Update app.py

app.py

@@ -12,7 +12,7 @@ from huggingface_hub import hf_hub_download
 from qdrant_client import QdrantClient, models
 from fastembed.sparse.splade_pp import supported_splade_models
 from fastembed import SparseTextEmbedding, SparseEmbedding
-from langchain_community.llms.llamacpp import LlamaCpp
+from langchain_community.chat_models.ollama import ChatOllama
 from langchain_core.callbacks import CallbackManager, StreamingStdOutCallbackHandler
 from fastembed_ext import FastEmbedEmbeddingsLc
 from langchain_community.document_loaders.wikipedia import WikipediaLoader
@@ -247,6 +247,14 @@ def load_models_and_components(show_spinner="Loading models..."):
         filename='Hermes-2-Pro-Llama-3-Instruct-Merged-DPO-Q8_0.gguf'
     )
 
+    llm = ChatOllama(
+        model=model_name, 
+        num_ctx=8192,
+        temperature=0,
+        num_gpu=0,
+        num_predict=3000
+    )
+
     llm = LlamaCpp(
         model_path=model_path,
         temperature=0.75,