Update app.py

app.py

@@ -1,15 +1,14 @@
 """
 Sixfinger Backend API - FRONTEND UYUMLU VERSİYON
 Ultra-fast AI Chat Backend with Multi-Model Support
-Supports: Groq, DeepInfra, LLM7.io
+Supports: Groq, LLM7.io
 """
 
 import os
 import time
 import json
 import logging
-import requests
-from typing import Optional, Dict, Any, Generator
+from typing import Optional, Dict, Any
 from datetime import datetime
 
 from fastapi import FastAPI, HTTPException, Header, Request
@@ -30,12 +29,6 @@ PROVIDERS = {
         "type": "groq",
         "requires_key": True
     },
-    "deepinfra": {
-        "name": "DeepInfra",
-        "type": "deepinfra",
-        "base_url": "https://api.deepinfra.com/v1/openai/chat/completions",
-        "requires_key": False
-    },
     "llm7": {
         "name": "LLM7.io",
         "type": "openai_compatible",
@@ -73,41 +66,6 @@ MODELS = {
         "daily_limit": 300
     },
     
-    # DeepInfra Models (Free)
-    "llama4-maverick": {
-        "provider": "deepinfra",
-        "model_id": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo",
-        "display_name": "Llama 4 Maverick 17B",
-        "size": "17B",
-        "language": "Multilingual",
-        "speed": "⚡⚡",
-        "description": "Meta'nın en yeni hızlı ve yetenekli modeli",
-        "plans": ["free", "starter", "pro", "plus"],
-        "daily_limit": 1000
-    },
-    "qwen3-coder": {
-        "provider": "deepinfra",
-        "model_id": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo",
-        "display_name": "Qwen3 Coder 480B",
-        "size": "480B",
-        "language": "Multilingual",
-        "speed": "⚡",
-        "description": "Kod yazma uzmanı dev model",
-        "plans": ["free", "starter", "pro", "plus"],
-        "daily_limit": 500
-    },
-    "deepseek-r1": {
-        "provider": "deepinfra",
-        "model_id": "deepseek-ai/DeepSeek-R1-0528-Turbo",
-        "display_name": "DeepSeek R1 Turbo",
-        "size": "Unknown",
-        "language": "Multilingual",
-        "speed": "⚡",
-        "description": "Muhakeme ve zeka odaklı model",
-        "plans": ["free", "starter", "pro", "plus"],
-        "daily_limit": 500
-    },
-    
     # ============ STARTER PLAN MODELS ============
     
     # LLM7.io Models (Starter+)
@@ -331,41 +289,6 @@ def call_groq_api(
         logger.error(f"Groq API error: {e}")
         raise HTTPException(status_code=500, detail=f"Groq API error: {str(e)}")
 
-def call_deepinfra_api(
-    model_id: str,
-    messages: list,
-    max_tokens: int,
-    temperature: float,
-    top_p: float,
-    stream: bool = False
-) -> Dict[str, Any]:
-    """DeepInfra API'ye istek at (non-streaming)"""
-    url = PROVIDERS["deepinfra"]["base_url"]
-    headers = {
-        "Content-Type": "application/json",
-        "X-Deepinfra-Source": "web-page"
-    }
-    
-    data = {
-        "model": model_id,
-        "messages": messages,
-        "max_tokens": max_tokens,
-        "temperature": temperature,
-        "top_p": top_p,
-        "stream": stream
-    }
-    
-    try:
-        if stream:
-            return requests.post(url, headers=headers, json=data, stream=True)
-        else:
-            response = requests.post(url, headers=headers, json=data)
-            response.raise_for_status()
-            return response.json()
-    except Exception as e:
-        logger.error(f"DeepInfra API error: {e}")
-        raise HTTPException(status_code=500, detail=f"DeepInfra API error: {str(e)}")
-
 def call_llm7_api(
     model_id: str,
     messages: list,
@@ -401,8 +324,6 @@ def call_api(
     """Universal API caller - provider'a göre yönlendir"""
     if provider == "groq":
         return call_groq_api(model_id, messages, max_tokens, temperature, top_p, stream)
-    elif provider == "deepinfra":
-        return call_deepinfra_api(model_id, messages, max_tokens, temperature, top_p, stream)
     elif provider == "llm7":
         return call_llm7_api(model_id, messages, max_tokens, temperature, top_p, stream)
     else:
@@ -419,7 +340,6 @@ def health_check():
         "timestamp": datetime.now().isoformat(),
         "providers": {
             "groq": bool(GROQ_API_KEY),
-            "deepinfra": True,
             "llm7": True
         }
     }
@@ -452,44 +372,22 @@ def chat(
     )
     
     try:
-        # Provider'a göre API call
-        if provider == "deepinfra":
-            # DeepInfra non-streaming response
-            response_data = call_api(
-                provider=provider,
-                model_id=model_id,
-                messages=messages,
-                max_tokens=request.max_tokens,
-                temperature=request.temperature,
-                top_p=request.top_p,
-                stream=False
-            )
-            
-            content = response_data["choices"][0]["message"]["content"]
-            usage = response_data.get("usage", {})
-            usage = {
-                "prompt_tokens": usage.get("prompt_tokens", 0),
-                "completion_tokens": usage.get("completion_tokens", 0),
-                "total_tokens": usage.get("total_tokens", 0)
-            }
-        else:
-            # Groq veya LLM7 response
-            response = call_api(
-                provider=provider,
-                model_id=model_id,
-                messages=messages,
-                max_tokens=request.max_tokens,
-                temperature=request.temperature,
-                top_p=request.top_p,
-                stream=False
-            )
-            
-            content = response.choices[0].message.content
-            usage = {
-                "prompt_tokens": getattr(response.usage, 'prompt_tokens', 0),
-                "completion_tokens": getattr(response.usage, 'completion_tokens', 0),
-                "total_tokens": getattr(response.usage, 'total_tokens', 0)
-            }
+        response = call_api(
+            provider=provider,
+            model_id=model_id,
+            messages=messages,
+            max_tokens=request.max_tokens,
+            temperature=request.temperature,
+            top_p=request.top_p,
+            stream=False
+        )
+
+        content = response.choices[0].message.content
+        usage = {
+            "prompt_tokens": getattr(response.usage, 'prompt_tokens', 0),
+            "completion_tokens": getattr(response.usage, 'completion_tokens', 0),
+            "total_tokens": getattr(response.usage, 'total_tokens', 0)
+        }
         
         elapsed = time.time() - start_time
         logger.info(f"Chat completed: provider={provider}, tokens={usage['total_tokens']}, time={elapsed:.2f}s")
@@ -574,52 +472,6 @@ def chat_stream(
             logger.error(f"Groq stream error: {e}")
             yield f"data: {json.dumps({'error': str(e)})}\n\n"
     
-    def generate_deepinfra():
-        """DeepInfra streaming generator"""
-        try:
-            yield f"data: {json.dumps({'info': f'Using {model_key} via DeepInfra'})}\n\n"
-            
-            url = PROVIDERS["deepinfra"]["base_url"]
-            headers = {
-                "Content-Type": "application/json",
-                "X-Deepinfra-Source": "web-page"
-            }
-            data = {
-                "model": model_id,
-                "messages": messages,
-                "max_tokens": request.max_tokens,
-                "temperature": request.temperature,
-                "top_p": request.top_p,
-                "stream": True
-            }
-            
-            response = requests.post(url, headers=headers, json=data, stream=True)
-            
-            total_completion_tokens = 0
-            
-            for line in response.iter_lines():
-                if line:
-                    decoded = line.decode('utf-8')
-                    if decoded.startswith("data: "):
-                        content = decoded[6:]
-                        if content == "[DONE]":
-                            break
-                        try:
-                            json_data = json.loads(content)
-                            delta = json_data.get("choices", [{}])[0].get("delta", {})
-                            if "content" in delta:
-                                token = delta["content"]
-                                yield f"data: {json.dumps({'text': token})}\n\n"
-                                total_completion_tokens += 1
-                        except json.JSONDecodeError:
-                            continue
-            
-            yield f"data: {json.dumps({'done': True, 'model_key': model_key, 'provider': 'deepinfra', 'attempts': 1, 'usage': {'prompt_tokens': 0, 'completion_tokens': total_completion_tokens, 'total_tokens': total_completion_tokens}})}\n\n"
-            
-        except Exception as e:
-            logger.error(f"DeepInfra stream error: {e}")
-            yield f"data: {json.dumps({'error': str(e)})}\n\n"
-    
     def generate_llm7():
         """LLM7.io streaming generator"""
         try:
@@ -651,8 +503,6 @@ def chat_stream(
     # Provider'a göre generator seç
     if provider == "groq":
         generator = generate_groq()
-    elif provider == "deepinfra":
-        generator = generate_deepinfra()
     elif provider == "llm7":
         generator = generate_llm7()
     else:
@@ -717,12 +567,6 @@ def list_providers():
                 "status": "active" if GROQ_API_KEY else "inactive",
                 "description": "Ultra-fast inference with Groq LPU"
             },
-            {
-                "id": "deepinfra",
-                "name": "DeepInfra",
-                "status": "active",
-                "description": "Free tier AI models - Llama 4, Qwen3 Coder, DeepSeek"
-            },
             {
                 "id": "llm7",
                 "name": "LLM7.io",
@@ -761,7 +605,6 @@ async def startup_event():
     logger.info("🚀 Sixfinger Backend API started")
     logger.info(f"📦 Version: {API_VERSION}")
     logger.info(f"🔑 Groq API: {'✅ Configured' if GROQ_API_KEY else '❌ Not configured'}")
-    logger.info(f"🌐 DeepInfra: ✅ Active (Free tier)")
     logger.info(f"🌐 LLM7.io: ✅ Active (Free tier)")
     logger.info(f"🤖 Total Models: {len(MODELS)}")