Update llama_cpp_inf.py

llama_cpp_inf.py

@@ -1,5 +1,4 @@
 ## Imports
-from llama_cpp import Llama
 import re
 from huggingface_hub import hf_hub_download
 from gradio_client import Client
@@ -23,13 +22,3 @@ def run_inference_lcpp(jsonstr, user_search):
     frag_res = re.findall(r'\w+|\s+|[^\w\s]', input_string)
     for word in frag_res:
         yield word
-
-if __name__ == "__main__":
-    prompt = """Context: A vector database, vector store or vector search engine is a database that can store vectors (fixed-length lists of numbers) along with other data items. Vector databases typically implement one or more Approximate Nearest Neighbor (ANN) algorithms,[1][2] so that one can search the database with a query vector to retrieve the closest matching database records.
-
-    Vectors are mathematical representations of data in a high-dimensional space. In this space, each dimension corresponds to a feature of the data, with the number of dimensions ranging from a few hundred to tens of thousands, depending on the complexity of the data being represented. A vector's position in this space represents its characteristics. Words, phrases, or entire documents, as well as images, audio, and other types of data, can all be vectorized; Prompt: Describe what is a vector database"""
-    res = llm(prompt, **generation_kwargs) # Res is a dictionary
-
-    ## Unpack and the generated text from the LLM response dictionary and print it
-    print(res["choices"][0]["text"])
-    # res is short for result