Update app.py

app.py

@@ -1,5 +1,6 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, Request
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.responses import JSONResponse
 from pydantic import BaseModel
 from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
 import torch
@@ -8,6 +9,7 @@ import httpx
 import time
 from concurrent.futures import ThreadPoolExecutor
 import hashlib
+from collections import defaultdict
 
 app = FastAPI(title="Distributed M2M100 API")
 
@@ -47,6 +49,7 @@ SPACE_PREFIX = "trans"
 DISCOVERY_CHUNK_SIZE = 50
 CACHE_TTL = 86400  # Cache time-to-live: 1 day in seconds (24 * 60 * 60)
 MAX_CACHE_SIZE = 10000  # Maximum number of cached translations
+MAX_RPS_LANGUAGES = 20000  # Maximum requests per second for /languages endpoint
 
 # =====================================================
 # GLOBALS
@@ -62,110 +65,35 @@ cooldown = {}
 # 🔥 Translation cache with TTL (NEW)
 translation_cache = {}
 
+# 🔥 RPS tracking for /languages endpoint (NEW)
+languages_request_times = []
+languages_lock = asyncio.Lock()
+
 # =====================================================
 # LANGUAGES
 # =====================================================
 SUPPORTED_LANGS = {
-    "af": "Afrikaans",
-    "am": "Amharic",
-    "ar": "Arabic",
-    "ast": "Asturian",
-    "az": "Azerbaijani",
-    "ba": "Bashkir",
-    "be": "Belarusian",
-    "bg": "Bulgarian",
-    "bn": "Bengali",
-    "br": "Breton",
-    "bs": "Bosnian",
-    "ca": "Catalan",
-    "ceb": "Cebuano",
-    "cs": "Czech",
-    "cy": "Welsh",
-    "da": "Danish",
-    "de": "German",
-    "el": "Greek",
-    "en": "English",
-    "es": "Spanish",
-    "et": "Estonian",
-    "fa": "Persian",
-    "ff": "Fulah",
-    "fi": "Finnish",
-    "fr": "French",
-    "fy": "Western Frisian",
-    "ga": "Irish",
-    "gd": "Scottish Gaelic",
-    "gl": "Galician",
-    "gu": "Gujarati",
-    "ha": "Hausa",
-    "he": "Hebrew",
-    "hi": "Hindi",
-    "hr": "Croatian",
-    "ht": "Haitian Creole",
-    "hu": "Hungarian",
-    "hy": "Armenian",
-    "id": "Indonesian",
-    "ig": "Igbo",
-    "ilo": "Ilocano",
-    "is": "Icelandic",
-    "it": "Italian",
-    "ja": "Japanese",
-    "jv": "Javanese",
-    "ka": "Georgian",
-    "kk": "Kazakh",
-    "km": "Khmer",
-    "kn": "Kannada",
-    "ko": "Korean",
-    "lb": "Luxembourgish",
-    "lg": "Ganda",
-    "ln": "Lingala",
-    "lo": "Lao",
-    "lt": "Lithuanian",
-    "lv": "Latvian",
-    "mg": "Malagasy",
-    "mk": "Macedonian",
-    "ml": "Malayalam",
-    "mn": "Mongolian",
-    "mr": "Marathi",
-    "ms": "Malay",
-    "my": "Myanmar",
-    "ne": "Nepali",
-    "nl": "Dutch",
-    "no": "Norwegian",
-    "ns": "Northern Sotho",
-    "oc": "Occitan",
-    "or": "Odia",
-    "pa": "Punjabi",
-    "pl": "Polish",
-    "ps": "Pashto",
-    "pt": "Portuguese",
-    "ro": "Romanian",
-    "ru": "Russian",
-    "sd": "Sindhi",
-    "si": "Sinhala",
-    "sk": "Slovak",
-    "sl": "Slovenian",
-    "so": "Somali",
-    "sq": "Albanian",
-    "sr": "Serbian",
-    "ss": "Swati",
-    "su": "Sundanese",
-    "sv": "Swedish",
-    "sw": "Swahili",
-    "ta": "Tamil",
-    "th": "Thai",
-    "tl": "Tagalog",
-    "tn": "Tswana",
-    "tr": "Turkish",
-    "uk": "Ukrainian",
-    "ur": "Urdu",
-    "uz": "Uzbek",
-    "vi": "Vietnamese",
-    "wo": "Wolof",
-    "xh": "Xhosa",
-    "yi": "Yiddish",
-    "yo": "Yoruba",
-    "zh": "Chinese",
-    "zu": "Zulu"
+    "af": "Afrikaans", "am": "Amharic", "ar": "Arabic", "ast": "Asturian", "az": "Azerbaijani",
+    "ba": "Bashkir", "be": "Belarusian", "bg": "Bulgarian", "bn": "Bengali", "br": "Breton",
+    "bs": "Bosnian", "ca": "Catalan", "ceb": "Cebuano", "cs": "Czech", "cy": "Welsh",
+    "da": "Danish", "de": "German", "el": "Greek", "en": "English", "es": "Spanish",
+    "et": "Estonian", "fa": "Persian", "ff": "Fulah", "fi": "Finnish", "fr": "French",
+    "fy": "Western Frisian", "ga": "Irish", "gd": "Scottish Gaelic", "gl": "Galician",
+    "gu": "Gujarati", "ha": "Hausa", "he": "Hebrew", "hi": "Hindi", "hr": "Croatian",
+    "ht": "Haitian Creole", "hu": "Hungarian", "hy": "Armenian", "id": "Indonesian",
+    "ig": "Igbo", "ilo": "Ilocano", "is": "Icelandic", "it": "Italian", "ja": "Japanese",
+    "jv": "Javanese", "ka": "Georgian", "kk": "Kazakh", "km": "Khmer", "kn": "Kannada",
+    "ko": "Korean", "lb": "Luxembourgish", "lg": "Ganda", "ln": "Lingala", "lo": "Lao",
+    "lt": "Lithuanian", "lv": "Latvian", "mg": "Malagasy", "mk": "Macedonian",
+    "ml": "Malayalam", "mn": "Mongolian", "mr": "Marathi", "ms": "Malay", "my": "Myanmar",
+    "ne": "Nepali", "nl": "Dutch", "no": "Norwegian", "ns": "Northern Sotho",
+    "oc": "Occitan", "or": "Odia", "pa": "Punjabi", "pl": "Polish", "ps": "Pashto",
+    "pt": "Portuguese", "ro": "Romanian", "ru": "Russian", "sd": "Sindhi",
+    "si": "Sinhala", "sk": "Slovak", "sl": "Slovenian", "so": "Somali", "sq": "Albanian",
+    "sr": "Serbian", "ss": "Swati", "su": "Sundanese", "sv": "Swedish", "sw": "Swahili",
+    "ta": "Tamil", "th": "Thai", "tl": "Tagalog", "tn": "Tswana", "tr": "Turkish",
+    "uk": "Ukrainian", "ur": "Urdu", "uz": "Uzbek", "vi": "Vietnamese", "wo": "Wolof",
+    "xh": "Xhosa", "yi": "Yiddish", "yo": "Yoruba", "zh": "Chinese", "zu": "Zulu"
 }
 
 # =====================================================
@@ -252,6 +180,7 @@ def is_blocked(url):
 async def check_space(client, i):
     space_name = SPACE_PREFIX if i == 0 else f"{SPACE_PREFIX}{i}"
     url = f"https://{USERNAME}-{space_name}.hf.space"
+    
     if is_blocked(url):
         return {
             "exists": True,
@@ -261,6 +190,7 @@ async def check_space(client, i):
                 "current_space_status": "cooldown"
             }
         }
+    
     try:
         response = await client.get(f"{url}/status")
         if response.status_code == 200:
@@ -317,6 +247,7 @@ async def discover_spaces_parallel():
     existing_spaces = []
     empty_space_url = None
     timeout = httpx.Timeout(5.0)
+    
     async with httpx.AsyncClient(timeout=timeout) as client:
         start = 0
         while True:
@@ -325,7 +256,7 @@ async def discover_spaces_parallel():
                 for i in range(start, start + DISCOVERY_CHUNK_SIZE)
             ]
             results = await asyncio.gather(*tasks)
-
+            
             found_empty = False
             for result in results:
                 if result["exists"]:
@@ -341,11 +272,12 @@ async def discover_spaces_parallel():
                     empty_space_url = result["url"]
                     found_empty = True
                     break
-
+            
             if found_empty:
                 break
+            
             start += DISCOVERY_CHUNK_SIZE
-
+    
     return {
         "existing_spaces": existing_spaces,
         "empty_space_url": empty_space_url
@@ -372,10 +304,36 @@ async def status():
     }
 
 # =====================================================
-# LANGUAGES
+# LANGUAGES WITH RPS LIMITING (UPDATED)
 # =====================================================
 @app.get("/languages")
-def languages():
+async def languages(request: Request):
+    async with languages_lock:
+        current_time = time.time()
+        
+        # Remove requests older than 1 second
+        global languages_request_times
+        languages_request_times = [
+            t for t in languages_request_times
+            if current_time - t < 1.0
+        ]
+        
+        # Check if we've exceeded the RPS limit
+        if len(languages_request_times) >= MAX_RPS_LANGUAGES:
+            # Discover empty space URL for redirection
+            discovered = await discover_spaces_parallel()
+            return JSONResponse(
+                status_code=429,
+                content={
+                    "status": "space_full",
+                    "message": f"Rate limit exceeded. Maximum {MAX_RPS_LANGUAGES} requests per second allowed.",
+                    "empty_space_url": discovered["empty_space_url"]
+                }
+            )
+        
+        # Add current request timestamp
+        languages_request_times.append(current_time)
+    
     return SUPPORTED_LANGS
 
 # =====================================================
@@ -384,7 +342,7 @@ def languages():
 @app.post("/translate")
 async def translate(req: TranslateRequest):
     global active_requests
-
+    
     # Character limit check (without spaces)
     char_count_without_spaces = len(req.text.replace(" ", ""))
     if char_count_without_spaces > MAX_CHARACTERS:
@@ -394,7 +352,7 @@ async def translate(req: TranslateRequest):
             "max_characters": MAX_CHARACTERS,
             "received_characters": char_count_without_spaces
         }
-
+    
     # Check cache first
     cached_result = get_from_cache(req.text, req.source_lang, req.target_lang)
     if cached_result is not None:
@@ -403,7 +361,7 @@ async def translate(req: TranslateRequest):
             "translated_text": cached_result,
             "from_cache": True
         }
-
+    
     queue_size = request_queue.qsize()
     if active_requests >= MAX_ACTIVE_REQUESTS and queue_size >= MAX_QUEUE_SIZE:
         discovered = await discover_spaces_parallel()
@@ -411,11 +369,10 @@ async def translate(req: TranslateRequest):
             "status": "space_full",
             "empty_space_url": discovered["empty_space_url"]
         }
-
+    
     await request_queue.put("req")
     async with lock:
         active_requests += 1
-
     try:
         loop = asyncio.get_running_loop()
         result = await loop.run_in_executor(