Update app.py

app.py

@@ -1,64 +1,108 @@
+import random
 import gradio as gr
+import ollama
 from huggingface_hub import InferenceClient
+import os
+import httpx
 
-"""
-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)",
-        ),
+#clienttt = httpx.Client(base_url="http://localhost:11434")
+#ollama._clienttt = clienttt
+#ollama.pull("llama2")
+
+def chat_short_story(length, genre, theme, tone, writing_style):
+    """
+    Generates a creative short story using a Hugging Face model.
+    Parameters:
+        length (int): The approximate word count for the story.
+        genre (str): The genre of the story (e.g., fantasy, mystery).
+        theme (str): The central theme of the story.
+        tone (str): The tone of the story (e.g., humorous, serious).
+        writing_style (str): The writing style (e.g., poetic, conversational).
+    Returns:
+        str: The generated short story, or an error message if unsuccessful.
+    """
+    # System message to define the assistant's role
+    system_message = (
+        "You are a highly creative short story writer capable of crafting stories across any genre. "
+        "For every story created, ensure you generate a suitable title."
+    )
+
+    # Construct the user prompt
+    prompt = (
+        f"Write a creative short story of approximately {length} words in the {genre} genre. "
+        f"Use a {writing_style} writing style with a {tone} tone. "
+        f"The story should revolve around the theme of {theme}. "
+        f"Ensure the narrative is compelling and includes a suitable title."
+    )
+
+    # Retrieve the Hugging Face API key from the environment
+    HUGGINGFACE_API_KEY = os.getenv("HUGGINGFACE_API_KEY")
+    if not HUGGINGFACE_API_KEY:
+        return "Error: Hugging Face API key not found. Please set the HUGGINGFACE_API_KEY environment variable."
+
+    # Initialize the Hugging Face Inference Client
+    try:
+        client = InferenceClient(api_key=HUGGINGFACE_API_KEY)
+    except Exception as e:
+        return f"Error: Failed to initialize Hugging Face client. Details: {e}"
+
+    # Interact with the model
+    try:
+        result = client.chat.completions.create(
+            model="meta-llama/Llama-2-7b-chat-hf",
+            messages=[
+                {"role": "system", "content": system_message},
+                {"role": "user", "content": prompt},
+            ]
+        )
+    except Exception as e:
+        return f"Error: Failed to interact with the model. Details: {e}"
+
+    # Extract the story content from the response
+    if "choices" in result and len(result["choices"]) > 0:
+        return result["choices"][0]["message"]["content"]
+    else:
+        return "Error: No story generated. Please check your prompt or model configuration."
+
+
+
+# Predefined options
+Length = [100, 250, 750]
+Length = [l for l in Length if l >= 100]
+r_length = random.choice(Length)
+
+Genre = [
+    "Fiction", "Nonfiction", "Drama", "Poetry", "Fantasy", "Horror", "Mystery",
+    "Science Fiction", "Suspense", "Women's fiction", "Supernatural/Paranormal", "Young adult"
+]
+r_genre = random.choice(Genre)
+
+Themes = [
+    "Love", "Redemption", "Forgiveness", "Coming of age", "Revenge", "Good vs evil",
+    "Bravery and hardship", "The power of social status", "The destructive nature of love",
+    "The fallibility of the human condition"
+]
+r_themes = random.choice(Themes)
+
+Writing_Styles = ["Expository", "Narrative", "Descriptive", "Persuasive", "Creative"]
+r_Style = random.choice(Writing_Styles)
+
+Tones = ["Formal", "Optimistic", "Worried", "Friendly", "Curious", "Assertive", "Encouraging"]
+r_tones = random.choice(Tones)
+
+
+# Gradio Interface setup
+iface = gr.Interface(
+    fn=chat_short_story,
+    inputs=[
+        gr.Slider(value=100, label="Story_Length", minimum=100, maximum=2500),
+        gr.Dropdown(label="Story_Genre", choices=Genre),
+        gr.Dropdown(label="Story_Theme", choices=Themes),
+        gr.Dropdown(label="Writing_Styles", choices=Writing_Styles),
+        gr.Dropdown(label="Story_Tone", choices=Tones)
     ],
+    outputs=gr.Text(),
+    title="Welcome to the Patrick's Story Generator"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+iface.launch()