Update main.py

main.py

@@ -1,6 +1,5 @@
 from fastapi import FastAPI, HTTPException, Depends, Header
 from fastapi.middleware.cors import CORSMiddleware
-from fastapi.responses import StreamingResponse, HTMLResponse
 import uvicorn
 import os
 import logging
@@ -14,369 +13,219 @@ app = FastAPI(title="FreeLLMAPI")
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
-    allow_credentials=True,
     allow_methods=["*"],
     allow_headers=["*"],
 )
 
-# ============================================================
-# Provider Secrets
-# ============================================================
+# ──────────────────────────────────────────
+# 读取原项目固定命名的 Secrets
+# ──────────────────────────────────────────
 
+# 原项目的 Provider Key 映射表
 PROVIDER_MAP = {
-    "GOOGLE_API_KEY": "google",
-    "GROQ_API_KEY": "groq",
-    "GITHUB_TOKEN": "github",
-    "OPENROUTER_API_KEY": "openrouter",
-    "MISTRAL_API_KEY": "mistral",
-    "TOGETHER_API_KEY": "together",
-    "NVIDIA_API_KEY": "nvidia",
-    "COHERE_API_KEY": "cohere",
-    "HF_TOKEN": "huggingface",
-    "CEREBRAS_API_KEY": "cerebras",
-    "SAMBANOVA_API_KEY": "sambanova",
-    "CLOUDFLARE_API_TOKEN": "cloudflare",
-    "ZHIPU_API_KEY": "zhipu",
+    "GOOGLE_API_KEY":        "google",
+    "GROQ_API_KEY":          "groq",
+    "GITHUB_TOKEN":          "github",
+    "OPENROUTER_API_KEY":    "openrouter",
+    "MISTRAL_API_KEY":       "mistral",
+    "TOGETHER_API_KEY":      "together",
+    "NVIDIA_API_KEY":        "nvidia",
+    "COHERE_API_KEY":        "cohere",
+    "HF_TOKEN":              "huggingface",
+    "CEREBRAS_API_KEY":      "cerebras",
+    "SAMBANOVA_API_KEY":     "sambanova",
+    "CLOUDFLARE_API_TOKEN":  "cloudflare",
+    "ZHIPU_API_KEY":         "zhipu",
 }
 
+# Provider 对应的 base_url 和支持的模型
 PROVIDER_CONFIG = {
     "google": {
         "base_url": "https://generativelanguage.googleapis.com/v1beta/openai",
         "models": [
-            "gemini-2.0-flash",
-            "gemini-2.0-flash-lite",
-            "gemini-1.5-flash",
-            "gemini-1.5-pro",
+            "gemini-2.0-flash","gemini-2.0-flash-lite",
+            "gemini-1.5-pro","gemini-1.5-flash","gemini-1.5-flash-8b"
         ],
     },
     "groq": {
         "base_url": "https://api.groq.com/openai/v1",
         "models": [
-            "llama-3.3-70b-versatile",
-            "llama-3.1-8b-instant",
-            "mixtral-8x7b-32768",
-            "gemma2-9b-it",
+            "llama-3.3-70b-versatile","llama-3.1-8b-instant",
+            "llama3-70b-8192","llama3-8b-8192",
+            "mixtral-8x7b-32768","gemma2-9b-it"
         ],
     },
     "github": {
         "base_url": "https://models.inference.ai.azure.com",
         "models": [
-            "gpt-4o",
-            "gpt-4o-mini",
-            "Phi-4",
-            "DeepSeek-R1",
+            "gpt-4o","gpt-4o-mini",
+            "Phi-3.5-mini-instruct","Phi-3.5-MoE-instruct",
+            "Meta-Llama-3.1-70B-Instruct","Meta-Llama-3.1-405B-Instruct"
         ],
     },
     "openrouter": {
         "base_url": "https://openrouter.ai/api/v1",
         "models": [
+            "mistralai/mistral-7b-instruct:free",
+            "meta-llama/llama-3.2-3b-instruct:free",
+            "google/gemma-3-1b-it:free",
             "deepseek/deepseek-r1:free",
-            "google/gemma-3-27b-it:free",
-            "meta-llama/llama-3.3-70b-instruct:free",
         ],
     },
     "mistral": {
         "base_url": "https://api.mistral.ai/v1",
         "models": [
-            "mistral-small-latest",
-            "mistral-large-latest",
+            "mistral-small-latest","mistral-large-latest",
+            "open-mistral-7b","open-mixtral-8x7b"
         ],
     },
     "together": {
         "base_url": "https://api.together.xyz/v1",
         "models": [
+            "meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
             "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
-            "deepseek-ai/DeepSeek-R1",
+            "mistralai/Mixtral-8x7B-Instruct-v0.1"
         ],
     },
     "nvidia": {
         "base_url": "https://integrate.api.nvidia.com/v1",
         "models": [
             "meta/llama-3.1-70b-instruct",
-            "deepseek-ai/deepseek-r1",
+            "meta/llama-3.1-8b-instruct",
+            "mistralai/mixtral-8x7b-instruct"
         ],
     },
     "cohere": {
-        "base_url": "https://api.cohere.com/compatibility/v1",
-        "models": [
-            "command-r-plus",
-            "command-r",
-        ],
+        "base_url": "https://api.cohere.com/v2",
+        "models": ["command-r-plus","command-r","command"],
     },
     "huggingface": {
-        "base_url": "https://huggingface.co/api/inference-proxy/together",
+        "base_url": "https://api-inference.huggingface.co/v1",
         "models": [
-            "meta-llama/Llama-3.3-70B-Instruct",
-            "Qwen/Qwen2.5-72B-Instruct",
+            "meta-llama/Llama-3.2-3B-Instruct",
+            "mistralai/Mistral-7B-Instruct-v0.3"
         ],
     },
     "cerebras": {
         "base_url": "https://api.cerebras.ai/v1",
-        "models": [
-            "llama3.1-8b",
-            "llama3.3-70b",
-        ],
+        "models": ["llama3.1-8b","llama3.1-70b"],
     },
     "sambanova": {
         "base_url": "https://api.sambanova.ai/v1",
         "models": [
-            "Meta-Llama-3.1-405B-Instruct",
+            "Meta-Llama-3.1-8B-Instruct",
+            "Meta-Llama-3.1-70B-Instruct",
+            "Meta-Llama-3.1-405B-Instruct"
         ],
     },
     "cloudflare": {
         "base_url": "https://api.cloudflare.com/client/v4/accounts/{}/ai/v1",
         "models": [
             "@cf/meta/llama-3.1-8b-instruct",
+            "@cf/mistral/mistral-7b-instruct-v0.1"
         ],
     },
     "zhipu": {
         "base_url": "https://open.bigmodel.cn/api/paas/v4",
-        "models": [
-            "glm-4-flash",
-            "glm-4",
-        ],
+        "models": ["glm-4-flash","glm-4","glm-3-turbo"],
     },
 }
 
 
-# ============================================================
-# Load Config
-# ============================================================
-
 def load_config():
+    """从环境变量读取所有配置"""
 
-    raw_keys = os.getenv("API_KEYS", "").strip()
-
-    api_keys = set(
-        k.strip()
-        for k in raw_keys.split(",")
-        if k.strip()
-    )
+    # ── 读取用户 API Keys（用于鉴权） ──
+    raw_keys = os.getenv("API_KEYS", "")
+    api_keys = set(k.strip() for k in raw_keys.split(",") if k.strip())
 
+    # ── 读取 Provider Keys ──
     providers = {}
-
-    cf_account_id = os.getenv(
-        "CLOUDFLARE_ACCOUNT_ID",
-        ""
-    )
-
     for env_name, provider_name in PROVIDER_MAP.items():
+        key_value = os.getenv(env_name, "").strip()
+        if not key_value:
+            continue  # 没配置该 Provider，跳过
 
-        key = os.getenv(env_name, "").strip()
-
-        if not key:
-            continue
-
-        cfg = PROVIDER_CONFIG[provider_name]
-
-        base_url = cfg["base_url"]
-
-        if provider_name == "cloudflare":
-            if cf_account_id:
-                base_url = base_url.format(cf_account_id)
-
+        cfg = PROVIDER_CONFIG.get(provider_name, {})
         providers[provider_name] = {
-            "api_key": key,
-            "base_url": base_url,
-            "models": cfg["models"],
+            "api_key":  key_value,
+            "base_url": cfg.get("base_url", ""),
+            "models":   cfg.get("models", []),
         }
+        logger.info(f"✅ 加载 Provider: {provider_name}")
 
-        logger.info(f"✅ Provider loaded: {provider_name}")
-
-    logger.info(
-        f"🚀 API Keys={len(api_keys)} Providers={len(providers)}"
-    )
+    logger.info(f"✅ 加载了 {len(api_keys)} 个 API Key")
+    logger.info(f"✅ 加载了 {len(providers)} 个 Provider: {list(providers.keys())}")
 
     return api_keys, providers
 
 
 API_KEYS, PROVIDERS = load_config()
 
-# ============================================================
-# Auth
-# ============================================================
-
-def verify_api_key(
-    authorization: str = Header(...)
-):
-    token = authorization.replace(
-        "Bearer ",
-        ""
-    ).strip()
+# ──────────────────────────────────────────
+# 鉴权
+# ──────────────────────────────────────────
 
+def verify_api_key(authorization: str = Header(...)):
+    token = authorization.removeprefix("Bearer ").strip()
     if token not in API_KEYS:
-        raise HTTPException(
-            status_code=401,
-            detail="Invalid API key"
-        )
-
+        raise HTTPException(status_code=401, detail="Invalid API key")
     return token
 
-# ============================================================
-# Routes
-# ============================================================
-
-@app.get("/", response_class=HTMLResponse)
-async def root():
-
-    return f"""
-    <html>
-    <body style="font-family:Arial;padding:40px">
-        <h1>🚀 FreeLLMAPI</h1>
-        <p>Status: ONLINE</p>
-        <p>Providers: {len(PROVIDERS)}</p>
-        <p>User Keys: {len(API_KEYS)}</p>
-    </body>
-    </html>
-    """
-
+# ──────────────────────────────────────────
+# 路由
+# ──────────────────────────────────────────
 
 @app.get("/health")
 async def health():
     return {
-        "status": "ok",
+        "status":    "ok",
+        "keys":      len(API_KEYS),
         "providers": list(PROVIDERS.keys()),
-        "provider_count": len(PROVIDERS),
-        "user_keys": len(API_KEYS),
-    }
-
-
-@app.get("/keys")
-async def keys():
-
-    result = {}
-
-    for env_name, provider in PROVIDER_MAP.items():
-        result[provider] = bool(
-            os.getenv(env_name)
-        )
-
-    return {
-        "providers": result,
-        "provider_count": len(PROVIDERS),
-        "user_api_keys": len(API_KEYS),
-    }
-
-
-@app.get("/debug")
-async def debug():
-    return {
-        "providers_loaded": list(PROVIDERS.keys()),
-        "provider_count": len(PROVIDERS),
-        "user_api_keys": len(API_KEYS),
-        "total_models": sum(
-            len(x["models"])
-            for x in PROVIDERS.values()
-        ),
     }
 
 
 @app.get("/v1/models")
-async def models(
-    _: str = Depends(verify_api_key)
-):
+async def list_models(_: str = Depends(verify_api_key)):
     data = []
-
-    for provider in PROVIDERS.values():
-        for model in provider["models"]:
-            data.append({
-                "id": model,
-                "object": "model"
-            })
-
-    return {
-        "object": "list",
-        "data": data
-    }
+    for p_cfg in PROVIDERS.values():
+        for m in p_cfg["models"]:
+            data.append({"id": m, "object": "model"})
+    return {"object": "list", "data": data}
 
 
 @app.post("/v1/chat/completions")
-async def chat(
+async def chat_completions(
     body: dict,
     _: str = Depends(verify_api_key)
 ):
-
-    model = body.get("model")
-
+    model    = body.get("model", "")
     provider = None
 
-    for p in PROVIDERS.values():
-        if model in p["models"]:
-            provider = p
+    for p_cfg in PROVIDERS.values():
+        if model in p_cfg["models"]:
+            provider = p_cfg
             break
 
     if not provider:
         raise HTTPException(
             status_code=404,
-            detail=f"Model not found: {model}"
+            detail=f"没有 Provider 支持模型: {model}"
         )
 
-    target_url = (
-        provider["base_url"]
-        + "/chat/completions"
-    )
-
-    headers = {
-        "Authorization":
-        f"Bearer {provider['api_key']}",
-        "Content-Type":
-        "application/json"
-    }
-
-    if provider["base_url"].startswith(
-        "https://openrouter.ai"
-    ):
-        headers["HTTP-Referer"] = (
-            "https://huggingface.co"
-        )
-        headers["X-Title"] = (
-            "HF FreeLLMAPI"
-        )
-
-    if body.get("stream", False):
-
-        async def generate():
-
-            async with httpx.AsyncClient(
-                timeout=120
-            ) as client:
-
-                async with client.stream(
-                    "POST",
-                    target_url,
-                    headers=headers,
-                    json=body,
-                ) as response:
-
-                    async for chunk in response.aiter_bytes():
-                        yield chunk
-
-        return StreamingResponse(
-            generate(),
-            media_type="text/event-stream"
-        )
-
-    async with httpx.AsyncClient(
-        timeout=120
-    ) as client:
-
-        response = await client.post(
-            target_url,
-            headers=headers,
+    async with httpx.AsyncClient(timeout=60) as client:
+        resp = await client.post(
+            f"{provider['base_url']}/chat/completions",
+            headers={"Authorization": f"Bearer {provider['api_key']}"},
             json=body,
         )
+        return resp.json()
 
-    try:
-        return response.json()
-    except Exception:
-        return {
-            "raw": response.text
-        }
+
+@app.get("/health")
+async def health():
+    return {"status": "ok"}
 
 
 if __name__ == "__main__":
-    uvicorn.run(
-        app,
-        host="0.0.0.0",
-        port=7860
-    )
+    uvicorn.run(app, host="0.0.0.0", port=7860)