Upload app.py with huggingface_hub

app.py

@@ -1,168 +1,65 @@
-import random
-import os
-import numpy as np
-import torch
-import gradio as gr
-import spaces
-from chatterbox.tts_turbo import ChatterboxTurboTTS
-
-
-MODEL = ChatterboxTurboTTS.from_pretrained("cuda" )
-
-EVENT_TAGS = [
-    "[clear throat]", "[sigh]", "[shush]", "[cough]", "[groan]",
-    "[sniff]", "[gasp]", "[chuckle]", "[laugh]"
-]
-
-CUSTOM_CSS = """
-.tag-container {
-    display: flex !important;
-    flex-wrap: wrap !important;
-    gap: 8px !important;
-    margin-top: 5px !important;
-    margin-bottom: 10px !important;
-    border: none !important;
-    background: transparent !important;
-}
-
-.tag-btn {
-    min-width: fit-content !important;
-    width: auto !important;
-    height: 32px !important;
-    font-size: 13px !important;
-    background: #eef2ff !important;
-    border: 1px solid #c7d2fe !important;
-    color: #3730a3 !important;
-    border-radius: 6px !important;
-    padding: 0 10px !important;
-    margin: 0 !important;
-    box-shadow: none !important;
-}
-
-.tag-btn:hover {
-    background: #c7d2fe !important;
-    transform: translateY(-1px);
-}
-"""
-
-INSERT_TAG_JS = """
-(tag_val, current_text) => {
-    const textarea = document.querySelector('#main_textbox textarea');
-    if (!textarea) return current_text + " " + tag_val;
-
-    const start = textarea.selectionStart;
-    const end = textarea.selectionEnd;
-
-    let prefix = " ";
-    let suffix = " ";
-
-    if (start === 0) prefix = "";
-    else if (current_text[start - 1] === ' ') prefix = "";
-
-    if (end < current_text.length && current_text[end] === ' ') suffix = "";
-
-    return current_text.slice(0, start) + prefix + tag_val + suffix + current_text.slice(end);
-}
-"""
-
-def set_seed(seed: int):
-    torch.manual_seed(seed)
-    torch.cuda.manual_seed(seed)
-    torch.cuda.manual_seed_all(seed)
-    random.seed(seed)
-    np.random.seed(seed)
-
-@spaces.GPU
-def generate(
-        text,
-        audio_prompt_path,
-        temperature,
-        seed_num,
-        min_p,
-        top_p,
-        top_k,
-        repetition_penalty,
-        norm_loudness
-):
-    if seed_num != 0:
-        set_seed(int(seed_num))
-
-    wav = MODEL.generate(
-        text,
-        audio_prompt_path=audio_prompt_path,
-        temperature=temperature,
-        min_p=min_p,
-        top_p=top_p,
-        top_k=int(top_k),
-        repetition_penalty=repetition_penalty,
-        norm_loudness=norm_loudness,
-    )
-
-    return (MODEL.sr, wav.squeeze(0).cpu().numpy())
-
-
-with gr.Blocks(title="Chatterbox Turbo") as demo:
-    gr.Markdown("# ⚡ Chatterbox Turbo")
-
-    with gr.Row():
-        with gr.Column():
-            text = gr.Textbox(
-                value="Oh, that's hilarious! [chuckle] Um anyway, we do have a new model in store. It's the SkyNet T-800 series and it's got basically everything. Including AI integration with ChatGPT and all that jazz. Would you like me to get some prices for you?",
-                label="Text to synthesize (max chars 300)",
-                max_lines=5,
-                elem_id="main_textbox"
-            )
-
-            with gr.Row(elem_classes=["tag-container"]):
-                for tag in EVENT_TAGS:
-                    btn = gr.Button(tag, elem_classes=["tag-btn"])
-                    btn.click(
-                        fn=None,
-                        inputs=[btn, text],
-                        outputs=text,
-                        js=INSERT_TAG_JS
-                    )
-
-            ref_wav = gr.Audio(
-                sources=["upload", "microphone"],
-                type="filepath",
-                label="Reference Audio File",
-                value="https://storage.googleapis.com/chatterbox-demo-samples/turbo/2.wav",
-            )
-
-            run_btn = gr.Button("Generate ⚡", variant="primary")
-
-        with gr.Column():
-            audio_output = gr.Audio(label="Output Audio")
-
-            with gr.Accordion("Advanced Options", open=False):
-                seed_num = gr.Number(value=0, label="Random seed (0 for random)")
-                temp = gr.Slider(0.05, 2.0, step=.05, label="Temperature", value=0.8)
-                top_p = gr.Slider(0.00, 1.00, step=0.01, label="Top P", value=0.95)
-                top_k = gr.Slider(0, 1000, step=10, label="Top K", value=1000)
-                repetition_penalty = gr.Slider(1.00, 2.00, step=0.05, label="Repetition Penalty", value=1.2)
-                min_p = gr.Slider(0.00, 1.00, step=0.01, label="Min P (Set to 0 to disable)", value=0.00)
-                norm_loudness = gr.Checkbox(value=True, label="Normalize Loudness (-27 LUFS)")
-
-    run_btn.click(
-        fn=generate,
-        inputs=[
-            text,
-            ref_wav,
-            temp,
-            seed_num,
-            min_p,
-            top_p,
-            top_k,
-            repetition_penalty,
-            norm_loudness,
-        ],
-        outputs=audio_output,
-    )
-
-if __name__ == "__main__":
-    demo.queue().launch(
-        mcp_server=True,
-        css=CUSTOM_CSS,
-        ssr_mode=False
-    )
+import os
+import gradio as gr
+import google.generativeai as genai
+
+"""**How to get Google Gemini API Key?**
+
+- Go to https://aistudio.google.com/app/api-keys
+- Click "Create API Key"
+- Copy the API Key for your use
+"""
+
+GEMINI_API_KEY="AIzaSyBg1CYTTOfWBrOzgxBhBLqHjujx7qVurrM"
+genai.configure(api_key=GEMINI_API_KEY)
+
+"""
+- Similar to Gemini Model we can also use HuggingFace Transformer Models.
+- Reference links: https://python.langchain.com/docs/integrations/providers/huggingface , https://python.langchain.com/docs/integrations/llms/huggingface_hub.html
+
+"""
+
+# from langchain.llms import HuggingFacePipeline
+# hf = HuggingFacePipeline.from_model_id(
+#     model_id="gpt2",
+#     task="text-generation",)
+
+# Initialize Gemini model
+gemini_model = genai.GenerativeModel('gemini-1.5-flash')
+
+# Custom LLM wrapper for Gemini
+class GeminiLLM:
+    def __init__(self, model):
+        self.model = model
+        self.memory_history = []
+
+    def predict(self, user_message):
+        # Build conversation context
+        full_prompt = "You are a helpful assistant to answer user queries.\n"
+        for msg in self.memory_history:
+            full_prompt += f"{msg}\n"
+        full_prompt += f"User: {user_message}\nChatbot:"
+
+        # Generate response
+        response = self.model.generate_content(full_prompt)
+        answer = response.text
+
+        # Update memory
+        self.memory_history.append(f"User: {user_message}")
+        self.memory_history.append(f"Chatbot: {answer}")
+
+        # Keep only last 10 exchanges
+        if len(self.memory_history) > 20:
+            self.memory_history = self.memory_history[-20:]
+
+        return answer
+
+llm_chain = GeminiLLM(gemini_model)
+
+def get_text_response(user_message,history):
+    response = llm_chain.predict(user_message = user_message)
+    return response
+
+demo = gr.ChatInterface(get_text_response, examples=["How are you doing?","What are your interests?","Which places do you like to visit?"])
+
+if __name__ == "__main__":
+    demo.launch(debug=True) #To create a public link, set `share=True` in `launch()`. To enable errors and logs, set `debug=True` in `launch()`.