From 60cadf3e8a0c7c8c597a42b26153831d61e2249b Mon Sep 17 00:00:00 2001
From: cotran <cotran2@utexas.edu>
Date: Thu, 10 Oct 2024 15:37:08 -0700
Subject: [PATCH] add history of messages

---
 arch/src/consts.rs         | 2 +-
 arch/src/stream_context.rs | 3 ++-
 model_server/app/main.py   | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/src/consts.rs b/arch/src/consts.rs
index 32172002..f4aae904 100644
--- a/arch/src/consts.rs
+++ b/arch/src/consts.rs
@@ -1,7 +1,7 @@
 pub const DEFAULT_EMBEDDING_MODEL: &str = "katanemo/bge-large-en-v1.5";
 pub const DEFAULT_INTENT_MODEL: &str = "katanemo/bart-large-mnli";
 pub const DEFAULT_PROMPT_TARGET_THRESHOLD: f64 = 0.8;
-pub const DEFAULT_HALLUCINATED_THRESHOLD: f64 = 0.1;
+pub const DEFAULT_HALLUCINATED_THRESHOLD: f64 = 0.25;
 pub const RATELIMIT_SELECTOR_HEADER_KEY: &str = "x-arch-ratelimit-selector";
 pub const SYSTEM_ROLE: &str = "system";
 pub const USER_ROLE: &str = "user";
diff --git a/arch/src/stream_context.rs b/arch/src/stream_context.rs
index bdf80885..c73728d8 100644
--- a/arch/src/stream_context.rs
+++ b/arch/src/stream_context.rs
@@ -756,7 +756,8 @@ impl StreamContext {
                         }
                     }
                 }
-            } else {
+            }
+            else {
                 user_messages = callout_context.user_message.as_ref().unwrap().clone();
             }
             info!("user messages: {}", user_messages);
diff --git a/model_server/app/main.py b/model_server/app/main.py
index 82bbeb50..a80b04c5 100644
--- a/model_server/app/main.py
+++ b/model_server/app/main.py
@@ -179,7 +179,7 @@ async def hallucination(req: HallucinationRequest, res: Response):
     """
     Take input as text and return the prediction of hallucination for each parameter
     """
-
+    logger.info(f"hallucination request: {req}")
     if req.model != zero_shot_model["model_name"]:
         raise HTTPException(status_code=400, detail="unknown model: " + req.model)