Update app.py

app.py

@@ -1,68 +1,58 @@
-from transformers import AutoModelForCausalLM, AutoTokenizer
 import gradio as gr
-import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
 import json
 
-
-title = "????AI ChatBot"
-description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
-examples = [["How are you?"]]
-
-
-tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
-model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")
-
-
-def predict(input, history=[]):
-    # tokenize the new input sentence
-    new_user_input_ids = tokenizer.encode(
-        input + tokenizer.eos_token, return_tensors="pt"
+# Load pre-trained model and tokenizer (replace with desired model if needed)
+model_name = "microsoft/DialoGPT-large"
+model = AutoModelForCausalLM.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+# Function to process user input and generate response
+def chat(message, history):
+    # Preprocess user input
+    input_ids = tokenizer(message, return_tensors="pt")["input_ids"]
+
+    # Generate response with beam search to improve fluency
+    generated_outputs = model.generate(
+        input_ids,
+        max_length=512,  # Adjust max_length as needed for response length
+        num_beams=5,  # Experiment with num_beams for better phrasing
+        no_repeat_ngram_size=2,  # Prevent repetition in responses
+        early_stopping=True,  # Stop generation if response seems complete
     )
 
-    # append the new user input tokens to the chat history
-    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)
-
-    # generate a response
-    history = model.generate(
-        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
-    ).tolist()
-
-    # convert the tokens to text, and then split the responses into lines
-    response = tokenizer.decode(history[0]).split("<|endoftext|>")
-    # print('decoded_response-->>'+str(response))
-    response = [
-        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
-    ]  # convert to tuples of list
-    # print('response-->>'+str(response))
-    return response, history
-
-def read_json_file(file_path): #read json file test
-    with open(file_path, 'r') as file:
-        data = json.load(file)
-    return data
-
-def main():
-    # List of file names
-    file_names = ['fileone.json', 'filesecond.json', 'filethird.json', 'filefourth.json', 'filefifth.json']
-    
-    # Read each JSON file and print its content
-    for file_name in file_names:
-        json_data = read_json_file(file_name)
-        print(f"Contents of {file_name}:")
-        print(json_data)
-        print()
-
-if __name__ == "__main__":
-    main()
-
-
-
-gr.Interface(
-    fn=predict,
-    title=title,
-    description=description,
-    examples=examples,
-    inputs=["text", "state"],
-    outputs=["chatbot", "state"],
-    theme="finlaymacklon/boxy_violet",
-).launch()
+    # Decode generated tokens to text
+    response = tokenizer.batch_decode(generated_outputs, skip_special_tokens=True)[0]
+
+    # Access and process JSON files (improved structure)
+    json_files = {
+        "fileone.json": "your_key_in_fileone",
+        "filesecond.json": "your_key_in_filesecond",
+        "filethird.json": "your_key_in_filethird",
+        "filefourth.json": "your_key_in_filefourth",
+        "filefifth.json": "your_key_in_filefifth",
+    }
+
+    if any(word in message.lower() for word in ["file", "data", "information"]):
+        try:
+            # Find the relevant JSON file based on keywords in message
+            relevant_file = next(
+                file for file, key in json_files.items() if key.lower() in message.lower()
+            )
+            with open(relevant_file, "r") as f:
+                data = json.load(f)
+                relevant_info = data.get(json_files[relevant_file], "No relevant information found")
+            response += f"\nHere's some information I found in {relevant_file}: {relevant_info}"
+        except (FileNotFoundError, StopIteration):
+            response += "\nCouldn't find the requested file or information."
+        except json.JSONDecodeError:
+            response += "\nError processing the JSON data."
+
+    # Update history with current conversation (optional)
+    history.append([message, response])
+
+    return response
+
+# Create Gradio interface for the chatbot
+interface = gr.Interface(chat, inputs="textbox", outputs="textbox", catch_exceptions=True)
+interface.launch(share=True)  # Launch the Gradio app and share link