Update app.py

app.py

@@ -1,25 +1,23 @@
 import gradio as gr
+from dotenv import load_dotenv
 from langchain import PromptTemplate, LLMChain, HuggingFaceHub
 from langchain.llms import CTransformers
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from transformers import pipeline
 from langchain.llms.huggingface_pipeline import HuggingFacePipeline
 
+load_dotenv()
 
 def generate_prompts(user_input):
 
-    model_name = "TheBloke/Mistral-7B-Instruct-v0.1-GGUF"
-    model = AutoModelForCausalLM.from_pretrained(model_name)
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-    config = {"temperature": 0.7, "max_length": 50}  # Example configuration
-    llm = CTransformers(model=model, tokenizer=tokenizer, config=config)
-    
     prompt_template = PromptTemplate(
         input_variables=["Question"],
-        template=f"Just list 10 quetion prompts for {user_input} and don't put number before each of the prompts.")
-    
-    
+        template=f"Just list 10 quetion prompts for {user_input} and don't put number before each of the prompts."
+    )
+    config = {'max_new_tokens': 2048, 'temperature': 0.7, 'context_length': 4096}
+    llm = CTransformers(model="TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
+                        config=config,
+                        threads=os.cpu_count())
     hub_chain = LLMChain(prompt = prompt_template, llm = llm)
     input_data = {"Question": user_input}