MODEL_NAME: &str = "Arch-Function-1.5B";
pub const X_ARCH_STATE_HEADER: &str = "x-arch-state";
pub const X_ARCH_API_RESPONSE: &str = "x-arch-api-response-message";
pub const X_ARCH_TOOL_CALL: &str = "x-arch-tool-call-message";
pub const X_ARCH_FC_MODEL_RESPONSE: &str = "x-arch-fc-model-response";
pub const ARCH_FC_MODEL_NAME: &str = "Arch-Function";
pub const REQUEST_ID_HEADER: &str = "x-request-id";
pub const TRACE_PARENT_HEADER: &str = "traceparent";
pub const ARCH_INTERNAL_CLUSTER_NAME: &str = "arch_internal";

View file

@ -50,8 +50,7 @@ pub trait Client: Context {
) -> Result<u32, ClientError> {
debug!(
"dispatching http call with args={:?} context={:?}",
call_args,
call_context
call_args, call_context
);
match self.dispatch_http_call(

View file

@ -101,9 +101,7 @@ impl RatelimitMap {
) -> Result<(), Error> {
debug!(
"Checking limit for provider={}, with selector={:?}, consuming tokens={:?}",
provider,
selector,
tokens_used
provider, selector, tokens_used
);
let provider_limits = match self.datastore.get(&provider) {

View file

@ -1,4 +1,4 @@
use log::{debug};
use log::debug;
#[allow(dead_code)]
pub fn token_count(model_name: &str, text: &str) -> Result<usize, String> {