From 817601872f4c626c8ccfac6692e7c9397091784f Mon Sep 17 00:00:00 2001
From: Debanjum <debanjum@gmail.com>
Date: Mon, 18 Nov 2024 16:22:32 -0800
Subject: [PATCH] Update default offline models enabled

---
 src/khoj/processor/conversation/utils.py | 11 ++++++-----
 src/khoj/utils/constants.py              |  3 ++-
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/src/khoj/processor/conversation/utils.py b/src/khoj/processor/conversation/utils.py
index 73ef0d95..91ba3c72 100644
--- a/src/khoj/processor/conversation/utils.py
+++ b/src/khoj/processor/conversation/utils.py
@@ -49,8 +49,6 @@ except ImportError:
 
 model_to_prompt_size = {
     # OpenAI Models
-    "gpt-3.5-turbo": 12000,
-    "gpt-4-turbo-preview": 20000,
     "gpt-4o": 20000,
     "gpt-4o-mini": 20000,
     "o1-preview": 20000,
@@ -60,11 +58,14 @@ model_to_prompt_size = {
     "gemini-1.5-pro": 20000,
     # Anthropic Models
     "claude-3-5-sonnet-20240620": 20000,
-    "claude-3-opus-20240229": 20000,
+    "claude-3-5-haiku-20241022": 20000,
     # Offline Models
-    "TheBloke/Mistral-7B-Instruct-v0.2-GGUF": 3500,
-    "NousResearch/Hermes-2-Pro-Mistral-7B-GGUF": 3500,
     "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF": 20000,
+    "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF": 20000,
+    "bartowski/Llama-3.2-3B-Instruct-GGUF": 20000,
+    "bartowski/gemma-2-9b-it-GGUF": 6000,
+    "bartowski/gemma-2-2b-it-GGUF": 6000,
+    "Qwen/Qwen2.5-14B-Instruct-GGUF": 20000,
 }
 model_to_tokenizer: Dict[str, str] = {}
 
diff --git a/src/khoj/utils/constants.py b/src/khoj/utils/constants.py
index b8107edb..591a0f08 100644
--- a/src/khoj/utils/constants.py
+++ b/src/khoj/utils/constants.py
@@ -10,9 +10,10 @@ telemetry_server = "https://khoj.beta.haletic.com/v1/telemetry"
 content_directory = "~/.khoj/content/"
 default_offline_chat_models = [
     "bartowski/Meta-Llama-3.1-8B-Instruct-GGUF",
+    "bartowski/Llama-3.2-3B-Instruct-GGUF",
     "bartowski/gemma-2-9b-it-GGUF",
     "bartowski/gemma-2-2b-it-GGUF",
-    "bartowski/Phi-3.5-mini-instruct-GGUF",
+    "Qwen/Qwen2.5-14B-Instruct-GGUF",
 ]
 default_openai_chat_models = ["gpt-4o-mini", "gpt-4o"]
 default_gemini_chat_models = ["gemini-1.5-flash", "gemini-1.5-pro"]