change billing to org

model_params.cfg

@@ -3,6 +3,8 @@ PROVIDER = huggingface
 MODEL = meta-llama/Meta-Llama-3-8B-Instruct
 MAX_TOKENS = 512
 TEMPERATURE = 0.2
+INFERENCE_PROVIDER = novita
+ORGANIZATION = GIZ
 
 [reader]
 TYPE = INF_PROVIDERS

utils/generator.py

@@ -34,10 +34,10 @@ def getconfig(configfile_path: str):
 def get_auth(provider: str) -> dict:
     """Get authentication configuration for different providers"""
     auth_configs = {
-        #"openai": {"api_key": os.getenv("OPENAI_API_KEY")},
+        "openai": {"api_key": os.getenv("OPENAI_API_KEY")},
         "huggingface": {"api_key": os.getenv("HF_TOKEN")},
-        #"anthropic": {"api_key": os.getenv("ANTHROPIC_API_KEY")},
-        #"cohere": {"api_key": os.getenv("COHERE_API_KEY")},
+        "anthropic": {"api_key": os.getenv("ANTHROPIC_API_KEY")},
+        "cohere": {"api_key": os.getenv("COHERE_API_KEY")},
     }
     
     if provider not in auth_configs:
@@ -61,6 +61,8 @@ PROVIDER = config.get("generator", "PROVIDER")
 MODEL = config.get("generator", "MODEL")
 MAX_TOKENS = int(config.get("generator", "MAX_TOKENS"))
 TEMPERATURE = float(config.get("generator", "TEMPERATURE"))
+INFERENCE_PROVIDER = config.get("generator", "INFERENCE_PROVIDER")
+ORGANIZATION = config.get("generator", "ORGANIZATION")
 
 # Set up authentication for the selected provider
 auth_config = get_auth(PROVIDER)
@@ -71,7 +73,6 @@ def get_chat_model():
         "temperature": TEMPERATURE,
         "max_tokens": MAX_TOKENS,
     }
-    logging.info(f"provider is {PROVIDER}")
     
     # if PROVIDER == "openai":
     #     return ChatOpenAI(
@@ -90,13 +91,15 @@ def get_chat_model():
     #         model=MODEL,
     #         cohere_api_key=auth_config["api_key"],
     #         **common_params
-    #    )
+    #     )
     if PROVIDER == "huggingface":
         # Initialize HuggingFaceEndpoint with explicit parameters
         llm = HuggingFaceEndpoint(
             repo_id=MODEL,
             huggingfacehub_api_token=auth_config["api_key"],
             task="text-generation",
+            provider=INFERENCE_PROVIDER,     
+            server_kwargs={"bill_to": ORGANIZATION},
             temperature=TEMPERATURE,
             max_new_tokens=MAX_TOKENS
         )
@@ -256,7 +259,9 @@ async def generate(query: str, context: Union[str, List[Dict[str, Any]]]) -> str
     try:
         messages = build_messages(query, formatted_context)
         answer = await _call_llm(messages)
+
         return answer
+        
     except Exception as e:
         logging.exception("Generation failed")
-        return f"Error: {str(e)}"
+        return f"Error: {str(e)}"