new code

src/pdfchatbot.py

@@ -36,6 +36,7 @@ class PDFChatBot:
         self.chunk_size = None
         self.current_context = None
         self.format_seperator="""\n\n--\n\n"""
+        self.pipe = None
         #self.chunk_size_slider = chunk_size_slider
 
     def load_embeddings(self):
@@ -59,7 +60,7 @@ class PDFChatBot:
 
     @spaces.GPU
     def create_organic_pipeline(self):
-        self.pipeline = pipeline(
+        self.pipe = pipeline(
             "text-generation",
             model="meta-llama/Meta-Llama-3-8B-Instruct",
             model_kwargs={"torch_dtype": torch.bfloat16},
@@ -78,12 +79,14 @@ 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},
@@ -95,7 +98,7 @@ class PDFChatBot:
             add_generation_prompt=True
         )
         temp = 0.1
-        outputs = pipe(
+        outputs = self.pipe(
             prompt,
             max_new_tokens=1024,
             do_sample=True,