Update app.py

app.py

@@ -18,6 +18,130 @@ import sys
 # Load environment variables
 load_dotenv()
 
+# Model rate limits information
+MODEL_LIMITS = {
+    "allam-2-7b": {
+        "rpm": 30,
+        "rpd": 7000,
+        "tpm": 6000,
+        "tpd": "No limit"
+    },
+    "deepseek-r1-distill-llama-70b": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": "No limit"
+    },
+    "deepseek-r1-distill-qwen-32b": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": "No limit"
+    },
+    "gemma2-9b-it": {
+        "rpm": 30,
+        "rpd": 14400,
+        "tpm": 15000,
+        "tpd": 500000
+    },
+    "llama-3.1-8b-instant": {
+        "rpm": 30,
+        "rpd": 14400,
+        "tpm": 6000,
+        "tpd": 500000
+    },
+    "llama-3.2-11b-vision-preview": {
+        "rpm": 30,
+        "rpd": 7000,
+        "tpm": 7000,
+        "tpd": 500000
+    },
+    "llama-3.2-1b-preview": {
+        "rpm": 30,
+        "rpd": 7000,
+        "tpm": 7000,
+        "tpd": 500000
+    },
+    "llama-3.2-3b-preview": {
+        "rpm": 30,
+        "rpd": 7000,
+        "tpm": 7000,
+        "tpd": 500000
+    },
+    "llama-3.2-90b-vision-preview": {
+        "rpm": 15,
+        "rpd": 3500,
+        "tpm": 7000,
+        "tpd": 250000
+    },
+    "llama-3.3-70b-specdec": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": 100000
+    },
+    "llama-3.3-70b-versatile": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": 100000
+    },
+    "llama-guard-3-8b": {
+        "rpm": 30,
+        "rpd": 14400,
+        "tpm": 15000,
+        "tpd": 500000
+    },
+    "llama3-70b-8192": {
+        "rpm": 30,
+        "rpd": 14400,
+        "tpm": 6000,
+        "tpd": 500000
+    },
+    "llama3-8b-8192": {
+        "rpm": 30,
+        "rpd": 14400,
+        "tpm": 6000,
+        "tpd": 500000
+    },
+    "mistral-saba-24b": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": 500000
+    },
+    "qwen-2.5-32b": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": "No limit"
+    },
+    "qwen-2.5-coder-32b": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": "No limit"
+    },
+    "qwen-qwq-32b": {
+        "rpm": 30,
+        "rpd": 1000,
+        "tpm": 6000,
+        "tpd": "No limit"
+    },
+    "claude-3-5-sonnet-20240620": {
+        "rpm": 30,
+        "rpd": 14400,
+        "tpm": 15000,
+        "tpd": 500000
+    },
+    "mixtral-8x7b-32768": {
+        "rpm": 30,
+        "rpd": 14400,
+        "tpm": 15000,
+        "tpd": 500000
+    }
+}
+
 # Initialize session state if not already done
 if 'conversation_history' not in st.session_state:
     st.session_state.conversation_history = []
@@ -168,6 +292,38 @@ st.markdown("""
         display: flex;
         flex-wrap: wrap;
     }
+    .model-limits-container {
+        background-color: #E8F5E9;
+        padding: 1rem;
+        border-radius: 5px;
+        margin-top: 0.5rem;
+        margin-bottom: 1rem;
+    }
+    .limit-pill {
+        display: inline-block;
+        margin: 0.2rem;
+        padding: 0.3rem 0.6rem;
+        background-color: #C8E6C9;
+        color: #2E7D32;
+        border-radius: 20px;
+        font-size: 0.8rem;
+    }
+    .limit-table {
+        width: 100%;
+        border-collapse: collapse;
+        margin-top: 0.5rem;
+        font-size: 0.9rem;
+    }
+    .limit-table th, .limit-table td {
+        padding: 0.4rem;
+        text-align: left;
+        border-bottom: 1px solid #E0E0E0;
+    }
+    .limit-table th {
+        background-color: #E8F5E9;
+        color: #2E7D32;
+        font-weight: bold;
+    }
 </style>
 """, unsafe_allow_html=True)
 
@@ -198,13 +354,67 @@ with st.sidebar:
     
     # Advanced Settings
     st.markdown('<div class="sub-header">Advanced Settings</div>', unsafe_allow_html=True)
+    
+    # Available models
+    available_models = [
+        'gemma2-9b-it', 
+        'llama3-8b-8192', 
+        'mixtral-8x7b-32768', 
+        'llama3-70b-8192', 
+        'claude-3-5-sonnet-20240620',
+        'llama-3.1-8b-instant',
+        'llama-3.2-3b-preview',
+        'llama-3.3-70b-versatile',
+        'qwen-2.5-32b',
+        'mistral-saba-24b'
+    ]
+    
     model_option = st.selectbox(
         'LLM Model',
-        ('gemma2-9b-it', 'llama3-8b-8192', 'mixtral-8x7b-32768', 'llama3-70b-8192', 'claude-3-5-sonnet-20240620'),
+        available_models,
         index=0,
-        help="Select from available Groq models - all free with no rate limits!"
+        help="Select from available Groq models"
     )
     
+    # Display the rate limits for the selected model
+    if model_option in MODEL_LIMITS:
+        limits = MODEL_LIMITS[model_option]
+        st.markdown('<div class="model-limits-container">', unsafe_allow_html=True)
+        st.markdown(f"#### Rate Limits for {model_option}")
+        
+        # Create a table for the limits
+        st.markdown("""
+        <table class="limit-table">
+            <tr>
+                <th>Limit Type</th>
+                <th>Value</th>
+            </tr>
+            <tr>
+                <td>Requests per Minute</td>
+                <td>{rpm}</td>
+            </tr>
+            <tr>
+                <td>Requests per Day</td>
+                <td>{rpd}</td>
+            </tr>
+            <tr>
+                <td>Tokens per Minute</td>
+                <td>{tpm}</td>
+            </tr>
+            <tr>
+                <td>Tokens per Day</td>
+                <td>{tpd}</td>
+            </tr>
+        </table>
+        """.format(
+            rpm=limits['rpm'],
+            rpd=limits['rpd'],
+            tpm=limits['tpm'],
+            tpd=limits['tpd']
+        ), unsafe_allow_html=True)
+        
+        st.markdown('</div>', unsafe_allow_html=True)
+    
     search_depth = st.slider('Search Depth', min_value=1, max_value=8, value=5, 
                             help="Higher values will search more thoroughly but take longer")