Upload 8 files

app.py

@@ -0,0 +1,336 @@
+"""
+PromptSuite AI
+==============
+
+Deskripsi Proyek:
+-----------------
+PromptSuite AI adalah platform rekayasa prompt modern untuk membandingkan, menganalisis,
+dan memperbaiki prompt secara otomatis ataupun manual, berbasis Large Language Model (LLM) open source.
+Platform ini dirancang untuk peneliti, praktisi AI, developer, dan siapapun yang ingin mengeksplorasi
+efek optimasi prompt terhadap kualitas output AI.
+
+Fitur:
+------
+- Perbandingan output prompt original & hasil refine (multi-tab, side-by-side)
+- Refinement otomatis maupun manual, dengan berbagai metaprompt canggih
+- UI responsif dengan status tombol dinamis & reset otomatis
+- Panel JSON untuk output full response (debug/research)
+- Dukungan custom CSS & styling profesional
+- Bisa dijalankan di lokal, server, maupun cloud
+
+Teknologi:
+----------
+- Gradio advanced + custom JS + modular backend PromptRefiner
+- Fleksibel untuk model apapun (tinggal sesuaikan backend PromptRefiner)
+- Siap untuk pengembangan riset atau industri
+
+"""
+
+import gradio as gr
+
+from prompt_refiner import PemurniPrompt
+from variables import api_token, models, meta_prompts, explanation_markdown, metaprompt_list, metaprompt_explanations, examples
+from custom_css import custom_css
+from themes import IndonesiaTheme
+
+class PromptSuiteAI:
+    def __init__(self, prompt_refiner: PemurniPrompt, custom_css):
+        self.prompt_refiner = prompt_refiner
+        default_model = models[-1] if len(models) >= 1 else models[0] if models else None
+
+        # with gr.Blocks(css=custom_css, theme=gr.themes.Default()) as self.interface:
+        with gr.Blocks(theme=IndonesiaTheme(), css=custom_css) as self.interface:
+            with gr.Column(elem_classes=["container", "title-container"]):
+                # Banner gambar di bagian atas
+                gr.HTML("""
+                  <div style='text-align: center;'>
+                        <img src='https://i.ibb.co/Gv3WDQrw/banner-propmptsuite.jpg' alt='Banner' style='width: 100%; height: auto;'/>
+                    </div>
+                """)
+                gr.Markdown("# PromptSuite AI")
+                gr.Markdown("### Otomatisasi dan Perbandingan Rekayasa Prompt LLM")
+                gr.Markdown("Bandingkan, evaluasi, dan optimasi prompt AI Anda secara praktis dan canggih.")
+                # Keterangan platform
+                gr.Markdown(
+                    """
+                    <span style='font-size:1.03em; color:#ccc'>
+                    PromptSuite AI adalah platform rekayasa prompt modern untuk membandingkan, menganalisis, 
+                    dan memperbaiki prompt secara otomatis ataupun manual, berbasis Large Language Model (LLM) open source.  
+                    Platform ini dirancang untuk peneliti, praktisi AI, developer, dan siapapun yang ingin mengeksplorasi 
+                    efek optimasi prompt terhadap kualitas output AI.
+                    </span>
+                    """
+                )
+
+            # --- KONTENER 2: Input Prompt & Contoh ---
+            with gr.Column(elem_classes=["container", "input-container"]):
+                prompt_text = gr.Textbox(label="Tulis prompt Anda (atau kosongkan untuk melihat metaprompt)", lines=5)
+                with gr.Accordion("Contoh Prompt", open=False, visible=True):     
+                    gr.Examples(examples=examples, inputs=[prompt_text]) 
+                automatic_metaprompt_button = gr.Button(
+                    "Pilih Otomatis Metode Perbaikan",
+                    elem_classes=["button-highlight"]
+                )
+                MetaPrompt_analysis = gr.Markdown()
+
+            # --- KONTENER 3: Pilihan Metaprompt & Penjelasan ---
+            with gr.Column(elem_classes=["container", "meta-container"]):
+                meta_prompt_choice = gr.Radio(
+                    choices=metaprompt_list,
+                    label="Pilih Metaprompt",
+                    value=metaprompt_list[0],
+                    elem_classes=["no-background", "radio-group"]
+                )
+                refine_button = gr.Button(
+                    "Perbaiki Prompt",
+                    elem_classes=["button-waiting"]
+                )
+                with gr.Accordion("Penjelasan Metaprompt", open=False, visible=True): 
+                    gr.Markdown(explanation_markdown)
+
+            # --- KONTENER 4: Analisis & Refined Prompt ---
+            with gr.Column(elem_classes=["container", "analysis-container"]):           
+                gr.Markdown(" ")
+                prompt_evaluation = gr.Markdown()
+                gr.Markdown("### Prompt yang Telah Diperbaiki")
+                refined_prompt = gr.Textbox(
+                    label=" ",
+                    interactive=True,
+                    show_label=True,
+                    show_copy_button=True,
+                )
+                explanation_of_refinements = gr.Markdown()
+
+            # --- KONTENER 5: Pilihan Model & Output Tab ---
+            with gr.Column(elem_classes=["container", "model-container"]):
+                with gr.Row():
+                    apply_model = gr.Dropdown(
+                        choices=models,
+                        value=default_model,
+                        label="Pilih Model",
+                        container=False,
+                        scale=1,
+                        min_width=300
+                    )
+                    apply_button = gr.Button(
+                        "Uji Prompt ke Model",
+                        elem_classes=["button-waiting"]
+                    )
+                gr.Markdown("### Hasil Pada Model Terpilih")
+                with gr.Tabs(elem_classes=["tabs"]):
+                    with gr.TabItem("Perbandingan Output", elem_classes=["tabitem"]):                     
+                        with gr.Row(elem_classes=["output-row"]):
+                            with gr.Column(scale=1, elem_classes=["comparison-column"]):
+                                gr.Markdown("### Output Prompt Asli")
+                                original_output1 = gr.Markdown(
+                                    elem_classes=["output-content"],
+                                    visible=True
+                                )
+                            with gr.Column(scale=1, elem_classes=["comparison-column"]):
+                                gr.Markdown("### Output Prompt Diperbaiki")
+                                refined_output1 = gr.Markdown(
+                                    elem_classes=["output-content"],
+                                    visible=True
+                                )
+                    with gr.TabItem("Output Prompt Asli", elem_classes=["tabitem"]):
+                        with gr.Row(elem_classes=["output-row"]):
+                            with gr.Column(scale=1, elem_classes=["comparison-column"]):
+                                gr.Markdown("### Output Prompt Asli")
+                                original_output = gr.Markdown(
+                                    elem_classes=["output-content"],
+                                    visible=True
+                                )
+                    with gr.TabItem("Output Prompt Diperbaiki", elem_classes=["tabitem"]):
+                        with gr.Row(elem_classes=["output-row"]):
+                            with gr.Column(scale=1, elem_classes=["comparison-column"]):
+                                gr.Markdown("### Output Prompt Diperbaiki")
+                                refined_output = gr.Markdown(
+                                    elem_classes=["output-content"],
+                                    visible=True
+                                )
+                with gr.Accordion("Respons JSON Lengkap", open=False, visible=True):
+                    full_response_json = gr.JSON()
+
+            # ======================= EVENT HANDLER / JS ==========================
+
+            # Handler untuk otomatis memilih metaprompt
+            def automatic_metaprompt(prompt: str):
+                if not prompt.strip():
+                    return "Silakan masukkan prompt untuk dianalisis.", None
+                metaprompt_analysis, recommended_key = self.prompt_refiner.automatic_metaprompt(prompt)
+                return metaprompt_analysis, recommended_key
+
+            # Handler untuk refine prompt manual
+            def refine_prompt(prompt: str, meta_prompt_choice: str):
+                if not prompt.strip():
+                    return ("Tidak ada prompt.", "", "", {})
+                result = self.prompt_refiner.refine_prompt(prompt, meta_prompt_choice)
+                return (
+                    result[0],  # Evaluasi awal prompt
+                    result[1],  # Prompt diperbaiki
+                    result[2],  # Penjelasan perbaikan
+                    result[3]   # Full JSON response
+                )
+
+            # Handler untuk menguji prompt pada model
+            def apply_prompts(original_prompt: str, refined_prompt_: str, model: str):
+                if not original_prompt or not refined_prompt_:
+                    return (
+                        "Silakan isi prompt asli dan hasil refine.",
+                        "Silakan isi prompt asli dan hasil refine.",
+                        "Silakan isi prompt asli dan hasil refine.",
+                        "Silakan isi prompt asli dan hasil refine."
+                    )
+                if not model:
+                    return (
+                        "Pilih model terlebih dahulu.",
+                        "Pilih model terlebih dahulu.",
+                        "Pilih model terlebih dahulu.",
+                        "Pilih model terlebih dahulu."
+                    )
+                try:
+                    original_output = self.prompt_refiner.apply_prompt(original_prompt, model)
+                    refined_output_ = self.prompt_refiner.apply_prompt(refined_prompt_, model)
+                except Exception as e:
+                    err = f"Terjadi error: {str(e)}"
+                    return (err, err, err, err)
+                return (
+                    str(original_output) if original_output else "Tidak ada output.",
+                    str(refined_output_) if refined_output_ else "Tidak ada output.",
+                    str(original_output) if original_output else "Tidak ada output.",
+                    str(refined_output_) if refined_output_ else "Tidak ada output."
+                )
+
+            # --- Event click dan chain JS custom, sama persis dengan kode asli ---
+            automatic_metaprompt_button.click(
+                fn=automatic_metaprompt,
+                inputs=[prompt_text],
+                outputs=[MetaPrompt_analysis, meta_prompt_choice]
+            ).then(
+                fn=lambda: None,
+                inputs=None,
+                outputs=None,
+                js="""
+                    () => {
+                        document.querySelectorAll('.analysis-container textarea, .analysis-container .markdown-text, .model-container .markdown-text, .comparison-output').forEach(el => {
+                            if (el.value !== undefined) {
+                                el.value = '';
+                            } else {
+                                el.textContent = '';
+                            }
+                        });
+                        const allButtons = Array.from(document.querySelectorAll('button')).filter(btn => 
+                            btn.textContent.includes('Pilih Otomatis') || 
+                            btn.textContent.includes('Perbaiki Prompt') || 
+                            btn.textContent.includes('Uji Prompt')
+                        );
+                        allButtons.forEach(btn => btn.classList.remove('button-highlight'));
+                        allButtons[1].classList.add('button-highlight');
+                        allButtons[0].classList.add('button-completed');
+                        allButtons[2].classList.add('button-waiting');
+                    }
+                """
+            )
+
+            refine_button.click(
+                fn=refine_prompt,
+                inputs=[prompt_text, meta_prompt_choice],
+                outputs=[prompt_evaluation, refined_prompt, explanation_of_refinements, full_response_json]
+            ).then(
+                fn=lambda: None,
+                inputs=None,
+                outputs=None,
+                js="""
+                    () => {
+                        document.querySelectorAll('.model-container .markdown-text, .comparison-output').forEach(el => {
+                            if (el.value !== undefined) {
+                                el.value = '';
+                            } else {
+                                el.textContent = '';
+                            }
+                        });
+                        const allButtons = Array.from(document.querySelectorAll('button')).filter(btn => 
+                            btn.textContent.includes('Pilih Otomatis') || 
+                            btn.textContent.includes('Perbaiki Prompt') || 
+                            btn.textContent.includes('Uji Prompt')
+                        );
+                        allButtons.forEach(btn => btn.classList.remove('button-highlight'));
+                        allButtons[2].classList.add('button-highlight');
+                        allButtons[1].classList.add('button-completed');
+                        allButtons[2].classList.remove('button-waiting');
+                    }
+                """
+            )
+
+            apply_button.click(
+                fn=apply_prompts,
+                inputs=[prompt_text, refined_prompt, apply_model],
+                outputs=[original_output, refined_output, original_output1, refined_output1],
+                show_progress=True
+            ).then(
+                fn=lambda: None,
+                inputs=None,
+                outputs=None,
+                js="""
+                    () => {
+                        const allButtons = Array.from(document.querySelectorAll('button')).filter(btn => 
+                            btn.textContent.includes('Pilih Otomatis') || 
+                            btn.textContent.includes('Perbaiki Prompt') || 
+                            btn.textContent.includes('Uji Prompt')
+                        );
+                        allButtons.forEach(btn => btn.classList.remove('button-highlight', 'button-waiting'));
+                        allButtons[2].classList.add('button-completed');
+                        document.querySelectorAll('.comparison-output').forEach(el => {
+                            if (el.parentElement) {
+                                el.parentElement.style.display = 'none';
+                                setTimeout(() => {
+                                    el.parentElement.style.display = 'block';
+                                }, 100);
+                            }
+                        });
+                    }
+                """
+            )
+
+            # Reset ketika input berubah
+            prompt_text.change(
+                fn=lambda: None,
+                inputs=None,
+                outputs=None,
+                js="""
+                    () => {
+                        document.querySelectorAll('.analysis-container textarea, .analysis-container .markdown-text, .model-container .markdown-text, .comparison-output').forEach(el => {
+                            if (el.value !== undefined) {
+                                el.value = '';
+                            } else {
+                                el.textContent = '';
+                            }
+                        });
+                        const allButtons = Array.from(document.querySelectorAll('button')).filter(btn => 
+                            btn.textContent.includes('Pilih Otomatis') || 
+                            btn.textContent.includes('Perbaiki Prompt') || 
+                            btn.textContent.includes('Uji Prompt')
+                        );
+                        allButtons.forEach(btn => {
+                            btn.classList.remove('button-completed', 'button-highlight', 'button-waiting');
+                        });
+                        allButtons[0].classList.add('button-highlight');
+                        allButtons.slice(1).forEach(btn => btn.classList.add('button-waiting'));
+                    }
+                """
+            )
+
+    def launch(self, share=False):
+        """Jalankan antarmuka PromptSuite AI"""
+        self.interface.launch(share=share)
+
+
+if __name__ == '__main__':
+    prompt_refiner = PemurniPrompt(api_token, meta_prompts, metaprompt_explanations)
+    app = PromptSuiteAI(prompt_refiner, custom_css)
+    app.launch(share=False)
+
+
+
+
+# Author: __drat (c)2025

custom_css.py

@@ -0,0 +1,52 @@
+# File ini awalnya digunakan untuk menyimpan custom CSS untuk tampilan Gradio.
+# Namun, sesuai instruksi, aplikasi sekarang tidak menggunakan CSS custom sama sekali.
+# Tidak perlu mengisi kode apapun di file ini.
+
+custom_css = """
+#col-left, #col-mid {
+    margin: 0 auto;
+    max-width: 400px;
+    padding: 10px;
+    border-radius: 15px;
+    background-color: #f9f9f9;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+}
+#col-right {
+    margin: 0 auto;
+    max-width: 400px;
+    padding: 10px;
+    border-radius: 15px;
+    background: linear-gradient(180deg, #B6BBC4, #EEEEEE);
+    color: white;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+}
+#col-bott {
+    margin: 0 auto;
+    padding: 10px;
+    border-radius: 15px;
+    background-color: #f9f9f9;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
+}
+#banner {
+    width: 100%;
+    text-align: center;
+    margin-bottom: 20px;
+}
+#run-button {
+    background-color: #ff4b5c;
+    color: white;
+    font-weight: bold;
+    padding: 30px;
+    border-radius: 10px;
+    cursor: pointer;
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.2);
+}
+#footer {
+    text-align: center;
+    margin-top: 20px;
+    color: silver;
+}
+#markdown-silver {
+    color: silver; /* Mengatur warna font Markdown menjadi silver */
+}
+"""

metaprompt_router.py

@@ -0,0 +1,130 @@
+
+def generate_metaprompt_router(methods_dict):
+  # Start with the base template
+  router_template = """
+You are an AI Prompt Selection Assistant. Your task is to analyze the user's query and recommend the most appropriate metaprompt from the following list based on the nature of the request. Provide your response in a structured JSON format.
+
+**Metaprompt List:**
+"""
+  
+  # Add each method to the template
+  for i, (key, method) in enumerate(methods_dict.items(), 1):
+      method_template = f"""
+{i}. **{key}**
+- **Name**: {method['name']}
+- **Description**: {method['description']}
+- **Sample**: {', '.join(f'"{example}"' for example in method.get('examples', []))}
+"""
+      router_template += method_template
+  
+  # Add the output format template
+  router_template += """
+For this given user query:
+[Insert initial prompt here]
+
+Analyze the query and provide your recommendation in the following JSON format enclosed in <json> tags:
+
+<json>
+{
+"user_query": "The original query from the user",
+"recommended_metaprompt": {
+    "key": "Key of the recommended metaprompt",
+    "name": "Name of the recommended metaprompt",
+    "description": "Brief description of the metaprompt's purpose",
+    "explanation": "Detailed explanation of why this metaprompt is the best fit for this specific query, including how it addresses the query's unique requirements and challenges",
+    "similar_sample": "If available, a sample use case from the list that's most similar to the user's query",
+    "customized_sample": "A new sample specifically tailored to the user's query using this metaprompt approach"
+},
+"alternative_recommendation": {
+    "key": "Key of the second-best metaprompt option",
+    "name": "Name of the second-best metaprompt option",
+    "explanation": "Brief explanation of why this could be an alternative choice and what specific benefits it might offer for this query"
+}
+}
+</json>
+"""
+  
+  return router_template
+
+# Generate the router configuration
+#metaprompt_router = generate_metaprompt_router(methods_dict)  # methods_dict is your full file dictionary
+
+
+metaprompt_router = """
+You are an AI Prompt Selection Assistant. Your task is to analyze the user's query and recommend the most appropriate metaprompt from the available methods. Each method has specific strengths and use cases.
+
+**Metaprompt List:**
+1. **comprehensive_multistage**
+- **Name**: Comprehensive Multi-Stage Refinement
+- **Description**: Use this method for a thorough, multi-stage refinement process. Ideal for complex prompts requiring in-depth analysis, exploration of alternatives, and synthesis of ideas. Best when time allows for detailed refinement and consideration of various aspects.
+- **Sample**: "Design a comprehensive educational curriculum for teaching artificial intelligence to high school students", "Develop a detailed analysis of climate change impacts on global agriculture over the next 50 years"
+
+2. **structured_roleplaying**
+- **Name**: Structured Role-Playing Enhancement
+- **Description**: Opt for this when you need a structured approach with emphasis on role-playing and advanced techniques. Useful for tasks benefiting from diverse perspectives and complex reasoning.
+- **Sample**: "Create a dialogue between Einstein and a modern AI researcher discussing the future of quantum computing", "Simulate a strategic planning meeting between historical business leaders solving current tech industry challenges"
+
+3. **balanced_scientific**
+- **Name**: Balanced Scientific Structuring
+- **Description**: Choose this for a balance between structure and advanced techniques, with a focus on role-playing. Suitable for scientific or technical prompts.
+- **Sample**: "Explain how CRISPR gene editing technology works and its potential applications in medicine", "Analyze the psychological and neurological factors that influence decision-making in high-pressure situations"
+
+4. **quick_simplified**
+- **Name**: Quick Simplified Refinement
+- **Description**: Use this simplified approach for straightforward prompts or when time is limited. Focuses on essential improvements without complex techniques.
+- **Sample**: "What are the key differences between renewable and non-renewable energy sources?", "Explain the basic principles of machine learning in simple terms"
+
+5. **logical_flow**
+- **Name**: Logical Flow Enhancement
+- **Description**: Choose this method to analyze and improve a prompt's strengths and weaknesses, focusing on information flow. Useful for enhancing the logical structure of prompts.
+- **Sample**: "Break down the process of implementing a sustainable urban transportation system", "Analyze the cause-and-effect relationship between social media use and mental health"
+
+6. **flexible_technique**
+- **Name**: Flexible Technique Integration
+- **Description**: Employ this advanced approach to combine multiple prompt engineering techniques. Ideal for complex tasks requiring both clarity and sophisticated methods.
+- **Sample**: "Create a comprehensive guide for starting a tech startup, including business, technical, and marketing aspects", "Design a multi-phase approach to teaching critical thinking skills in different educational contexts"
+
+7. **autoregressive_reasoning**
+- **Name**: Autoregressive Reasoning Optimization
+- **Description**: Utilize this method for tasks requiring careful reasoning before conclusions. Best for prompts needing detailed output formatting.
+- **Sample**: "Develop a step-by-step analysis of market trends to predict future investment opportunities", "Create a systematic approach to debugging complex software systems"
+
+8. **mathematical_proof**
+- **Name**: Mathematical Proof Structuring
+- **Description**: Specialized approach for mathematical and formal proofs. Use this for tasks requiring a logical, step-by-step prompt engineering process.
+- **Sample**: "Prove the relationship between energy and mass in Einstein's E=mc²", "Demonstrate the mathematical principles behind modern encryption methods"
+
+9. **sequential_contextual**
+- **Name**: Sequential Contextual Enhancement
+- **Description**: Advanced reasoning and proof engineering approach. Focuses on systematic prompt enhancement through structured analysis, enhancement protocols, and validation. Ideal for complex tasks requiring thorough documentation and systematic improvements.
+- **Sample**: "Create a framework for analyzing the long-term societal impacts of artificial intelligence", "Develop a systematic approach to evaluating and improving corporate sustainability practices"
+
+10. **attention_aware**
+- **Name**: Attention-Aware Positioning
+- **Description**: Token-efficient prompt optimization focusing on attention positioning and context management. Best for tasks requiring careful information placement and progressive context building while maintaining efficiency.
+- **Sample**: "Design a progressive learning curriculum that builds complex concepts from fundamental principles", "Create a narrative structure for explaining quantum physics concepts to general audiences"
+
+For this given user query:
+[Insert initial prompt here]
+
+Analyze the query and provide your recommendation in the following JSON format enclosed in <json> tags:
+
+<json>
+{
+"user_query": "The original query from the user",
+"recommended_metaprompt": {
+    "key": "Key of the recommended metaprompt",
+    "name": "Name of the recommended metaprompt",
+    "description": "Brief description of the metaprompt's purpose",
+    "explanation": "Detailed explanation of why this metaprompt is the best fit for this specific query, including how it addresses the query's unique requirements and challenges",
+    "similar_sample": "If available, a sample use case from the list that's most similar to the user's query",
+    "customized_sample": "A new sample specifically tailored to the user's query using this metaprompt approach"
+},
+"alternative_recommendation": {
+    "key": "Key of the second-best metaprompt option",
+    "name": "Name of the second-best metaprompt option",
+    "explanation": "Brief explanation of why this could be an alternative choice and what specific benefits it might offer for this query"
+}
+}
+</json>
+"""

metaprompt_sample.py

@@ -0,0 +1,57 @@
+openai_metaprompt='''
+Given a task description or existing prompt, produce a detailed system prompt to guide a language model in completing the task effectively.
+
+Initial Prompt: [Insert initial prompt here]
+
+# Guidelines
+
+- Understand the Task: Grasp the main objective, goals, requirements, constraints, and expected output.
+- Minimal Changes: If an existing prompt is provided, improve it only if it's simple. For complex prompts, enhance clarity and add missing elements without altering the original structure.
+- Reasoning Before Conclusions**: Encourage reasoning steps before any conclusions are reached. ATTENTION! If the user provides examples where the reasoning happens afterward, REVERSE the order! NEVER START EXAMPLES WITH CONCLUSIONS!
+    - Reasoning Order: Call out reasoning portions of the prompt and conclusion parts (specific fields by name). For each, determine the ORDER in which this is done, and whether it needs to be reversed.
+    - Conclusion, classifications, or results should ALWAYS appear last.
+- Examples: Include high-quality examples if helpful, using placeholders [in brackets] for complex elements.
+   - What kinds of examples may need to be included, how many, and whether they are complex enough to benefit from placeholders.
+- Clarity and Conciseness: Use clear, specific language. Avoid unnecessary instructions or bland statements.
+- Formatting: Use markdown features for readability. DO NOT USE ``` CODE BLOCKS UNLESS SPECIFICALLY REQUESTED.
+- Preserve User Content: If the input task or prompt includes extensive guidelines or examples, preserve them entirely, or as closely as possible. If they are vague, consider breaking down into sub-steps. Keep any details, guidelines, examples, variables, or placeholders provided by the user.
+- Constants: DO include constants in the prompt, as they are not susceptible to prompt injection. Such as guides, rubrics, and examples.
+- Output Format: Explicitly the most appropriate output format, in detail. This should include length and syntax (e.g. short sentence, paragraph, JSON, etc.)
+    - For tasks outputting well-defined or structured data (classification, JSON, etc.) bias toward outputting a JSON.
+    - JSON should never be wrapped in code blocks (```) unless explicitly requested.
+
+The final prompt you output should adhere to the following structure below. Do not include any additional commentary, only output the completed system prompt. SPECIFICALLY, do not include any additional messages at the start or end of the prompt. (e.g. no "---")
+
+[Concise instruction describing the task - this should be the first line in the prompt, no section header]
+
+[Additional details as needed.]
+
+[Optional sections with headings or bullet points for detailed steps.]
+
+# Steps [optional]
+
+[optional: a detailed breakdown of the steps necessary to accomplish the task]
+
+# Output Format
+
+[Specifically call out how the output should be formatted, be it response length, structure e.g. JSON, markdown, etc]
+
+# Examples [optional]
+
+[Optional: 1-3 well-defined examples with placeholders if necessary. Clearly mark where examples start and end, and what the input and output are. User placeholders as necessary.]
+[If the examples are shorter than what a realistic example is expected to be, make a reference with () explaining how real examples should be longer / shorter / different. AND USE PLACEHOLDERS! ]
+
+# Notes [optional]
+
+[optional: edge cases, details, and an area to call or repeat out specific important considerations]
+
+Only provide the output in the following JSON format enclosed in <json> tags:
+
+<json>
+{
+"initial_prompt_evaluation": "Your evaluation of the initial prompt with Strengths and Weaknesses in a string on markdown bullet points format",
+"refined_prompt": "Your refined prompt",
+"explanation_of_refinements": "Explanation of the techniques used and improvements made, also include the extract of final prompt where it made. Answer in bullet points if accurate. Output in a single comprehensive string"
+}
+</json>
+'''

prompt_refiner.py

@@ -0,0 +1,64 @@
+# Kelas PemurniPrompt digunakan untuk menganalisis dan memperbaiki prompt sesuai metode/metaprompt yang dipilih pengguna
+
+class PemurniPrompt:
+    def __init__(self, api_token, meta_prompts, metaprompt_explanations):
+        self.api_token = api_token
+        self.meta_prompts = meta_prompts
+        self.metaprompt_explanations = metaprompt_explanations
+
+    def automatic_metaprompt(self, prompt):
+        """
+        Otomatis memilih metaprompt terbaik berdasarkan isi prompt user.
+        Return tuple: (analisis, saran_metaprompt)
+        """
+        # Algoritma dummy — bisa di-upgrade sesuai kebutuhan!
+        if not prompt or prompt.strip() == "":
+            return "Prompt kosong. Silakan isi prompt.", None
+
+        # Heuristik sederhana: Jika panjang, pilih comprehensive_multistage, jika mengandung 'data', pilih balanced_scientific
+        if "data" in prompt.lower():
+            analisis = "Prompt ini berkaitan dengan data, disarankan 'balanced_scientific'."
+            return analisis, "balanced_scientific"
+        elif len(prompt.split()) > 25:
+            analisis = "Prompt cukup kompleks, disarankan 'comprehensive_multistage'."
+            return analisis, "comprehensive_multistage"
+        else:
+            analisis = "Prompt normal, gunakan 'logical_flow' untuk hasil optimal."
+            return analisis, "logical_flow"
+
+    def refine_prompt(self, prompt, metaprompt_key):
+        """
+        Melakukan perbaikan prompt secara manual dengan metaprompt terpilih.
+        Return: (evaluasi, prompt_baru, penjelasan, full_response)
+        """
+        if not prompt or prompt.strip() == "":
+            return ("Tidak ada prompt yang diberikan.", "", "", {})
+
+        # Dummy refining — gabungkan template metaprompt dengan prompt user
+        template = self.meta_prompts.get(metaprompt_key, "")
+        if template:
+            prompt_baru = f"{template.strip()}\n{prompt.strip()}"
+        else:
+            prompt_baru = f"[{metaprompt_key}]\n{prompt.strip()}"
+
+        evaluasi = f"Prompt telah diperbaiki menggunakan metaprompt '{metaprompt_key}'."
+        penjelasan = self.metaprompt_explanations.get(metaprompt_key, "Tidak ada penjelasan tersedia.")
+        full_response = {
+            "prompt_awal": prompt,
+            "prompt_baru": prompt_baru,
+            "metaprompt": metaprompt_key,
+            "evaluasi": evaluasi,
+            "penjelasan": penjelasan
+        }
+        return (evaluasi, prompt_baru, penjelasan, full_response)
+
+    def apply_prompt(self, prompt, model):
+        """
+        Mensimulasikan pengujian prompt pada model LLM.
+        Return: string output hasil 'jawaban model'
+        """
+        if not prompt or not model:
+            return "Prompt atau model kosong."
+
+        # Dummy output — ganti dengan pemanggilan API model Anda jika siap
+        return f"(MODEL: {model})\nHASIL:\n{prompt[:400]} ...[Output simulasi LLM]"

requirements.txt

@@ -0,0 +1,7 @@
+transformers 
+torch
+gradio
+httpx==0.24.1
+accelerate>=0.26.0
+tenacity
+pydantic

themes.py

@@ -0,0 +1,54 @@
+from __future__ import annotations
+from typing import Iterable
+from gradio.themes.base import Base
+from gradio.themes.utils import colors, fonts, sizes
+
+class IndonesiaTheme(Base):
+    def __init__(
+        self,
+        *,
+        primary_hue: colors.Color | str = colors.red,
+        secondary_hue: colors.Color | str = colors.gray,
+        neutral_hue: colors.Color | str = colors.gray,
+        spacing_size: sizes.Size | str = sizes.spacing_md,
+        radius_size: sizes.Size | str = sizes.radius_md,
+        text_size: sizes.Size | str = sizes.text_lg,
+        font: fonts.Font
+        | str
+        | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("Quicksand"),
+            "ui-sans-serif",
+            "sans-serif",
+        ),
+        font_mono: fonts.Font
+        | str
+        | Iterable[fonts.Font | str] = (
+            fonts.GoogleFont("IBM Plex Mono"),
+            "ui-monospace",
+            "monospace",
+        ),
+    ):
+        super().__init__(
+            primary_hue=primary_hue,
+            secondary_hue=secondary_hue,
+            neutral_hue=neutral_hue,
+            spacing_size=spacing_size,
+            radius_size=radius_size,
+            text_size=text_size,
+            font=font,
+            font_mono=font_mono,
+        )
+        super().set(
+            body_background_fill="linear-gradient(to bottom, #e0e0e0, #7d7d7d)",  # Gradasi abu-abu muda ke abu-abu tua
+            body_background_fill_dark="linear-gradient(to bottom, #7d7d7d, #4a4a4a)",  # Gradasi abu-abu tua ke lebih gelap untuk dark mode
+            button_primary_background_fill="linear-gradient(90deg, #d84a4a, #b33030)",  # Merah ke merah tua
+            button_primary_background_fill_hover="linear-gradient(90deg, #e85b5b, #cc4b4b)",  # Merah lebih terang untuk hover
+            button_primary_text_color="white",
+            button_primary_background_fill_dark="linear-gradient(90deg, #b33030, #8f1f1f)",  # Merah tua untuk dark mode
+            slider_color="*secondary_300",
+            slider_color_dark="*secondary_600",
+            block_title_text_weight="600",
+            block_border_width="3px",
+            block_shadow="*shadow_drop_lg",
+            button_large_padding="32px",
+        )

variables.py

@@ -0,0 +1,121 @@
+import json
+import os
+
+# --- Cek variabel lingkungan untuk templates ---
+template_json = os.getenv('PROMPT_TEMPLATES', '{}')
+
+try:
+    # Parsing data JSON dengan penanganan error
+    data_prompt = json.loads(template_json)
+except json.JSONDecodeError:
+    # Jika JSON tidak valid, fallback ke dict kosong
+    data_prompt = {}
+
+# --- Daftar metaprompt Fallback (10 yang Deddy minta) ---
+daftar_metaprompt_fallback = [
+    "comprehensive_multistage",
+    "structured_roleplaying",
+    "balanced_scientific",
+    "quick_simplified",
+    "logical_flow",
+    "flexible_technique",
+    "autoregressive_reasoning",
+    "mathematical_proof",
+    "sequential_contextual",
+    "attention_aware"
+]
+
+# --- Deskripsi fallback untuk tiap metaprompt ---
+penjelasan_metaprompt_fallback = {
+    "comprehensive_multistage": "Pendekatan multi-tahap yang komprehensif dan bertingkat.",
+    "structured_roleplaying": "Simulasi peran dengan struktur yang jelas.",
+    "balanced_scientific": "Keseimbangan antara sains, logika, dan objektivitas.",
+    "quick_simplified": "Hasil cepat dan penyederhanaan dalam eksekusi.",
+    "logical_flow": "Alur berpikir yang logis dan runtut.",
+    "flexible_technique": "Teknik adaptif, fleksibel untuk berbagai kasus.",
+    "autoregressive_reasoning": "Penalaran progresif, tahap demi tahap.",
+    "mathematical_proof": "Pendekatan matematis dan pembuktian formal.",
+    "sequential_contextual": "Proses bertahap dan mempertimbangkan konteks.",
+    "attention_aware": "Memaksimalkan fokus dan perhatian pada poin penting."
+}
+
+# --- Prioritaskan dari JSON ENV jika ada, jika tidak fallback ke default di atas ---
+if data_prompt:
+    daftar_metaprompt = [kunci for kunci in data_prompt.keys()]
+    penjelasan_metaprompt = {
+        kunci: data.get("description", "Tidak ada deskripsi")
+        for kunci, data in data_prompt.items()
+    }
+else:
+    daftar_metaprompt = daftar_metaprompt_fallback
+    penjelasan_metaprompt = penjelasan_metaprompt_fallback
+
+print("Daftar Metaprompt:", daftar_metaprompt)
+
+# --- Markdown penjelasan untuk UI ---
+penjelasan_markdown = "".join([
+    f"- **{kunci}**: {isi}\n"
+    for kunci, isi in penjelasan_metaprompt.items()
+])
+
+# --- Daftar model yang tersedia ---
+daftar_model = [
+    "meta-llama/Meta-Llama-3-70B-Instruct",
+    "meta-llama/Meta-Llama-3-8B-Instruct",
+    "meta-llama/Llama-3.1-70B-Instruct",
+    "meta-llama/Llama-3.1-8B-Instruct",
+    "meta-llama/Llama-3.2-3B-Instruct",
+    "meta-llama/Llama-3.2-1B-Instruct",
+    "meta-llama/Llama-2-13b-chat-hf",
+    "meta-llama/Llama-2-7b-chat-hf",
+    "HuggingFaceH4/zephyr-7b-beta",
+    "HuggingFaceH4/zephyr-7b-alpha",
+    "Qwen/Qwen2.5-72B-Instruct",
+    "Qwen/Qwen2.5-1.5B",
+    "microsoft/Phi-3.5-mini-instruct"
+]
+
+# --- Mengambil contoh prompt dari JSON templates (jika ada) ---
+contoh_prompt = []
+for kunci, data in data_prompt.items():
+    contoh_template = data.get("examples", [])
+    if contoh_template:
+        contoh_prompt.extend([
+            [contoh[0], kunci] if isinstance(contoh, list) else [contoh, kunci]
+            for contoh in contoh_template
+        ])
+
+# --- Token API ---
+api_token = os.getenv('HF_API_TOKEN')
+if not api_token:
+    raise ValueError("HF_API_TOKEN tidak ditemukan di environment variable")
+
+# --- Dictionary meta_prompts (template prompt) ---
+meta_prompts = {
+    kunci: data.get("template", "Template tidak tersedia")
+    for kunci, data in data_prompt.items()
+} if data_prompt else {k: "" for k in daftar_metaprompt}
+
+# --- Model default untuk refiner, dari env atau fallback ---
+model_refiner_prompt = os.getenv('prompt_refiner_model', 'meta-llama/Llama-3.1-8B-Instruct')
+print("Model refiner prompt yang digunakan:", model_refiner_prompt)
+
+# --- Variabel tambahan dari environment jika ada ---
+echo_refiner_prompt = os.getenv('echo_prompt_refiner')
+openai_metaprompt = os.getenv('openai_metaprompt')
+metaprompt_lanjut = os.getenv('advanced_meta_prompt')
+
+# --- Ekspor alias variabel supaya tetap kompatibel dengan app.py ---
+metaprompt_list = daftar_metaprompt
+explanation_markdown = penjelasan_markdown
+models = daftar_model
+
+examples = [
+    ["Buatlah ringkasan mendalam mengenai dampak revolusi industri 4.0 terhadap pola kerja masyarakat urban di Indonesia, dengan menyoroti perubahan sosial, ekonomi, serta tantangan sumber daya manusia di era digital.", "comprehensive_multistage"],
+    ["Bertindaklah sebagai pakar komunikasi publik dan simulasi tanya jawab antara seorang menteri dan wartawan terkait isu kenaikan harga bahan pokok, lengkap dengan dialog dan argumentasi masing-masing pihak.", "structured_roleplaying"],
+    ["Analisis secara kritis data pertumbuhan ekonomi Indonesia dalam lima tahun terakhir, dan jelaskan faktor-faktor utama yang mempengaruhi fluktuasi angka tersebut secara ilmiah dan objektif.", "balanced_scientific"],
+    ["Sederhanakan penjelasan tentang blockchain sehingga mudah dipahami oleh pelajar SMA, namun tetap mencakup mekanisme dasar, manfaat, serta potensi risikonya.", "quick_simplified"],
+    ["Jelaskan urutan logis proses produksi energi listrik dari sumber energi terbarukan, mulai dari tahap input sumber daya, konversi energi, distribusi, hingga konsumsi akhir oleh masyarakat.", "logical_flow"]
+]
+metaprompt_explanations = penjelasan_metaprompt
+