Update app.py

app.py

@@ -1,63 +1,78 @@
-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)",
-        ),
-    ],
-)
+from peft import AutoPeftModelForCausalLM
+from transformers import GenerationConfig
+from transformers import AutoTokenizer
+import torch
+import streamlit as st
+from streamlit_chat import message
 
+st.session_state.clicked=True
+
+def process_data_sample(example):
+
+    processed_example = "<|system|>\n You are a support chatbot who helps with user queries chatbot who always responds in the style of a professional.</s>\n<|user|>\n" + example + "</s>\n<|assistant|>\n"
+
+    return processed_example
+
+@st.cache_resource(show_spinner=True)
+def create_bot():
+
+    tokenizer = AutoTokenizer.from_pretrained("Vasanth/zephyr-support-chatbot")
+
+    model = AutoPeftModelForCausalLM.from_pretrained(
+                                                        "Vasanth/zephyr-support-chatbot",
+                                                        low_cpu_mem_usage=True,
+                                                        return_dict=True,
+                                                        torch_dtype=torch.float16,
+                                                        device_map="cuda"
+                                                    )
+
+    generation_config = GenerationConfig(
+                                            do_sample=True,
+                                            temperature=0.5,
+                                            max_new_tokens=256,
+                                            pad_token_id=tokenizer.eos_token_id
+                                        )
+    
+    return model, tokenizer, generation_config
+
+model, tokenizer, generation_config = create_bot()
+
+bot = create_bot()
+
+def infer_bot(prompt):
+    inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+    outputs = model.generate(**inputs, generation_config=generation_config)
+    out_str = tokenizer.decode(outputs[0], skip_special_tokens=True).replace(prompt, '')
+    return out_str
+
+def display_conversation(history):
+    for i in range(len(history["assistant"])):
+        message(history["user"][i], is_user=True, key=str(i) + "_user")
+        message(history["assistant"][i],key=str(i))
+
+def main():
+
+    st.title("Support Member 📚🤖")
+    st.subheader("A bot created using Zephyr which was finetuned to possess the capabilities to be a support member")
+
+    user_input = st.text_input("Enter your query")
+
+    if "assistant" not in st.session_state:
+        st.session_state["assistant"] = ["I am ready to help you"]
+    if "user" not in st.session_state:
+        st.session_state["user"] = ["Hey there!"]
+                
+    if st.session_state.clicked:
+        if st.button("Answer"):
+
+            answer = infer_bot(user_input)
+            st.session_state["user"].append(user_input)
+            st.session_state["assistant"].append(answer)
+
+            if st.session_state["assistant"]:
+                display_conversation(st.session_state)
 
 if __name__ == "__main__":
-    demo.launch()
+    main()
+    
+