Create app.py

app.py

@@ -0,0 +1,145 @@
+import os
+import random
+from huggingface_hub import InferenceClient
+import gradio as gr
+#from utils import parse_action, parse_file_content, read_python_module_structure
+from datetime import datetime
+from PIL import Image
+import agent
+from models import models
+import urllib.request
+import uuid
+import requests
+import io
+loaded_model=[]
+for i,model in enumerate(models):
+    loaded_model.append(gr.load(f'models/{model}'))
+print (loaded_model)
+
+now = datetime.now()
+date_time_str = now.strftime("%Y-%m-%d %H:%M:%S")
+
+client = InferenceClient(
+    "mistralai/Mixtral-8x7B-Instruct-v0.1"
+)
+
+############################################
+model = gr.load("models/stabilityai/sdxl-turbo")
+
+VERBOSE = True
+MAX_HISTORY = 10000
+#MODEL = "gpt-3.5-turbo"  # "gpt-4"
+history = []
+
+def infer(txt):
+    return (model(txt))
+
+def format_prompt(message, history):
+  prompt = "<s>"
+  for user_prompt, bot_response in history:
+    prompt += f"[INST] {user_prompt} [/INST]"
+    prompt += f" {bot_response}</s> "
+  prompt += f"[INST] {message} [/INST]"
+  return prompt
+
+
+
+def run_gpt(
+    in_prompt,
+    history,
+):
+    print(f'history :: {history}')
+    prompt=format_prompt(in_prompt,history)
+    seed = random.randint(1,1111111111111111)
+    print (seed)
+    generate_kwargs = dict(
+        temperature=1.0,
+        max_new_tokens=1048,
+        top_p=0.99,
+        repetition_penalty=1.0,
+        do_sample=True,
+        seed=seed,
+    )
+
+    
+    content = agent.GENERATE_PROMPT + prompt
+
+    print(content)
+    
+    #formatted_prompt = format_prompt(f"{system_prompt}, {prompt}", history)
+    #formatted_prompt = format_prompt(f'{content}', history)
+
+    stream = client.text_generation(content, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    resp = ""
+    for response in stream:
+        resp += response.token.text
+    return resp
+
+
+def run(purpose,history,model_drop):
+    print (history)
+    #print(purpose)
+    #print(hist)
+    task=None
+    directory="./"
+    #if history:
+    #    history=str(history).strip("[]")
+    #if not history:
+    #    history = ""
+
+    #action_name, action_input = parse_action(line)
+    out_prompt = run_gpt(
+        purpose,
+        history,
+        
+        )
+
+    yield ("",[(purpose,out_prompt)],None)
+    #out_img = infer(out_prompt)
+    model=loaded_model[int(model_drop)]
+    out_img=model(out_prompt)
+    print(out_img)
+    url=f'https://johann22-mixtral-diffusion.hf.space/file={out_img}'
+    print(url)
+    uid = uuid.uuid4()
+    #urllib.request.urlretrieve(image, 'tmp.png')
+    #out=Image.open('tmp.png')
+    r = requests.get(url, stream=True)
+    if r.status_code == 200:
+        out = Image.open(io.BytesIO(r.content))
+    yield ("",[(purpose,out_prompt)],out)
+        #return ("", [(purpose,history)])
+
+
+
+################################################
+
+with gr.Blocks() as iface:
+    gr.HTML("""<center><h1>Chat Diffusion</h1><br><h3>This chatbot will generate images</h3></center>""")
+    #chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
+    with gr.Row():
+        with gr.Column():
+            chatbot=gr.Chatbot()
+            msg = gr.Textbox()
+            model_drop=gr.Dropdown(label="Diffusion Models", type="index", choices=[m for m in models], value=models[0])
+    with gr.Row():
+        submit_b = gr.Button()
+        stop_b = gr.Button("Stop")
+        clear = gr.ClearButton([msg, chatbot])
+    
+    sumbox=gr.Image(label="Image")
+
+        
+    sub_b = submit_b.click(run, [msg,chatbot,model_drop],[msg,chatbot,sumbox])
+    sub_e = msg.submit(run, [msg, chatbot,model_drop], [msg, chatbot,sumbox])
+    stop_b.click(None,None,None, cancels=[sub_b,sub_e])
+iface.launch()
+'''
+gr.ChatInterface(
+    fn=run,
+    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, likeable=True, layout="panel"),
+    title="Mixtral 46.7B\nMicro-Agent\nInternet Search <br> development test",
+    examples=examples,
+    concurrency_limit=20,
+).launch(show_api=False)
+'''