Update app.py

app.py

@@ -9,11 +9,14 @@ from langchain_community.llms import HuggingFacePipeline
 from langchain.retrievers import ParentDocumentRetriever
 from langchain.storage import InMemoryStore
 from langchain_chroma import Chroma
+from langchain.llms import LlamaCpp
 from langchain_core.prompts import ChatPromptTemplate, FewShotChatMessagePromptTemplate
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.runnables import RunnableLambda
 from datetime import date
 from transformers import AutoModelForCausalLM, AutoTokenizer
+from setup import OLMO_MODEL
+model_path = OLMO_MODEL
 
 # Environment variables
 os.environ['LANGCHAIN_TRACING_V2'] = 'true'
@@ -81,25 +84,16 @@ def get_chain(temperature):
     
     # Replace the local OLMOLLM with the Hugging Face model
     
-    model_name = "OLMo-7B-Instruct"
-
-# Load the tokenizer and model
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    model = AutoModelForCausalLM.from_pretrained(model_name)
-
-    # Create a text generation pipeline with the model
-    pipe = pipeline(
-        "text-generation",
-        model=model,
-        tokenizer=tokenizer,
-        max_length=2200,  # Adjust based on your input length
-        max_new_tokens=100,  # Number of tokens to generate
-        temperature=temperature  # Adjust the creativity of the output
-                )
+    llm = LlamaCpp(
+        model_path=str(model_path),
+        callback_manager=callback_manager,
+        temperature=0.8,
+        max_tokens=3000,
+        verbose=False,
+        echo=False
+    )
 
     
-    # Initialize the LangChain HuggingFacePipeline
-    llm = HuggingFacePipeline(pipeline=pipe)
 
     
     # Initialize LangChain