Update main.py

main.py

@@ -1,5 +1,9 @@
 from flask import Flask, request, jsonify
 from langchain_community.llms import LlamaCpp
+from llama_cpp import Llama
+
+
+
 import os 
 app = Flask(__name__)
 
@@ -7,13 +11,11 @@ n_gpu_layers = 0
 n_batch = 1024
 
 
-llm = LlamaCpp(
-    model_path="Phi-3-mini-4k-instruct-q4.gguf",  # path to GGUF file
-    temperature=0.1,
-    n_gpu_layers=n_gpu_layers,
-    n_batch=n_batch,
-    n_ctx=4096
+llm = Llama(
+  model_path="Phi-3-mini-4k-instruct-q4.gguf",  # path to GGUF file
+  n_gpu_layers=0, # The number of layers to offload to GPU, if you have GPU acceleration available. Set to 0 if no GPU acceleration is available on your system.
 )
+
 file_size = os.stat('Phi-3-mini-4k-instruct-q4.gguf')
 print("model size ====> :", file_size.st_size, "bytes")
 
@@ -27,10 +29,9 @@ def get_skills():
         f"<|user|>\n{cv_body}<|end|>\n<|assistant|>Can you list the skills mentioned in the CV?<|end|>",
         max_tokens=256,  # Generate up to 256 tokens
         stop=["<|end|>"], 
-        echo=True,  # Whether to echo the prompt
     )
 
-    return jsonify({'skills': output})
+    return jsonify({'skills': output['choices'][0]['text']})
 
 if __name__ == '__main__':
     app.run()