Upload 24 files

app.py

@@ -5,6 +5,7 @@ from models.text.together.main import TogetherAPI
 from models.text.vercel.main import XaiAPI, GroqAPI, DeepinfraAPI
 from models.image.vercel.main import FalAPI
 from models.image.together.main import TogetherImageAPI
+from models.fetch import FetchModel
 
 app = FastAPI()
 
@@ -110,5 +111,68 @@ async def generate_images(request: Request):
         response = await streamModel.generate(query)
         return response
     
+    except Exception as e:
+        return {"error": f"An error occurred: {str(e)}"}
+    
+
+@app.get('/api/v1/fetch-models')
+async def fetch_models():
+    model = FetchModel()
+    return model.all_models()
+
+@app.post('/api/v1/text/generate')
+async def text_generate(request: Request):
+    data = await request.json()
+    messages = data['messages']
+    choice = data['model']
+    api_key = data['api_key']
+
+    if api_key != "test123":
+        return {"error": "Invalid API key."}
+    
+    if api_key not in data:
+        return {"error": "API key is required."}
+
+    if not messages or not model:
+        return {"error": "Invalid request. 'messages' and 'model' are required."}
+    
+    model = FetchModel().select_model(choice)
+    if not model:
+        return {"error": f"Model '{choice}' is not supported."}
+
+    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()
+        deepinfra_models = DeepinfraAPI().get_model_list()
+
+        if model in together_models:
+            streamModel = TogetherAPI()
+        elif model in xai_models:
+            streamModel = XaiAPI()
+        elif model in groq_models:
+            streamModel = GroqAPI()
+        elif model in deepinfra_models:
+            streamModel = DeepinfraAPI()
+        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)}"}

models/fetch.py

@@ -0,0 +1,145 @@
+import random
+
+class FetchModel:
+
+    @staticmethod
+    def all_models():
+
+        models = [
+            {
+                "id": "llama-4-maverick-17b",
+                "name": "LLaMA 4 Maverick 17B",
+                "description": "Meta AI's 17B-parameter general-purpose model from the LLaMA 4 series, designed for high-quality text generation.",
+                "type": "text"
+            },
+            {
+                "id": "llama-4-scout-17b",
+                "name": "LLaMA 4 Scout 17B",
+                "description": "Instruction-tuned version of LLaMA 4 by Meta, tailored for alignment and structured task performance.",
+                "type": "text"
+            },
+            {
+                "id": "llama-3.1-8b",
+                "name": "LLaMA 3.1 8B",
+                "description": "A fast and lightweight 8B parameter model from Meta's LLaMA 3.1 line, optimized for low-latency inference.",
+                "type": "text"
+            },
+            {
+                "id": "llama-3.3-70b",
+                "name": "LLaMA 3.3 70B",
+                "description": "Meta's 70B parameter flagship model from LLaMA 3.3, designed for state-of-the-art language understanding and generation.",
+                "type": "text"
+            },
+            {
+                "id": "deepseek-r1",
+                "name": "DeepSeek R1",
+                "description": "DeepSeek AIs foundational model focused on reasoning, language understanding, and long-context comprehension.",
+                "type": "text"
+            },
+            {
+                "id": "deepseek-v3",
+                "name": "DeepSeek V3",
+                "description": "DeepSeek AIs third-generation model with enhanced reasoning and coding abilities.",
+                "type": "text"
+            },
+            {
+                "id": "qwen-2.5-72b",
+                "name": "Qwen 2.5 72B",
+                "description": "Large instruction-tuned language model from Qwen 2.5 family, optimized for complex NLP tasks.",
+                "type": "text"
+            },
+            {
+                "id": "gemma-2-27b",
+                "name": "Gemma 2 27B",
+                "description": "Googles instruction-tuned model with 27B parameters, capable of high-performance natural language understanding.",
+                "type": "text"
+            },
+            {
+                "id": "grok-3",
+                "name": "Grok 3",
+                "description": "xAI's general-purpose large language model designed for reasoning, conversation, and alignment.",
+                "type": "text"
+            },
+            {
+                "id": "grok-3-fast",
+                "name": "Grok 3 (Fast)",
+                "description": "A low-latency version of Grok 3 optimized for responsiveness and quick task execution.",
+                "type": "text"
+            },
+            {
+                "id": "grok-3-mini",
+                "name": "Grok 3 Mini",
+                "description": "A smaller variant of Grok 3 designed for lighter inference while maintaining core capabilities.",
+                "type": "text"
+            },
+            {
+                "id": "grok-3-mini-fast",
+                "name": "Grok 3 Mini (Fast)",
+                "description": "Fast and lightweight variant of Grok 3 Mini for extremely low-latency use cases.",
+                "type": "text"
+            },
+            {
+                "id": "grok-2-1212",
+                "name": "Grok 2 1212",
+                "description": "An earlier generation Grok model from xAI, optimized for general language tasks with improved efficiency.",
+                "type": "text"
+            }
+        ]
+        
+        return models
+    
+    async def select_model(id):
+        if id == "llama-4-maverick-17b":
+            options = ['meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8']
+            model = random.choice(options)
+            return model
+        elif id == "llama-4-scout-17b":
+            options = ['meta-llama/Llama-4-Scout-17B-16E-Instruct', 'meta-llama/llama-4-scout-17b-16e-instruct']
+            model = random.choice(options)
+            return model
+        elif id == "llama-3.1-8b":
+            options = ['llama-3.1-8b-instant']
+            model = random.choice(options)
+            return model
+        elif id == "llama-3.3-70b":
+            options = ['meta-llama/Llama-3.3-70B-Instruct-Turbo', 'llama-3.3-70b-versatile']
+            model = random.choice(options)
+            return model
+        elif id == "deepseek-r1":
+            options = ['deepseek-ai/DeepSeek-R1', 'deepseek-r1-distill-llama-70b']
+            model = random.choice(options)
+            return model
+        elif id == "deepseek-v3":
+            options = ['deepseek-ai/DeepSeek-V3']
+            model = random.choice(options)
+            return model
+        elif id == "qwen-2.5-72b":
+            options = ['Qwen/Qwen2.5-VL-72B-Instruct', 'Qwen/Qwen2.5-72B-Instruct']
+            model = random.choice(options)
+            return model
+        elif id == "gemma-2-27b":
+            options = ['google/gemma-2-27b-it']
+            model = random.choice(options)
+            return model
+        elif id == "grok-3":
+            options = ['grok-3']
+            model = random.choice(options)
+            return model
+        elif id == "grok-3-fast":
+            options = ['grok-3-fast']
+            model = random.choice(options)
+            return model
+        elif id == "grok-3-mini":
+            options = ['grok-3-mini']
+            model = random.choice(options)
+            return model
+        elif id == "grok-3-mini-fast":
+            options = ['grok-3-mini-fast']
+            model = random.choice(options)
+            return model
+        elif id == "grok-2-1212":
+            options = ['grok-2-1212']
+            model = random.choice(options)
+            return model
+
+

test.py

@@ -1,47 +1,47 @@
-# 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 = "Qwen/Qwen2.5-72B-Instruct"
-
-# 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}")
+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 = "Qwen/Qwen2.5-72B-Instruct"
+
+url = "https://chipling-api.hf.space/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}")
 
 
 import requests
 
-url = 'http://127.0.1:8000/api/v1/generate-images'
+url = 'https://chipling-api.hf.space/api/v1/generate-images'
 
 query = {
     'prompt': 'a beautiful landscape',
-    'model': 'black-forest-labs/FLUX.1-dev',
+    'model': 'fal-ai/fast-sdxl',
 }
 
 response = requests.post(url, json=query)