apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-05-07 06:42:42 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

add model prefix

Browse source
This commit is contained in:
cotran 2024-10-10 15:44:15 -07:00
parent 7163de5277
commit 45aaaf09be
2 changed files with 9 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

1
arch/src/consts.rs
View file

@ -19,3 +19,4 @@ pub const REQUEST_ID_HEADER: &str = "x-request-id";
pub const ARCH_INTERNAL_CLUSTER_NAME: &str = "arch_internal";
pub const ARCH_UPSTREAM_HOST_HEADER: &str = "x-arch-upstream";
pub const ARCH_LLM_UPSTREAM_LISTENER: &str = "arch_llm_listener";
pub const ARCH_MODEL_PREFIX: &str = "Arch";

17
arch/src/stream_context.rs
View file

@ -1,9 +1,9 @@
use crate::consts::{
ARCH_FC_MODEL_NAME, ARCH_FC_REQUEST_TIMEOUT_MS, ARCH_INTERNAL_CLUSTER_NAME,
ARCH_LLM_UPSTREAM_LISTENER, ARCH_MESSAGES_KEY, ARCH_PROVIDER_HINT_HEADER, ARCH_ROUTING_HEADER,
ARCH_STATE_HEADER, ARCH_UPSTREAM_HOST_HEADER, ARC_FC_CLUSTER, CHAT_COMPLETIONS_PATH,
DEFAULT_EMBEDDING_MODEL, DEFAULT_HALLUCINATED_THRESHOLD, DEFAULT_INTENT_MODEL,
DEFAULT_PROMPT_TARGET_THRESHOLD, GPT_35_TURBO, MODEL_SERVER_NAME,
ARCH_LLM_UPSTREAM_LISTENER, ARCH_MESSAGES_KEY, ARCH_MODEL_PREFIX, ARCH_PROVIDER_HINT_HEADER,
ARCH_ROUTING_HEADER, ARCH_STATE_HEADER, ARCH_UPSTREAM_HOST_HEADER, ARC_FC_CLUSTER,
CHAT_COMPLETIONS_PATH, DEFAULT_EMBEDDING_MODEL, DEFAULT_HALLUCINATED_THRESHOLD,
DEFAULT_INTENT_MODEL, DEFAULT_PROMPT_TARGET_THRESHOLD, GPT_35_TURBO, MODEL_SERVER_NAME,
RATELIMIT_SELECTOR_HEADER_KEY, REQUEST_ID_HEADER, SYSTEM_ROLE, USER_ROLE,
};
use crate::filter_context::{EmbeddingsStore, WasmMetrics};
@ -453,7 +453,7 @@ impl StreamContext {
if messages.len() >= 2 {
let latest_assistant_message = &messages[messages.len() - 2];
if let Some(model) = latest_assistant_message.model.as_ref() {
if model.contains("Arch") {
if model.contains(ARCH_MODEL_PREFIX) {
arch_assistant = true;
}
}
@ -735,7 +735,7 @@ impl StreamContext {
if messages.len() >= 2 {
let latest_assistant_message = &messages[messages.len() - 2];
if let Some(model) = latest_assistant_message.model.as_ref() {
if model.contains("Arch") {
if model.contains(ARCH_MODEL_PREFIX) {
arch_assistant = true;
}
}
@ -746,7 +746,7 @@ impl StreamContext {
if arch_assistant {
for message in messages.iter() {
if let Some(model) = message.model.as_ref() {
if !model.contains("Arch") {
if !model.contains(ARCH_MODEL_PREFIX) {
break;
}
}
@ -756,8 +756,7 @@ impl StreamContext {
}
}
}
}
else {
} else {
user_messages = callout_context.user_message.as_ref().unwrap().clone();
}
info!("user messages: {}", user_messages);