Update app.py

app.py

@@ -23,10 +23,19 @@ model = AutoModelForSeq2SeqLM.from_pretrained(MODEL_NAME)
 yolo_model = YOLO(YOLO_MODEL_PATH)  # Load YOLOv8 model
 
 # System Prompt Template
-SYSTEM_PROMPT = """You are a professional financial analyst specializing in cryptocurrency technical analysis. 
-Analyze the following chart elements and provide detailed report with:
+SYSTEM_PROMPT = """
+You are a professional financial analyst specializing in cryptocurrency technical analysis.
+Analyze the following chart elements and provide a detailed report based on the user's question:
 
-1. Trend analysis (primary, secondary trends)
+### Chart Elements:
+Support/Resistance: {support_resistance}
+Trendlines: {trendlines}
+Patterns: {patterns}
+Candlestick formations: {candlesticks}
+
+### User Question:
+{question}
+1. Trend analysis (primary and secondary trends)
 2. Key support/resistance levels
 3. Detected chart patterns
 4. Candlestick formations
@@ -34,9 +43,8 @@ Analyze the following chart elements and provide detailed report with:
 6. Trading signals with confidence levels
 7. Risk management suggestions
 
-Format response in markdown with clear sections. Use professional trading terminology.
-Current Elements Detected: {elements}
-User Question: {question}"""
+Format the response in markdown with clear sections, using professional trading terminology.
+"""
 
 # Chart Analysis Functions
 def preprocess_image(image):
@@ -58,36 +66,38 @@ def preprocess_image(image):
     return enhanced
 
 def detect_chart_elements(image):
-    # Perform object detection on the chart image
-    results = yolo_model(image)  # Object detection using YOLOv8
+    # Detect technical patterns using YOLO model
+    detections = chart_detector(image)
     
     elements = {
         'support_resistance': [],
         'trendlines': [],
         'patterns': [],
         'candlesticks': [],
-        'key_levels': []
     }
     
-    for result in results:
-        for detection in result.boxes:
-            label = detection.cls  # Class label for the detected object
-            confidence = detection.conf  # Confidence score
-            
-            if confidence > 0.5:  # Filter by confidence level (adjust threshold as needed)
-                if 'support' in label:
-                    elements['support_resistance'].append(label)
-                elif 'trendline' in label:
-                    elements['trendlines'].append(label)
-                elif 'pattern' in label:
-                    elements['patterns'].append(label)
-                elif 'candlestick' in label:
-                    elements['candlesticks'].append(label)
-
+    # Process model detections
+    for det in detections:
+        label = det['label']
+        if 'support' in label.lower() or 'resistance' in label.lower():
+            elements['support_resistance'].append(label)
+        elif 'trendline' in label.lower():
+            elements['trendlines'].append(label)
+        elif 'pattern' in label.lower():
+            elements['patterns'].append(label.split('_')[0])  # Assuming the pattern name is before '_'
+        elif 'candlestick' in label.lower():
+            elements['candlesticks'].append(label)
+    
     return elements
 
 def generate_llm_response(elements, question):
-    prompt = SYSTEM_PROMPT.format(elements=elements, question=question)
+    prompt = SYSTEM_PROMPT.format(
+        support_resistance="; ".join(elements['support_resistance']),
+        trendlines="; ".join(elements['trendlines']),
+        patterns="; ".join(elements['patterns']),
+        candlesticks="; ".join(elements['candlesticks']),
+        question=question
+    )
     
     inputs = tokenizer(prompt, return_tensors="pt", max_length=1024, truncation=True)
     outputs = model.generate(
@@ -102,60 +112,30 @@ def generate_llm_response(elements, question):
     response = tokenizer.decode(outputs[0], skip_special_tokens=True)
     return response
 
-# Gradio Interface
-def analyze_chart(image, question, chat_history):
+# Gradio Interface Functions
+def respond(image, question, chat_history):
     # Preprocess image
     processed_img = preprocess_image(image)
     
-    # Detect elements
+    # Detect elements in the chart
     elements = detect_chart_elements(processed_img)
     
-    # Generate analysis
-    analysis = generate_llm_response(str(elements), question)
-    
-    # Update chat
-    chat_history.append((question, analysis))
+    # Generate analysis response
+    analysis = generate_llm_response(elements, question)
     
-    # Create annotated image
-    draw = ImageDraw.Draw(image)
-    elements_str = "\n".join([f"{k}: {v}" for k,v in elements.items()])
+    # Update chat history with the user's question and the model's analysis response
+    chat_history.append(("User: " + question, "Assistant: " + analysis))
     
-    return analysis, chat_history, image
+    return chat_history
 
-with gr.Blocks(theme=gr.themes.Soft(), css=".gradio-container {background-color: #f5f5f5}") as demo:
-    with gr.Row():
-        gr.Markdown("# Professional Crypto Chart Analyzer 📊", elem_id="title")
-    
-    with gr.Row():
-        with gr.Column(scale=1):
-            image_input = gr.Image(label="Upload Chart", type="pil", elem_id="upload-box")
-            submit_btn = gr.Button("Analyze", variant="primary")
-        
-        with gr.Column(scale=2):
-            chatbot = gr.Chatbot(
-                label="Analysis Chat",
-                bubble_full_width=False,
-                avatar_images=(
-                    "user.png", 
-                    "assistant.png"
-                ),
-                height=600
-            )
-            question_input = gr.Textbox(
-                label="Ask Technical Questions", 
-                placeholder="Enter your analysis question...",
-                lines=3
-            )
-    
-    with gr.Row():
-        analysis_output = gr.Markdown(label="Technical Analysis Report")
-        annotated_output = gr.Image(label="Annotated Chart", width=800)
-    
-    submit_btn.click(
-        analyze_chart,
-        [image_input, question_input, chatbot],
-        [analysis_output, chatbot, annotated_output]
-    )
+# Gradio Interface
+demo = gr.ChatInterface(
+    fn=respond,
+    chatbot=gr.Chatbot(show_copy_button=True, layout="panel"),
+    title="Crypto Trading Assistant",
+    theme="Nymbo/Nymbo_Theme",
+    textbox=gr.Textbox(label="Ask Technical Questions", placeholder="Enter your analysis question...")
+)
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    demo.launch()