new code

src/pdfchatbot.py

@@ -78,6 +78,12 @@ class PDFChatBot:
     def create_organic_response(self, history, query):
         self.get_organic_context(query)
         tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
+        pipe = pipeline(
+            "text-generation",
+            model="meta-llama/Meta-Llama-3-8B-Instruct",
+            model_kwargs={"torch_dtype": torch.bfloat16},
+            device="cuda",
+        )
         messages = [
             {"role": "system", "content": "From the the contained given below, answer the question of user \n " + self.current_context},
             {"role": "user", "content": query},
@@ -89,7 +95,7 @@ class PDFChatBot:
             add_generation_prompt=True
         )
         temp = 0.1
-        outputs = self.pipeline(
+        outputs = pipe(
             prompt,
             max_new_tokens=1024,
             do_sample=True,