Update app.py

app.py

@@ -13,6 +13,7 @@
 # from chromadb.utils import embedding_functions
 # from langchain.embeddings import SentenceTransformerEmbeddings
 # from langchain.embeddings import HuggingFaceBgeEmbeddings
+ffrom langchain_community.llms import Llamacpp
 from langchain.embeddings import HuggingFaceInstructEmbeddings
 from langchain.document_loaders import (
     CSVLoader,
@@ -347,15 +348,19 @@ def main():
                     'threads': int(os.cpu_count() / 2)
                     }
                     
-                    llm = CTransformers(
-                        model = "TheBloke/zephyr-7B-beta-GGUF",
-                        model_file = "zephyr-7b-beta.Q4_0.gguf",
-                        model_type="mistral",
-                        lib="avx2", #for CPU use
-                        **config
-                    )
+                    # llm = CTransformers(
+                    #     model = "TheBloke/zephyr-7B-beta-GGUF",
+                    #     model_file = "zephyr-7b-beta.Q4_0.gguf",
+                    #     model_type="mistral",
+                    #     lib="avx2", #for CPU use
+                    #     **config
+                    # )
+
+                    llm = Llamacpp(model_path = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF",temperature=0.75,max_tokens=2000,top_p=1,)
                     st.write("LLM Initialized:")
 
+            
+
                     model_name = "BAAI/bge-large-en"
                     model_kwargs = {'device': 'cpu'}
                     encode_kwargs = {'normalize_embeddings': False}