Upload 9 files

app.py

@@ -1,7 +1,72 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, Request
+from fastapi.responses import StreamingResponse
+from fastapi.middleware.cors import CORSMiddleware
+from models.together.main import TogetherAPI
+from models.vercel.main import XaiAPI, GroqAPI
+
 
 app = FastAPI()
 
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # Allows all origins
+    allow_credentials=True,
+    allow_methods=["*"],  # Allows all methods
+    allow_headers=["*"],  # Allows all headers
+)
+
 @app.get("/")
-def greet_json():
-    return {"Hello": "World!"}
+async def root():
+    return {"message": "Server Running Successfully"}
+
+@app.post("/api/v1/generate")
+async def generate(request: Request):
+    data = await request.json()
+    messages = data['messages']
+    model = data['model']
+
+    if not messages or not model:
+        return {"error": "Invalid request. 'messages' and 'model' are required."}
+
+    try:
+        query = {
+            'model': model,
+            'max_tokens': None,
+            'temperature': 0.7,
+            'top_p': 0.7,
+            'top_k': 50,
+            'repetition_penalty': 1,
+            'stream_tokens': True,
+            'stop': ['<|eot_id|>', '<|eom_id|>'],
+            'messages': messages,
+            'stream': True,
+        }
+        
+        together_models = TogetherAPI().get_model_list()
+        xai_models = XaiAPI().get_model_list()
+        groq_models = GroqAPI().get_model_list()
+
+        if model in together_models:
+            streamModel = TogetherAPI()
+        elif model in xai_models:
+            streamModel = XaiAPI()
+        elif model in groq_models:
+            streamModel = GroqAPI()
+        else:
+            return {"error": f"Model '{model}' is not supported."}
+
+        response = streamModel.generate(query)
+
+        return StreamingResponse(response, media_type="text/event-stream")
+    
+    except Exception as e:
+        return {"error": f"An error occurred: {str(e)}"}
+
+@app.get("/api/v1/models")
+async def get_models():
+    try:
+        streamModel = TogetherAPI()
+        models = streamModel.get_model_list()
+        return {"models": models}
+    except Exception as e:
+        return {"error": f"An error occurred: {str(e)}"}

models/together/main.py

@@ -0,0 +1,79 @@
+import httpx
+import asyncio
+
+class TogetherAPI:
+
+    cookies = {
+        'intercom-id-evnv2y8k': 'fea4d452-f9be-42e0-93e3-1e47a3836362',
+        'intercom-device-id-evnv2y8k': '2bb3e469-0159-4b6b-a33e-1aea4b51ccb1',
+        '__stripe_mid': 'e0f7c1ba-56c6-44d4-ba1d-cf4611453eb43cf922',
+        'state-csrf': '6f2o8nqgee2dfqdmhaxipe',
+        'together_auth_cookie': '%7B%22expires%22%3A%222026-04-09T15%3A14%3A08.985Z%22%2C%22session%22%3A%220eae08c6fd1b79a22476a317d440a2104d74cd3ba333e40771b5ce50a90784297eb82eff36263debca2ee0658abe3e43cab97f87794421111d4bdec56b43dd2595ee22a165c123ba3d0f807759555b5f6d3f51b7c248e7cefcdf0f0b897f62b25b2a569e2cb89633032f15dca9818f39ed49f3ac2d7e0bc3d24517c62c78b1e4%22%7D',
+        '__stripe_sid': '979e00a2-06ed-45be-9a95-88d7e7580f625ccce4',
+        'intercom-session-evnv2y8k': 'TzZzSzBNRG8xdHJtTVprMm1zUXFob0M2ekhFV3VmeDZFcW5UVldlYmFYc3RsRjFmdWJidjU1ZXVSZzNOSW9QTE82OUx6anlvMWVncmlTd2ZvOERDUXN4OUdoSEM5ZzRnQmh4d2o5S3JKeDA9LS00S3JOclNpNzU0VkVBaTNRNWhSMm93PT0=--2719775e99e920753d35527a45a6731bac5e8f8f',
+        'AMP_7112ee0414': 'JTdCJTIyZGV2aWNlSWQlMjIlM0ElMjJmY2ZmNjE3Ny00Yzg0LTRlOTItYTFhMC1kM2Y1ZjllOTFkYTglMjIlMkMlMjJ1c2VySWQlMjIlM0ElMjI2N2I1ZDkwNDNkZTIyN2Q0OGIzMWEwZTMlMjIlMkMlMjJzZXNzaW9uSWQlMjIlM0ExNzQ0MjExNjQyMjEwJTJDJTIyb3B0T3V0JTIyJTNBZmFsc2UlMkMlMjJsYXN0RXZlbnRUaW1lJTIyJTNBMTc0NDIxMTc1ODAwOSUyQyUyMmxhc3RFdmVudElkJTIyJTNBMjMyJTJDJTIycGFnZUNvdW50ZXIlMjIlM0E1JTdE',
+    }
+
+    headers = {
+        'accept': 'application/json',
+        'accept-language': 'en-US,en;q=0.9,ja;q=0.8',
+        'authorization': 'Bearer 4d900964e385651ea685af6f6cd5573a17b421f50657f73f903525177915a7e2',
+        'content-type': 'application/json',
+        'priority': 'u=1, i',
+        'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',
+        'sec-ch-ua-mobile': '?0',
+        'sec-ch-ua-platform': '"macOS"',
+        'sec-fetch-dest': 'empty',
+        'sec-fetch-mode': 'cors',
+        'sec-fetch-site': 'same-origin',
+        'x-stainless-arch': 'unknown',
+        'x-stainless-lang': 'js',
+        'x-stainless-os': 'Unknown',
+        'x-stainless-package-version': '0.11.1',
+        'x-stainless-retry-count': '0',
+        'x-stainless-runtime': 'browser:chrome',
+        'x-stainless-runtime-version': '135.0.0',
+        'referer': 'https://api.together.ai/playground/v2/chat/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8',
+    }
+
+    def __init__(self):
+        self.base_url = "https://api.together.ai/inference"
+
+    def get_model_list(self):
+       models = ['meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8', 'meta-llama/Llama-4-Scout-17B-16E-Instruct', 'deepseek-ai/DeepSeek-R1', 'deepseek-ai/DeepSeek-V3', 'Qwen/Qwen2.5-VL-72B-Instruct', 'google/gemma-2-27b-it']
+       return models
+    
+    async def generate(self, json_data: dict):
+        max_retries = 5
+        for attempt in range(max_retries):
+            async with httpx.AsyncClient(timeout=None) as client:
+                try:
+                    request_ctx = client.stream(
+                        "POST",
+                        "https://api.together.ai/inference",
+                        cookies=TogetherAPI.cookies,
+                        headers=TogetherAPI.headers,
+                        json=json_data
+                    )
+
+                    async with request_ctx as response:
+                        if response.status_code == 200:
+                            async for line in response.aiter_lines():
+                                if line:
+                                    yield f"{line}\n"
+                            return
+                        elif response.status_code == 429:
+                            if attempt < max_retries - 1:
+                                await asyncio.sleep(0.5)
+                                continue
+                            yield "data: [Rate limited, max retries]\n\n"
+                            return
+                        else:
+                            yield f"data: [Unexpected status code: {response.status_code}]\n\n"
+                            return
+                except Exception as e:
+                    yield f"data: [Connection error: {str(e)}]\n\n"
+                    return
+
+        yield "data: [Max retries reached]\n\n"
+        

models/vercel/main.py

@@ -0,0 +1,210 @@
+import httpx
+import asyncio
+import random
+import json
+
+class XaiAPI:
+
+    headers = {
+        'accept': '*/*',
+        'accept-language': 'en-US,en;q=0.9,ja;q=0.8',
+        'content-type': 'application/json',
+        'origin': 'https://ai-sdk-starter-xai.vercel.app',
+        'referer': 'https://ai-sdk-starter-xai.vercel.app/',
+        'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',
+        'sec-ch-ua-mobile': '?0',
+        'sec-ch-ua-platform': '"macOS"',
+        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36'
+    }
+
+
+    def __init__(self):
+        self.base_url = "https://ai-sdk-starter-xai.vercel.app/api/chat"
+
+    def get_model_list(self):
+       models = ["grok-3-mini", "grok-2-1212", "grok-3", "grok-3-fast", "grok-3-mini-fast"]
+       return models
+    
+    def convert(messages):
+        converted = []
+        for message in messages:
+            role = message.get("role", "user")
+            content = message.get("content", "")
+
+            if isinstance(content, list):
+                parts = content
+                text_content = "\n".join([p.get("text", "") for p in content if p.get("type") == "text"])
+            else:
+                text_content = str(content)
+                parts = [{"type": "text", "text": text_content}]
+                if role == "assistant":
+                    parts.insert(0, {"type": "step-start"})
+
+            converted.append({
+                "role": role,
+                "content": text_content,
+                "parts": parts
+            })
+        return converted
+    
+    async def generate(self, json_data: dict):
+        messages = XaiAPI.convert(json_data["messages"])
+        
+        request_data = {
+            "id": "".join(random.choices("0123456789abcdef", k=16)),
+            "messages": messages,
+            "selectedModel": json_data.get("model", "grok-2-1212"),
+        }
+
+        chunk_id = "chipling-xai-" + "".join(random.choices("0123456789abcdef", k=32))
+        created = int(asyncio.get_event_loop().time())
+        total_tokens = 0
+
+        try:
+            async with httpx.AsyncClient(timeout=None) as client:
+                async with client.stream(
+                    "POST",
+                    "https://ai-sdk-starter-xai.vercel.app/api/chat",
+                    headers=XaiAPI.headers,
+                    json=request_data
+                ) as request_ctx:
+                    if request_ctx.status_code == 200:
+                        async for line in request_ctx.aiter_lines():
+                            if line:
+                                if line.startswith('0:'):
+                                    # Clean up the text and properly escape JSON characters
+                                    text = line[2:].strip()
+                                    if text.startswith('"') and text.endswith('"'):
+                                        text = text[1:-1]
+                                    text = text.replace('\\n', '\n').replace('\\', '')
+                                    
+                                    response = {
+                                        "id": chunk_id,
+                                        "object": "chat.completion.chunk",
+                                        "created": created,
+                                        "model": json_data.get("model", "grok-2-1212"),
+                                        "choices": [{
+                                            "index": 0,
+                                            "text": text,
+                                            "logprobs": None,
+                                            "finish_reason": None
+                                        }],
+                                        "usage": None
+                                    }
+                                    yield f"data: {json.dumps(response)}\n\n"
+                                    total_tokens += 1
+                                elif line.startswith('d:'):
+                                    final = {
+                                        "id": chunk_id,
+                                        "object": "chat.completion.chunk", 
+                                        "created": created,
+                                        "model": json_data.get("model", "grok-2-1212"),
+                                        "choices": [],
+                                        "usage": {
+                                            "prompt_tokens": len(messages),
+                                            "completion_tokens": total_tokens,
+                                            "total_tokens": len(messages) + total_tokens
+                                        }
+                                    }
+                                    yield f"data: {json.dumps(final)}\n\n"
+                                    yield "data: [DONE]\n\n"
+                        return
+                    else:
+                        yield f"data: [Unexpected status code: {request_ctx.status_code}]\n\n"
+        except Exception as e:
+            yield f"data: [Connection error: {str(e)}]\n\n"
+
+
+class GroqAPI:
+
+    headers = {
+        'accept': '*/*',
+        'accept-language': 'en-US,en;q=0.9,ja;q=0.8',
+        'content-type': 'application/json',
+        'origin': 'https://ai-sdk-starter-groq.vercel.app',
+        'priority': 'u=1, i',
+        'referer': 'https://ai-sdk-starter-groq.vercel.app/',
+        'sec-ch-ua': '"Google Chrome";v="135", "Not-A.Brand";v="8", "Chromium";v="135"',
+        'sec-ch-ua-mobile': '?0',
+        'sec-ch-ua-platform': '"macOS"',
+        'sec-fetch-dest': 'empty',
+        'sec-fetch-mode': 'cors',
+        'sec-fetch-site': 'same-origin',
+        'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/135.0.0.0 Safari/537.36',
+    }
+
+    def __init__(self):
+        self.base_url = "https://ai-sdk-starter-groq.vercel.app/api/chat"
+
+    def get_model_list(self):
+       models = ['meta-llama/llama-4-scout-17b-16e-instruct', 'llama-3.1-8b-instant', 'llama-3.3-70b-versatile', 'deepseek-r1-distill-llama-70b']
+       return models
+    
+
+    async def generate(self, json_data: dict):
+        messages = XaiAPI.convert(json_data["messages"])
+
+        request_data = {
+            "id": "".join(random.choices("0123456789abcdef", k=16)),
+            "messages": messages,
+            "selectedModel": json_data.get("model", "deepseek-r1-distill-llama-70b"),
+        }
+
+        chunk_id = "chipling-groq-" + "".join(random.choices("0123456789abcdef", k=32))
+        created = int(asyncio.get_event_loop().time())
+        total_tokens = 0
+
+        try:
+            async with httpx.AsyncClient(timeout=None) as client:
+                async with client.stream(
+                    "POST",
+                    "https://ai-sdk-starter-groq.vercel.app/api/chat",
+                    headers=GroqAPI.headers,
+                    json=request_data
+                ) as request_ctx:
+                    print(request_ctx.status_code)
+                    if request_ctx.status_code == 200:
+                        async for line in request_ctx.aiter_lines():
+                            if line:
+                                if line.startswith('0:'):
+                                    # Clean up the text and properly escape JSON characters
+                                    text = line[2:].strip()
+                                    if text.startswith('"') and text.endswith('"'):
+                                        text = text[1:-1]
+                                    text = text.replace('\\n', '\n').replace('\\', '')
+                                    
+                                    response = {
+                                        "id": chunk_id,
+                                        "object": "chat.completion.chunk",
+                                        "created": created,
+                                        "model": json_data.get("model", "deepseek-r1-distill-llama-70b"),
+                                        "choices": [{
+                                            "index": 0,
+                                            "text": text,
+                                            "logprobs": None,
+                                            "finish_reason": None
+                                        }],
+                                        "usage": None
+                                    }
+                                    yield f"data: {json.dumps(response)}\n\n"
+                                    total_tokens += 1
+                                elif line.startswith('d:'):
+                                    final = {
+                                        "id": chunk_id,
+                                        "object": "chat.completion.chunk", 
+                                        "created": created,
+                                        "model": json_data.get("model", "deepseek-r1-distill-llama-70b"),
+                                        "choices": [],
+                                        "usage": {
+                                            "prompt_tokens": len(messages),
+                                            "completion_tokens": total_tokens,
+                                            "total_tokens": len(messages) + total_tokens
+                                        }
+                                    }
+                                    yield f"data: {json.dumps(final)}\n\n"
+                                    yield "data: [DONE]\n\n"
+                        return
+                    else:
+                        yield f"data: [Unexpected status code: {request_ctx.status_code}]\n\n"
+        except Exception as e:
+            yield f"data: [Connection error: {str(e)}]\n\n"

requirements.txt

@@ -1,2 +1,9 @@
-fastapi
+fastapi==0.115.12
+httpx==0.28.1
+pydantic==2.11.3
+Requests==2.32.3
 uvicorn[standard]
+asyncio
+jinja2
+aiofiles
+curl_cffi

test.py

@@ -0,0 +1,35 @@
+import requests
+import json
+
+messages = [
+    {"role": "user", "content": "helo"},
+    {"role": "assistant", "content": "Hello! How can I assist you today?"},
+    {"role": "user", "content": "who are you and give me a breif description of who created you "}
+]
+
+model = "grok-3-mini"
+
+url = " http://127.0.0.1:8000/api/v1/generate"
+
+payload = {
+    "messages": messages,
+    "model": model
+}
+
+response = requests.post(url, json=payload, stream=True)
+
+if response.status_code == 200:
+    for line in response.iter_lines():
+        if line:
+            decoded_line = line.decode('utf-8')
+            if decoded_line.startswith('data: [DONE]'):
+                break
+            elif decoded_line.startswith('data: '):
+                try:
+                    json_data = json.loads(decoded_line[6:])
+                    if json_data["choices"] and "text" in json_data["choices"][0]:
+                        print(json_data["choices"][0]["text"], end='')
+                except json.JSONDecodeError:
+                    continue
+else:
+    print(f"Request failed with status code {response.status_code}")