import os import gradio as gr import re import folium from fastai.vision.all import * from groq import Groq from PIL import Image # Load the trained model learn = load_learner('export.pkl') labels = learn.dls.vocab # Initialize Groq client client = Groq( api_key=os.environ.get("GROQ_API_KEY"), ) def clean_bird_name(name): """Clean bird name by removing numbers and special characters, and fix formatting""" # Remove numbers and dots at the beginning cleaned = re.sub(r'^\d+\.', '', name) # Replace underscores with spaces cleaned = cleaned.replace('_', ' ') # Remove any remaining special characters cleaned = re.sub(r'[^\w\s]', '', cleaned) # Fix spacing cleaned = ' '.join(cleaned.split()) return cleaned def get_bird_habitat_map(bird_name, check_tanzania=True): """Get habitat map locations for the bird using Groq API""" clean_name = clean_bird_name(bird_name) # First check if the bird is endemic to Tanzania if check_tanzania: tanzania_check_prompt = f""" Is the {clean_name} bird native to or commonly found in Tanzania? Answer with ONLY "yes" or "no". """ try: tanzania_check = client.chat.completions.create( messages=[{"role": "user", "content": tanzania_check_prompt}], model="llama-3.3-70b-versatile", ) is_in_tanzania = "yes" in tanzania_check.choices[0].message.content.lower() except: # Default to showing Tanzania if we can't determine is_in_tanzania = True else: is_in_tanzania = True # Now get the habitat locations prompt = f""" Provide a JSON array of the main habitat locations for the {clean_name} bird in the world. Return ONLY a JSON array with 3-5 entries, each containing: 1. "name": Location name 2. "lat": Latitude (numeric value) 3. "lon": Longitude (numeric value) 4. "description": Brief description of why this is a key habitat (2-3 sentences) Example format: [ {{"name": "Example Location", "lat": 12.34, "lon": 56.78, "description": "Brief description"}}, ... ] {'' if is_in_tanzania else 'DO NOT include any locations in Tanzania as this bird is not native to or commonly found there.'} """ try: chat_completion = client.chat.completions.create( messages=[ { "role": "user", "content": prompt, } ], model="llama-3.3-70b-versatile", ) response = chat_completion.choices[0].message.content # Extract JSON from response (in case there's additional text) import json import re # Find JSON pattern in response json_match = re.search(r'\[.*\]', response, re.DOTALL) if json_match: locations = json.loads(json_match.group()) else: # Fallback if JSON extraction fails locations = [ {"name": "Primary habitat region", "lat": 0, "lon": 0, "description": "Could not retrieve specific habitat information for this bird."} ] return locations, is_in_tanzania except Exception as e: return [{"name": "Error retrieving data", "lat": 0, "lon": 0, "description": "Please try again or check your connection."}], False def create_habitat_map(habitat_locations): """Create a folium map with the habitat locations""" # Find center point based on valid coordinates valid_coords = [(loc.get("lat", 0), loc.get("lon", 0)) for loc in habitat_locations if loc.get("lat", 0) != 0 or loc.get("lon", 0) != 0] if valid_coords: # Calculate the average of the coordinates avg_lat = sum(lat for lat, _ in valid_coords) / len(valid_coords) avg_lon = sum(lon for _, lon in valid_coords) / len(valid_coords) # Create map centered on the average coordinates m = folium.Map(location=[avg_lat, avg_lon], zoom_start=3) else: # Default world map if no valid coordinates m = folium.Map(location=[20, 0], zoom_start=2) # Add markers for each habitat location for location in habitat_locations: name = location.get("name", "Unknown") lat = location.get("lat", 0) lon = location.get("lon", 0) description = location.get("description", "No description available") # Skip invalid coordinates if lat == 0 and lon == 0: continue # Add marker folium.Marker( location=[lat, lon], popup=folium.Popup(f"{name}
{description}", max_width=300), tooltip=name ).add_to(m) # Save map to HTML map_html = m._repr_html_() return map_html def format_bird_info(raw_info): """Improve the formatting of bird information""" # Add proper line breaks between sections and ensure consistent heading levels formatted = raw_info # Fix heading levels (make all main sections h3) formatted = re.sub(r'#+\s+NOT TYPICALLY FOUND IN TANZANIA', '
⚠️ NOT TYPICALLY FOUND IN TANZANIA
', formatted) # Replace markdown headings with HTML headings for better control formatted = re.sub(r'#+\s+(.*)', r'

\1

', formatted) # Add paragraph tags for better spacing formatted = re.sub(r'\n\*\s+(.*)', r'

• \1

', formatted) formatted = re.sub(r'\n([^<\n].*)', r'

\1

', formatted) # Remove any duplicate paragraph tags formatted = formatted.replace('

', '

') formatted = formatted.replace('

', '

') return formatted def get_bird_info(bird_name): """Get detailed information about a bird using Groq API""" clean_name = clean_bird_name(bird_name) prompt = f""" Provide detailed information about the {clean_name} bird, including: 1. Physical characteristics and appearance 2. Habitat and distribution 3. Diet and behavior 4. Migration patterns (emphasize if this pattern has changed in recent years due to climate change) 5. Conservation status If this bird is not commonly found in Tanzania, explicitly flag that this bird is "NOT TYPICALLY FOUND IN TANZANIA" at the beginning of your response and explain why its presence might be unusual. Format your response in markdown for better readability. """ try: chat_completion = client.chat.completions.create( messages=[ { "role": "user", "content": prompt, } ], model="llama-3.3-70b-versatile", ) return chat_completion.choices[0].message.content except Exception as e: return f"Error fetching information: {str(e)}" def predict_and_get_info(img): """Predict bird species and get detailed information""" # Process the image img = PILImage.create(img) # Get prediction pred, pred_idx, probs = learn.predict(img) # Get top 5 predictions (or all if less than 5) num_classes = min(5, len(labels)) top_indices = probs.argsort(descending=True)[:num_classes] top_probs = probs[top_indices] top_labels = [labels[i] for i in top_indices] # Format as dictionary with cleaned names for display prediction_results = {clean_bird_name(top_labels[i]): float(top_probs[i]) for i in range(num_classes)} # Get top prediction (original format for info retrieval) top_bird = str(pred) # Also keep a clean version for display clean_top_bird = clean_bird_name(top_bird) # Get habitat locations and create map habitat_locations, is_in_tanzania = get_bird_habitat_map(top_bird) habitat_map_html = create_habitat_map(habitat_locations) # Get detailed information about the top predicted bird bird_info = get_bird_info(top_bird) formatted_info = format_bird_info(bird_info) # Create combined info with map at the top and properly formatted information custom_css = """ """ combined_info = f""" {custom_css}

Natural Habitat Map for {clean_top_bird}

{habitat_map_html}

Detailed Information

{formatted_info}
""" return prediction_results, combined_info, clean_top_bird def follow_up_question(question, bird_name): """Allow researchers to ask follow-up questions about the identified bird""" if not question.strip() or not bird_name: return "Please identify a bird first and ask a specific question about it." prompt = f""" The researcher is asking about the {bird_name} bird: "{question}" Provide a detailed, scientific answer focusing on accurate ornithological information. If the question relates to Tanzania or climate change impacts, emphasize those aspects in your response. IMPORTANT: Do not repeat basic introductory information about the bird that would have already been provided in a general description. Do not start your answer with phrases like "Introduction to the {bird_name}" or similar repetitive headers. Directly answer the specific question asked. Format your response in markdown for better readability. """ try: chat_completion = client.chat.completions.create( messages=[ { "role": "user", "content": prompt, } ], model="llama-3.3-70b-versatile", ) return chat_completion.choices[0].message.content except Exception as e: return f"Error fetching information: {str(e)}" # Create the Gradio interface with gr.Blocks(theme=gr.themes.Soft()) as app: gr.Markdown("# Bird Species Identification for Researchers") gr.Markdown("Upload an image to identify bird species and get detailed information relevant to research in Tanzania and climate change studies.") # Store the current bird for context current_bird = gr.State("") # Main identification section with gr.Row(): with gr.Column(scale=1): input_image = gr.Image(type="pil", label="Upload Bird Image") submit_btn = gr.Button("Identify Bird", variant="primary") with gr.Column(scale=2): prediction_output = gr.Label(label="Top 5 Predictions", num_top_classes=5) bird_info_output = gr.HTML(label="Bird Information") # Clear divider gr.Markdown("---") # Follow-up question section with improved UI gr.Markdown("## Research Questions") conversation_history = gr.Markdown("") with gr.Row(): follow_up_input = gr.Textbox( label="Ask a question about this bird", placeholder="Example: How has climate change affected this bird's migration pattern?", lines=2 ) with gr.Row(): follow_up_btn = gr.Button("Submit Question", variant="primary") clear_btn = gr.Button("Clear Conversation") # Set up event handlers def process_image(img): if img is None: return None, "Please upload an image", "", "" try: pred_results, info, clean_bird_name = predict_and_get_info(img) return pred_results, info, clean_bird_name, "" except Exception as e: return None, f"Error processing image: {str(e)}", "", "" def update_conversation(question, bird_name, history): if not question.strip(): return history answer = follow_up_question(question, bird_name) # Format the conversation with clear separation new_exchange = f""" ### Question: {question} ### Answer: {answer} --- """ updated_history = new_exchange + history return updated_history def clear_conversation_history(): return "" submit_btn.click( process_image, inputs=[input_image], outputs=[prediction_output, bird_info_output, current_bird, conversation_history] ) follow_up_btn.click( update_conversation, inputs=[follow_up_input, current_bird, conversation_history], outputs=[conversation_history] ).then( lambda: "", outputs=follow_up_input ) clear_btn.click( clear_conversation_history, outputs=[conversation_history] ) # Launch the app app.launch(share=True)