Update space

app.py

@@ -18,32 +18,12 @@ from langchain_chroma import Chroma
 """
 For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
 """ 
+llm = HuggingFacePipeline.from_model_id(
+    model_id="meta-llama/Llama-3.2-3B",
+    task="text-generation",
+    pipeline_kwargs={"max_new_tokens": 10},
+)
 
-from langchain.llms.base import LLM
-from typing import Optional, List, Mapping, Any
-import subprocess
-
-class LlamaCppLLM(LLM):
-    model_path: str  # Path to the GGUF model
-    n_ctx: int = 2048  # Context window size
-
-    def _call(self, prompt: str, stop: Optional[List[str]] = None) -> str:
-        # Use llama.cpp to generate a response
-        command = [
-            "./main",  # Path to llama.cpp executable
-            "-m", self.model_path,
-            "-p", prompt,
-            "--ctx-size", str(self.n_ctx),
-        ]
-        result = subprocess.run(command, capture_output=True, text=True)
-        return result.stdout
-
-    @property
-    def _llm_type(self) -> str:
-        return "llama-cpp"
-
-# Initialize the custom LLM
-llm = LlamaCppLLM(model_path="path/to/bling-phi-3-gguf.bin")
 
 # Initialize embedding model "all-MiniLM-L6-v2"
 embedding_model = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")