rm client class

Author: balogh.adam@icloud.com

examples/alpha/create_workflow.py

@@ -2,7 +2,7 @@
 
 import opengradient as og
 
-og_client = og.Client(private_key=os.environ.get("OG_PRIVATE_KEY"))
+alpha = og.Alpha(private_key=os.environ.get("OG_PRIVATE_KEY"))
 
 # Define model input
 input_query = og.HistoricalInputQuery(
@@ -21,7 +21,7 @@
 model_cid = "hJD2Ja3akZFt1A2LT-D_1oxOCz_OtuGYw4V9eE1m39M"
 
 # Deploy schedule
-contract_address = og_client.alpha.new_workflow(
+contract_address = alpha.new_workflow(
     model_cid=model_cid,
     input_query=input_query,
     # Input name in ONNX model

examples/alpha/run_embeddings_model.py

@@ -2,7 +2,7 @@
 
 import opengradient as og
 
-og_client = og.Client(private_key=os.environ.get("OG_PRIVATE_KEY"))
+alpha = og.Alpha(private_key=os.environ.get("OG_PRIVATE_KEY"))
 
 queries = [
     "how much protein should a female eat",
@@ -14,7 +14,7 @@
     "Since you're reading this, you are probably someone from a judo background or someone who is just wondering how judo techniques can be applied under wrestling rules. So without further ado, let's get to the question. Are Judo throws allowed in wrestling? Yes, judo throws are allowed in freestyle and folkstyle wrestling. You only need to be careful to follow the slam rules when executing judo throws. In wrestling, a slam is lifting and returning an opponent to the mat with unnecessary force.",
 ]
 
-model_embeddings = og_client.alpha.infer(
+model_embeddings = alpha.infer(
     model_cid="intfloat/multilingual-e5-large-instruct",
     model_input={"queries": queries, "instruction": instruction, "passages": passages},
     inference_mode=og.InferenceMode.VANILLA,

examples/alpha/run_inference.py

@@ -2,9 +2,9 @@
 
 import opengradient as og
 
-og_client = og.Client(private_key=os.environ.get("OG_PRIVATE_KEY"))
+alpha = og.Alpha(private_key=os.environ.get("OG_PRIVATE_KEY"))
 
-inference_result = og_client.alpha.infer(
+inference_result = alpha.infer(
     model_cid="hJD2Ja3akZFt1A2LT-D_1oxOCz_OtuGYw4V9eE1m39M",
     model_input={
         "open_high_low_close": [

examples/alpha/use_workflow.py

@@ -2,16 +2,16 @@
 
 import opengradient as og
 
-og_client = og.Client(private_key=os.environ.get("OG_PRIVATE_KEY"))
+alpha = og.Alpha(private_key=os.environ.get("OG_PRIVATE_KEY"))
 
-model_output = og_client.alpha.read_workflow_result(
+model_output = alpha.read_workflow_result(
     # This is the workflow contract address that you previously deployed
     contract_address="0x58Dd93E1aE6B6f21b479b3B2913B055eFD2E74Ee"
 )
 
 print(f"Latest model prediction: {model_output.numbers}")
 
-model_output_history = og_client.alpha.read_workflow_history(
+model_output_history = alpha.read_workflow_history(
     # This is the workflow contract address that you previously deployed
     contract_address="0x58Dd93E1aE6B6f21b479b3B2913B055eFD2E74Ee",
     num_results=5,

examples/create_model_repo.py

@@ -2,12 +2,9 @@
 
 import opengradient as og
 
-og_client = og.Client(
-    private_key=os.environ.get("OG_PRIVATE_KEY"),
+hub = og.ModelHub(
     email=os.environ.get("OG_MODEL_HUB_EMAIL"),
     password=os.environ.get("OG_MODEL_HUB_PASSWORD"),
 )
 
-og_client.model_hub.create_model(
-    model_name="example-model", model_desc="An example machine learning model for demonstration purposes", version="1.0.0"
-)
+hub.create_model(model_name="example-model", model_desc="An example machine learning model for demonstration purposes", version="1.0.0")

examples/langchain_react_agent.py

@@ -15,13 +15,15 @@
 
 import opengradient as og
 
+private_key = os.environ.get("OG_PRIVATE_KEY")
+
 # One-time Permit2 approval for OPG spending (idempotent)
-client = og.init(private_key=os.environ.get("OG_PRIVATE_KEY"))
-client.llm.ensure_opg_approval(opg_amount=5)
+llm_client = og.LLM(private_key=private_key)
+llm_client.ensure_opg_approval(opg_amount=5)
 
 # Create the OpenGradient LangChain adapter
 llm = og.agents.langchain_adapter(
-    private_key=os.environ.get("OG_PRIVATE_KEY"),
+    private_key=private_key,
     model_cid=og.TEE_LLM.GPT_4_1_2025_04_14,
     max_tokens=300,
     x402_settlement_mode=og.x402SettlementMode.INDIVIDUAL_FULL,

examples/llm_chat.py

@@ -9,16 +9,14 @@
 
 
 async def main():
-    client = og.Client(
-        private_key=os.environ.get("OG_PRIVATE_KEY"),
-    )
-    client.llm.ensure_opg_approval(opg_amount=2)
+    llm = og.LLM(private_key=os.environ.get("OG_PRIVATE_KEY"))
+    llm.ensure_opg_approval(opg_amount=2)
 
     messages = [
         {"role": "user", "content": "What is the capital of France?"},
     ]
 
-    result = await client.llm.chat(
+    result = await llm.chat(
         model=og.TEE_LLM.GEMINI_2_5_FLASH,
         messages=messages,
         max_tokens=300,

examples/llm_chat_streaming.py

@@ -5,18 +5,16 @@
 
 
 async def main():
-    client = og.Client(
-        private_key=os.environ.get("OG_PRIVATE_KEY"),
-    )
-    client.llm.ensure_opg_approval(opg_amount=1)
+    llm = og.LLM(private_key=os.environ.get("OG_PRIVATE_KEY"))
+    llm.ensure_opg_approval(opg_amount=1)
 
     messages = [
         {"role": "user", "content": "What is Python?"},
         {"role": "assistant", "content": "Python is a high-level programming language."},
         {"role": "user", "content": "What makes it good for beginners?"},
     ]
 
-    stream = await client.llm.chat(
+    stream = await llm.chat(
         model=og.TEE_LLM.GPT_4_1_2025_04_14,
         messages=messages,
         x402_settlement_mode=og.x402SettlementMode.INDIVIDUAL_FULL,

examples/llm_tool_calling.py

@@ -13,10 +13,7 @@
 
 
 async def main():
-    # Initialize client
-    client = og.Client(
-        private_key=os.environ.get("OG_PRIVATE_KEY"),
-    )
+    llm = og.LLM(private_key=os.environ.get("OG_PRIVATE_KEY"))
 
     # Define a simple tool
     tools = [
@@ -54,15 +51,15 @@ async def main():
     ]
 
     # One-time Permit2 approval for OPG spending (idempotent)
-    client.llm.ensure_opg_approval(opg_amount=5)
+    llm.ensure_opg_approval(opg_amount=5)
 
     print("Testing Gemini tool calls...")
     print(f"Model: {og.TEE_LLM.GEMINI_2_5_FLASH_LITE}")
     print(f"Messages: {messages}")
     print(f"Tools: {tools}")
     print("-" * 50)
 
-    result = await client.llm.chat(
+    result = await llm.chat(
         model=og.TEE_LLM.GEMINI_2_5_FLASH_LITE,
         messages=messages,
         tools=tools,

examples/twins_chat.py

@@ -5,17 +5,14 @@
 
 import opengradient as og
 
-client = og.init(
-    private_key=os.environ.get("OG_PRIVATE_KEY"),
-    twins_api_key=os.environ.get("TWINS_API_KEY"),
-)
+twins = og.Twins(api_key=os.environ.get("TWINS_API_KEY"))
 
 # Chat with Elon Musk
 print("--------------------------------")
 print("Chat with Elon Musk")
 print("--------------------------------")
 
-elon = client.twins.chat(
+elon = twins.chat(
     twin_id="0x1abd463fd6244be4a1dc0f69e0b70cd5",
     model=og.TEE_LLM.GROK_4_1_FAST_NON_REASONING,
     messages=[{"role": "user", "content": "What do you think about AI?"}],
@@ -28,7 +25,7 @@
 print("Chat with Donald Trump")
 print("--------------------------------")
 
-trump = client.twins.chat(
+trump = twins.chat(
     twin_id="0x66ae99aae4324ed580b2787ac5e811f6",
     model=og.TEE_LLM.GROK_4_1_FAST_NON_REASONING,
     messages=[{"role": "user", "content": "What's your plan for America?"}],