Update app.py

app.py

@@ -1,15 +1,19 @@
 from flask import Flask, request, jsonify
-from transformers import AutoModelForCausalLM, AutoTokenizer
+from llama_cpp import Llama
+# from transformers import AutoModelForCausalLM, AutoTokenizer
+llm = Llama.from_pretrained(
+	repo_id="bartowski/Llama-3.2-1B-Instruct-GGUF",
+	filename="Llama-3.2-1B-Instruct-IQ3_M.gguf",
+)
+# MODEL_NAME = "meta-llama/Llama-3.1-8B-Instruct"
 
-MODEL_NAME = "meta-llama/Llama-3.1-8B-Instruct"
+# tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+# model = AutoModelForCausalLM.from_pretrained(MODEL_NAME).to("cpu")
 
-tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
-model = AutoModelForCausalLM.from_pretrained(MODEL_NAME).to("cpu")
-
-app = Flask(__name__)
-DEFAULT_TEMPERATURE = 0.7
-DEFAULT_MAX_TOKENS = 150
-DEFAULT_TOP_P = 0.95
+# app = Flask(__name__)
+# DEFAULT_TEMPERATURE = 0.7
+# DEFAULT_MAX_TOKENS = 150
+# DEFAULT_TOP_P = 0.95
 
 def generate_journal_suggestion(current_page):
     try:
@@ -18,16 +22,26 @@ def generate_journal_suggestion(current_page):
             Întrebarea ar trebui să încurajeze reflecția personală mai profundă, explorarea sentimentelor sau clarificarea obiectivelor."""
         )
         
-        input_ids = tokenizer(suggestion_prompt, return_tensors="pt").input_ids.to("cpu")
-
-        output_ids = model.generate(
-            input_ids,
-            max_length=DEFAULT_MAX_TOKENS,
-            temperature=DEFAULT_TEMPERATURE,
-            top_p=DEFAULT_TOP_P,
-            do_sample=True,
+        # input_ids = tokenizer(suggestion_prompt, return_tensors="pt").input_ids.to("cpu")
+
+        # output_ids = model.generate(
+        #     input_ids,
+        #     max_length=DEFAULT_MAX_TOKENS,
+        #     temperature=DEFAULT_TEMPERATURE,
+        #     top_p=DEFAULT_TOP_P,
+        #     do_sample=True,
+        # )
+        
+        suggestion_response = llm.create_chat_completion(
+        	messages = [
+        		{
+        			"role": "user",
+        			"content": "What is the capital of France?"
+        		}
+        	]
         )
-        suggestion_response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+        return suggestion_response
+        # suggestion_response = tokenizer.decode(output_ids[0], skip_special_tokens=True)
 
     except Exception as e:
         return f"Error: {str(e)}"
@@ -51,4 +65,6 @@ def chat():
     return jsonify({"journal_suggestion": suggestion})
 
 if __name__ == "__main__":
-    app.run(debug=True)
+#     app.run(debug=True)
+
+