Upload 2 files

app.py

@@ -0,0 +1,93 @@
+import gradio as gr
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+import os
+
+# ============================================================
+# CONFIG
+# ============================================================
+REPO_ID  = "Wessym/prompt-refiner-mistral7b-Q4_K_M-GGUF"
+FILENAME = "prompt-refiner-mistral7b-Q4_K_M.gguf"
+
+SYSTEM_PROMPT = (
+    'You are an expert Prompt Engineer. '
+    'Your role is to analyze user inputs and either:\n\n'
+    '1. REFINE valid prompts into a structured format with these exact sections:\n'
+    '   [ROLE]: Who should respond\n'
+    '   [CONTEXT]: Background and environment\n'
+    '   [TASK]: What exactly needs to be done\n'
+    '   [CONSTRAINTS/STYLE]: Style, tone, format constraints\n'
+    '   [VARIABLES]: Customizable parameters\n'
+    '   [OUTPUT FORMAT]: Expected structure of the output\n\n'
+    '   For French inputs use: '
+    '[RÔLE], [CONTEXTE], [TÂCHE], [CONTRAINTES/STYLE], [VARIABLES], [FORMAT DE SORTIE]\n\n'
+    '2. DETECT and REJECT invalid inputs using the same structure but with:\n'
+    '   [ROLE]: Prompt Validator (or [RÔLE]: Validateur de Prompt)\n'
+    '   [OUTPUT FORMAT]: INVALID — <TYPE> — <Reason> | Suggestion: <tip>\n\n'
+    '   Invalid types: RANDOM_CHARS, NUMBERS_ONLY, PUNCTUATION_ONLY, SOCIAL_GREETING,\n'
+    '   TOO_VAGUE, ETHICAL_REFUSAL, REPEATED_CHARS, GENERAL_QUESTION\n\n'
+    'Always respond in the same language as the input.'
+)
+
+# ============================================================
+# CHARGEMENT DU MODELE (une seule fois au démarrage)
+# ============================================================
+print("Chargement du modèle...")
+model_path = hf_hub_download(
+    repo_id  = REPO_ID,
+    filename = FILENAME,
+    token    = os.environ.get("HF_TOKEN"),
+)
+
+llm = Llama(
+    model_path   = model_path,
+    n_ctx        = 2048,
+    n_threads    = 4,
+    n_gpu_layers = 0,
+    verbose      = False,
+)
+print("Modèle chargé ✅")
+
+# ============================================================
+# FONCTION PRINCIPALE
+# ============================================================
+def refine_prompt(user_input: str) -> str:
+    if not user_input.strip():
+        return "❌ Veuillez entrer un prompt."
+
+    prompt = f"<s>[INST] {SYSTEM_PROMPT}\n\nUser input to process: {user_input} [/INST]"
+
+    response = llm(
+        prompt,
+        max_tokens     = 512,
+        temperature    = 0.3,
+        top_p          = 0.9,
+        repeat_penalty = 1.1,
+        stop           = ["</s>", "[INST]"],
+    )
+    return response["choices"][0]["text"].strip()
+
+# ============================================================
+# INTERFACE GRADIO
+# ============================================================
+with gr.Blocks(title="Prompt Refiner") as demo:
+    gr.Markdown("# 🚀 Prompt Refiner\nEntre ton prompt et il sera structuré automatiquement.")
+
+    with gr.Row():
+        input_box  = gr.Textbox(label="Ton prompt", placeholder="Ex: Crée un script YouTube sur l'IA...", lines=3)
+        output_box = gr.Textbox(label="Prompt raffiné", lines=10)
+
+    btn = gr.Button("Raffiner ✨", variant="primary")
+    btn.click(fn=refine_prompt, inputs=input_box, outputs=output_box)
+
+    gr.Examples(
+        examples=[
+            ["Create a YouTube script about AI for beginners"],
+            ["Rédige un article de blog sur le marketing digital"],
+            ["bonjour je mappelle wassim"],
+            ["qsdqsdqsdqs"],
+        ],
+        inputs=input_box,
+    )
+
+demo.launch()

requirements.txt

@@ -0,0 +1,3 @@
+gradio
+huggingface_hub
+llama-cpp-python