Rename app_old.py to app_R.py

app_old.py → app_R.py

@@ -1,79 +1,21 @@
-# import gradio as gr
-# from huggingface_hub import InferenceClient
-
-# """
-# For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-# """
-# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-# def respond(
-#     message,
-#     history: list[tuple[str, str]],
-#     system_message,
-#     max_tokens,
-#     temperature,
-#     top_p,
-# ):
-#     messages = [{"role": "system", "content": system_message}]
-
-#     for val in history:
-#         if val[0]:
-#             messages.append({"role": "user", "content": val[0]})
-#         if val[1]:
-#             messages.append({"role": "assistant", "content": val[1]})
-
-#     messages.append({"role": "user", "content": message})
-
-#     response = ""
-
-#     for message in client.chat_completion(
-#         messages,
-#         max_tokens=max_tokens,
-#         stream=True,
-#         temperature=temperature,
-#         top_p=top_p,
-#     ):
-#         token = message.choices[0].delta.content
-
-#         response += token
-#         yield response
-
-# """
-# For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-# """
-# demo = gr.ChatInterface(
-#     respond,
-#     additional_inputs=[
-#         gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-#         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-#         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-#         gr.Slider(
-#             minimum=0.1,
-#             maximum=1.0,
-#             value=0.95,
-#             step=0.05,
-#             label="Top-p (nucleus sampling)",
-#         ),
-#     ],
-# )
-
-
-# if __name__ == "__main__":
-#     demo.launch()
-
-
-
-
 import gradio as gr
 import torch
-from transformers import RagRetriever, RagSequenceForGeneration, AutoTokenizer
+from transformers import RagRetriever, RagSequenceForGeneration
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
+# Load model
 device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
+dataset_path = "./sample/my_knowledge_dataset"
+index_path = "./sample/my_knowledge_dataset_hnsw_index.faiss"
+
+retriever = RagRetriever.from_pretrained("facebook/rag-sequence-nq", index_name="custom",
+                                            passages_path = dataset_path,
+                                            index_path = index_path,
+                                            n_docs = 5)
+rag_model = RagSequenceForGeneration.from_pretrained('facebook/rag-sequence-nq', retriever=retriever)
+rag_model.retriever.init_retrieval()
+rag_model.to(device)
+
 def strip_title(title):
     if title.startswith('"'):
         title = title[1:]
@@ -81,7 +23,7 @@ def strip_title(title):
         title = title[:-1]
     return title
 
-def retrieved_info(rag_model, query):
+def retrieved_info(query, rag_model = rag_model):
     # Tokenize query
     retriever_input_ids = rag_model.retriever.question_encoder_tokenizer.batch_encode_plus(
         [query],
@@ -109,16 +51,11 @@ def retrieved_info(rag_model, query):
         titles = [strip_title(title) for title in docs["title"]]
         texts = docs["text"]
         for title, text in zip(titles, texts):
-            #print(f"Title: {title}")
-            #print(f"Context: {text}")
             retrieved_context.append(f"{title}: {text}")
 
     answer = retrieved_context
     return answer
 
-
-
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -127,21 +64,7 @@ def respond(
     temperature,
     top_p,
 ):
-    # Load model
-    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-
-    dataset_path = "./sample/my_knowledge_dataset"
-    index_path = "./sample/my_knowledge_dataset_hnsw_index.faiss"
-
-    tokenizer = AutoTokenizer.from_pretrained("facebook/rag-sequence-nq")
-    retriever = RagRetriever.from_pretrained("facebook/rag-sequence-nq", index_name="custom",
-                                             passages_path = dataset_path,
-                                             index_path = index_path,
-                                             n_docs = 5)
-    rag_model = RagSequenceForGeneration.from_pretrained('facebook/rag-sequence-nq', retriever=retriever)
-    rag_model.retriever.init_retrieval()
-    rag_model.to(device)
-
+    
     if message:  # If there's a user query
         response = retrieved_info(rag_model, message)  # Get the answer from your local FAISS and Q&A model
         return response[0]
@@ -150,22 +73,16 @@ def respond(
     return ""
 
 
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 # Custom title and description
 title = "🧠 Welcome to Your AI Knowledge Assistant"
 description = """
-HI!!, I am a chatbot, I retrieves relevant information from a custom dataset using RAG. Ask any question, and let me assist you.
-My capabilities and knowledge is limited right now because of computational resources. Originally I can acess more than a million files 
-from my knowledge-base but, right now, I am limited to less than 1000 files. LET'S BEGGINNNN......
+HI!!, I am your loyal assistant, My functionality is based on RAG model, I retrieves relevant information and provide answers based on that. Ask me any question, and let me assist you.
+My capabilities are limited because I am still in development phase. I will do my best to assist you. SOOO LET'S BEGGINNNN......
 """
 
 demo = gr.ChatInterface(
     respond,
     type = 'messages',
-    submit_btn = True,
     additional_inputs=[
         gr.Textbox(value="You are a helpful and friendly assistant.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
@@ -180,12 +97,12 @@ demo = gr.ChatInterface(
     ],
     title=title,
     description=description,
+    submit_btn = True,
     textbox=gr.Textbox(placeholder=["'What is the future of AI?' or 'App Development'"]),
     examples=[["✨Future of AI"], ["📱App Development"]],
-    example_icons=["🤖", "📱"],
+    #example_icons=["🤖", "📱"],
     theme="compact",
 )
 
-
 if __name__ == "__main__":
-    demo.launch(share = True )
+    demo.launch(share = True )