Update app.py

app.py

@@ -2,9 +2,10 @@ import streamlit as st
 import requests
 import os
 import json
+import pandas as pd
 
-# Function to call the Together AI model
-def call_ai_model(all_message):
+# Function to call the Together AI model for the initial analysis
+def call_ai_model_initial(all_message):
     url = "https://api.together.xyz/v1/chat/completions"
     payload = {
         "model": "NousResearch/Nous-Hermes-2-Yi-34B",
@@ -32,9 +33,38 @@ def call_ai_model(all_message):
 
     return response
 
+# Function to call the Together AI model for analyzing the text and computing performance score
+def call_ai_model_analysis(analysis_text):
+    url = "https://api.together.xyz/v1/chat/completions"
+    payload = {
+        "model": "NousResearch/Nous-Hermes-2-Yi-34B",
+        "temperature": 1.05,
+        "top_p": 0.9,
+        "top_k": 50,
+        "repetition_penalty": 1,
+        "n": 1,
+        "messages": [{"role": "user", "content": analysis_text}],
+        "stream_tokens": True,
+    }
+
+    TOGETHER_API_KEY = os.getenv('TOGETHER_API_KEY')
+    if TOGETHER_API_KEY is None:
+        raise ValueError("TOGETHER_API_KEY environment variable not set.")
+    
+    headers = {
+        "accept": "application/json",
+        "content-type": "application/json",
+        "Authorization": f"Bearer {TOGETHER_API_KEY}",
+    }
+
+    response = requests.post(url, json=payload, headers=headers, stream=True)
+    response.raise_for_status()  # Ensure HTTP request was successful
+
+    return response
+
 # Streamlit app layout
-st.title("Climate Impact on Sports Performance")
-st.write("Analyze and visualize the impact of climate conditions on sports performance.")
+st.title("Climate Impact on Sports Performance and Infrastructure")
+st.write("Analyze and visualize the impact of climate conditions on sports performance and infrastructure.")
 
 # Inputs for climate conditions
 temperature = st.number_input("Temperature (°C):", min_value=-50, max_value=50, value=25)
@@ -45,31 +75,87 @@ air_quality_index = st.number_input("Air Quality Index:", min_value=0, max_value
 precipitation = st.number_input("Precipitation (mm):", min_value=0.0, max_value=500.0, value=10.0)
 atmospheric_pressure = st.number_input("Atmospheric Pressure (hPa):", min_value=900, max_value=1100, value=1013)
 
-# Button to generate predictions
+# Geographic location input
+latitude = st.number_input("Latitude:", min_value=-90.0, max_value=90.0, value=0.0)
+longitude = st.number_input("Longitude:", min_value=-180.0, max_value=180.0, value=0.0)
+
 if st.button("Generate Prediction"):
     all_message = (
-        f"Assess the impact on sports performance based on climate conditions: "
-        f"Temperature {temperature}°C, Humidity {humidity}%, Wind Speed {wind_speed} km/h, "
-        f"UV Index {uv_index}, Air Quality Index {air_quality_index}, "
-        f"Precipitation {precipitation} mm, Atmospheric Pressure {atmospheric_pressure} hPa."
+        f"Assess the impact on sports performance and infrastructure based on climate conditions: "
+        f"Temperature {temperature}°C, Humidity {humidity}%, Wind Speed {wind_speed} km/h, UV Index {uv_index}, "
+        f"Air Quality Index {air_quality_index}, Precipitation {precipitation} mm, Atmospheric Pressure {atmospheric_pressure} hPa. "
+        f"Location: Latitude {latitude}, Longitude {longitude}."
+        f"After analyzing that, I want you to visualize the data in the best way possible, might be in a table, using a chart or any other way so that it could be easy to understand."
     )
 
     try:
+        with st.spinner("Analyzing climate conditions..."):
+            initial_response = call_ai_model_initial(all_message)
+
+            initial_text = ""
+            for line in initial_response.iter_lines():
+                if line:
+                    line_content = line.decode('utf-8')
+                    if line_content.startswith("data: "):
+                        line_content = line_content[6:]  # Strip "data: " prefix
+                    try:
+                        json_data = json.loads(line_content)
+                        if "choices" in json_data:
+                            delta = json_data["choices"][0]["delta"]
+                            if "content" in delta:
+                                initial_text += delta["content"]
+                    except json.JSONDecodeError:
+                        continue
+
+            st.success("Initial analysis completed!")
+
         with st.spinner("Generating predictions..."):
-            # Call AI model to get qualitative analysis
-            qualitative_analysis = (
-                f"Analyze the impact on sports performance under the following conditions: "
-                f"Temperature {temperature}°C, Humidity {humidity}%, Wind Speed {wind_speed} km/h, "
-                f"UV Index {uv_index}, Air Quality Index {air_quality_index}, "
-                f"Precipitation {precipitation} mm, Atmospheric Pressure {atmospheric_pressure} hPa."
+            analysis_text = (
+                f"Analyze the following text and extract a performance score based on the climate conditions and their impact: {initial_text}"
             )
-            qualitative_result = call_ai_model(qualitative_analysis)
+            analysis_response = call_ai_model_analysis(analysis_text)
+
+            analysis_result = ""
+            for line in analysis_response.iter_lines():
+                if line:
+                    line_content = line.decode('utf-8')
+                    if line_content.startswith("data: "):
+                        line_content = line_content[6:]  # Strip "data: " prefix
+                    try:
+                        json_data = json.loads(line_content)
+                        if "choices" in json_data:
+                            delta = json_data["choices"][0]["delta"]
+                            if "content" in delta:
+                                analysis_result += delta["content"]
+                    except json.JSONDecodeError:
+                        continue
+
+            st.success("Predictions generated!")
+
+            # Extract performance score from the analysis result
+            # Assuming the performance score is provided in the text as "Performance Score: XX%"
+            performance_score = "N/A"
+            for line in analysis_result.split('\n'):
+                if "Performance Score:" in line:
+                    performance_score = line.split(":")[1].strip()
+
+            # Prepare data for visualization
+            results_data = {
+                "Condition": ["Temperature", "Humidity", "Wind Speed", "UV Index", "Air Quality Index", "Precipitation", "Atmospheric Pressure"],
+                "Value": [temperature, humidity, wind_speed, uv_index, air_quality_index, precipitation, atmospheric_pressure]
+            }
+            results_df = pd.DataFrame(results_data)
+
+            # Display results in a table
+            st.subheader("Results Summary")
+            st.table(results_df)
 
-        st.success("Predictions generated.")
+            # Display prediction
+            st.markdown("**Predicted Impact on Performance and Infrastructure:**")
+            st.markdown(initial_text.strip())
 
-        # Display qualitative analysis
-        st.subheader("Qualitative Analysis")
-        st.write(qualitative_result)
+            # Display performance score
+            st.markdown(f"**Performance Score:** {performance_score}")
 
     except ValueError as ve:
         st.error(f"Configuration error: {ve}")