UPDATE APP.PY

app.py

@@ -1,121 +1,154 @@
-import gradio as gr
-import numpy as np
-import random
-import spaces
-import torch
-from diffusers import DiffusionPipeline
-
-dtype = torch.bfloat16
-device = "cuda" if torch.cuda.is_available() else "cpu"
-
-pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=torch.bfloat16, revision="refs/pr/1").to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 2048
-
-@spaces.GPU()
-def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4, progress=gr.Progress(track_tqdm=True)):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-    generator = torch.Generator().manual_seed(seed)
-    image = pipe(
-            prompt = prompt, 
-            width = width,
-            height = height,
-            num_inference_steps = num_inference_steps, 
-            generator = generator,
-            guidance_scale=0.0
-    ).images[0] 
-    return image, seed
- 
-examples = [
-    "a tiny astronaut hatching from an egg on the moon",
-    "a cat holding a sign that says hello world",
-    "an anime illustration of a wiener schnitzel",
-]
-
-css="""
-#col-container {
-    margin: 0 auto;
-    max-width: 520px;
-}
-"""
-
-with gr.Blocks(css=css) as demo:
-    
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(f"""# fuzzy.1 [schnell]
-12B param rectified flow transformer distilled from [fuzzy.1 [pro]](https://blackforestlabs.ai/) for 4 step generation
-[[blog](https://blackforestlabs.ai/2024/07/31/announcing-black-forest-labs/)] [[model](https://huggingface.co/spaces/odaly/fuzzylab)]
-        """)
-        
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-            
-            run_button = gr.Button("Run", scale=0)
-        
-        result = gr.Image(label="Result", show_label=False)
-        
-        with gr.Accordion("Advanced Settings", open=False):
-            
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-            
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
-            
-            with gr.Row():
-                
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                )
-                
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,
-                )
-            
-            with gr.Row():
-                
-  
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=4,
-                )
-        
-        gr.Examples(
-            examples = examples,
-            fn = infer,
-            inputs = [prompt],
-            outputs = [result, seed],
-            cache_examples="lazy"
-        )
+# app.py
+from typing import List, Union
+
+from dotenv import load_dotenv, find_dotenv
+from langchain.callbacks import get_openai_callback
+from langchain.chat_models import ChatOpenAI
+from langchain.schema import (SystemMessage, HumanMessage, AIMessage)
+from langchain.llms import LlamaCpp
+from langchain.callbacks.manager import CallbackManager
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+import streamlit as st
 
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn = infer,
-        inputs = [prompt, seed, randomize_seed, width, height, num_inference_steps],
-        outputs = [result, seed]
+
+def init_page() -> None:
+    st.set_page_config(
+        page_title="Personal ChatGPT"
     )
+    st.header("Personal ChatGPT")
+    st.sidebar.title("Options")
+
+
+def init_messages() -> None:
+    clear_button = st.sidebar.button("Clear Conversation", key="clear")
+    if clear_button or "messages" not in st.session_state:
+        st.session_state.messages = [
+            SystemMessage(
+                content="You are a helpful AI assistant. Reply your answer in mardkown format.")
+        ]
+        st.session_state.costs = []
+
+
+def select_llm() -> Union[ChatOpenAI, LlamaCpp]:
+    model_name = st.sidebar.radio("Choose LLM:",
+                                  ("gpt-3.5-turbo-0613", "gpt-4",
+                                   "llama-2-7b-chat.ggmlv3.q2_K"))
+    temperature = st.sidebar.slider("Temperature:", min_value=0.0,
+                                    max_value=1.0, value=0.0, step=0.01)
+    if model_name.startswith("gpt-"):
+        return ChatOpenAI(temperature=temperature, model_name=model_name)
+    elif model_name.startswith("llama-2-"):
+        callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
+        return LlamaCpp(
+            model_path=f"./models/{model_name}.bin",
+            input={"temperature": temperature,
+                   "max_length": 2000,
+                   "top_p": 1
+                   },
+            callback_manager=callback_manager,
+            verbose=False,  # True
+        )
+
+
+def get_answer(llm, messages) -> tuple[str, float]:
+    if isinstance(llm, ChatOpenAI):
+        with get_openai_callback() as cb:
+            answer = llm(messages)
+        return answer.content, cb.total_cost
+    if isinstance(llm, LlamaCpp):
+        return llm(llama_v2_prompt(convert_langchainschema_to_dict(messages))), 0.0
+
+
+def find_role(message: Union[SystemMessage, HumanMessage, AIMessage]) -> str:
+    """
+    Identify role name from langchain.schema object.
+    """
+    if isinstance(message, SystemMessage):
+        return "system"
+    if isinstance(message, HumanMessage):
+        return "user"
+    if isinstance(message, AIMessage):
+        return "assistant"
+    raise TypeError("Unknown message type.")
+
+
+def convert_langchainschema_to_dict(
+        messages: List[Union[SystemMessage, HumanMessage, AIMessage]]) \
+        -> List[dict]:
+    """
+    Convert the chain of chat messages in list of langchain.schema format to
+    list of dictionary format.
+    """
+    return [{"role": find_role(message),
+             "content": message.content
+             } for message in messages]
+
+
+def llama_v2_prompt(messages: List[dict]) -> str:
+    """
+    Convert the messages in list of dictionary format to Llama2 compliant format.
+    """
+    B_INST, E_INST = "[INST]", "[/INST]"
+    B_SYS, E_SYS = "<<SYS>>\n", "\n<</SYS>>\n\n"
+    BOS, EOS = "<s>", "</s>"
+    DEFAULT_SYSTEM_PROMPT = f"""You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe. Please ensure that your responses are socially unbiased and positive in nature. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information."""
+
+    if messages[0]["role"] != "system":
+        messages = [
+            {
+                "role": "system",
+                "content": DEFAULT_SYSTEM_PROMPT,
+            }
+        ] + messages
+    messages = [
+        {
+            "role": messages[1]["role"],
+            "content": B_SYS + messages[0]["content"] + E_SYS + messages[1]["content"],
+        }
+    ] + messages[2:]
+
+    messages_list = [
+        f"{BOS}{B_INST} {(prompt['content']).strip()} {E_INST} {(answer['content']).strip()} {EOS}"
+        for prompt, answer in zip(messages[::2], messages[1::2])
+    ]
+    messages_list.append(
+        f"{BOS}{B_INST} {(messages[-1]['content']).strip()} {E_INST}")
+
+    return "".join(messages_list)
+
+
+def main() -> None:
+    _ = load_dotenv(find_dotenv())
+
+    init_page()
+    llm = select_llm()
+    init_messages()
+
+    # Supervise user input
+    if user_input := st.chat_input("Input your question!"):
+        st.session_state.messages.append(HumanMessage(content=user_input))
+        with st.spinner("ChatGPT is typing ..."):
+            answer, cost = get_answer(llm, st.session_state.messages)
+        st.session_state.messages.append(AIMessage(content=answer))
+        st.session_state.costs.append(cost)
+
+    # Display chat history
+    messages = st.session_state.get("messages", [])
+    for message in messages:
+        if isinstance(message, AIMessage):
+            with st.chat_message("assistant"):
+                st.markdown(message.content)
+        elif isinstance(message, HumanMessage):
+            with st.chat_message("user"):
+                st.markdown(message.content)
+
+    costs = st.session_state.get("costs", [])
+    st.sidebar.markdown("## Costs")
+    st.sidebar.markdown(f"**Total cost: ${sum(costs):.5f}**")
+    for cost in costs:
+        st.sidebar.markdown(f"- ${cost:.5f}")
+
 
-demo.launch()
+# streamlit run app.py
+if __name__ == "__main__":
+    main