testing with llama2

.idea/misc.xml

@@ -1,4 +1,7 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
+  <component name="Black">
+    <option name="sdkName" value="Python 3.12 (LLama3Rag)" />
+  </component>
   <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.12 (LLama3Rag)" project-jdk-type="Python SDK" />
 </project>

src/interface.py

@@ -2,29 +2,30 @@ import gradio as gr
 
 # Gradio application setup
 def create_demo():
-    with gr.Blocks(title= "RAG Chatbot Q&A",
-        theme = "Soft"
-        ) as demo:
+    with gr.Blocks(title="RAG Chatbot Q&A", theme="Soft") as demo:
         with gr.Column():
             with gr.Row():
                 chat_history = gr.Chatbot(value=[], elem_id='chatbot', height=680)
                 show_img = gr.Image(label='Overview', height=680)
 
+        with gr.Row():
+            # Add sliders here
+            with gr.Column(scale=0.2):  # Adjust scale as needed
+                slider1 = gr.Slider(minimum=0, maximum=100, value=50, label="Chunk Size")
+                slider2 = gr.Slider(minimum=-10, maximum=10, value=0, label="Chunk Overlap")
+
         with gr.Row():
             with gr.Column(scale=0.60):
                 text_input = gr.Textbox(
                     show_label=False,
                     placeholder="Type here to ask your PDF",
                 container=False)
-
             with gr.Column(scale=0.20):
                 submit_button = gr.Button('Send')
-
             with gr.Column(scale=0.20):
                 uploaded_pdf = gr.UploadButton("📁 Upload PDF", file_types=[".pdf"])
-                
 
-        return demo, chat_history, show_img, text_input, submit_button, uploaded_pdf
+    return demo, chat_history, show_img, text_input, submit_button, uploaded_pdf, slider1, slider2
 
 if __name__ == '__main__':
     demo, chatbot, show_img, text_input, submit_button, uploaded_pdf = create_demo()

src/pdfchatbot.py

@@ -11,6 +11,8 @@ from langchain.document_loaders import PyPDFLoader
 from langchain.prompts import PromptTemplate
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 import spaces
+from langchain_text_splitters import CharacterTextSplitter
+
 
 
 class PDFChatBot:
@@ -90,7 +92,9 @@ class PDFChatBot:
         """
         Load the vector database from the documents and embeddings.
         """
-        self.vectordb = Chroma.from_documents(self.documents, self.embeddings)
+        text_splitter = CharacterTextSplitter(chunk_size=256, chunk_overlap=0)
+        docs = text_splitter.split_documents(self.documents)
+        self.vectordb = Chroma.from_documents(docs, self.embeddings)
 
     def load_tokenizer(self):
         """