opengradient 0.4.3__py3-none-any.whl → 0.4.5__py3-none-any.whl

opengradient/__init__.py

@@ -8,7 +8,7 @@ from .client import Client
 from .defaults import DEFAULT_INFERENCE_CONTRACT_ADDRESS, DEFAULT_RPC_URL
 from .types import LLM, TEE_LLM, HistoricalInputQuery, InferenceMode, LlmInferenceMode, SchedulerParams
 
-from . import llm, mltools
+from . import llm, alphasense
 
 _client = None
 
@@ -367,7 +367,7 @@ __all__ = [
     "read_workflow_result",
     "run_workflow",
     "llm",
-    "mltools"
+    "alphasense",
 ]
 
 __pdoc__ = {
@@ -377,7 +377,7 @@ __pdoc__ = {
     "defaults": False,
     "exceptions": False,
     "llm": True,
-    "mltools": True,
+    "alphasense": True,
     "proto": False,
     "types": False,
     "utils": False,

opengradient/alphasense/__init__.py

@@ -0,0 +1,11 @@
+"""
+OpenGradient AlphaSense Tools
+"""
+
+from .run_model_tool import *
+from .read_workflow_tool import *
+from .types import ToolType
+
+__all__ = ["create_run_model_tool", "create_read_workflow_tool", "ToolType"]
+
+__pdoc__ = {"run_model_tool": False, "read_workflow_tool": False, "types": False}

opengradient/alphasense/read_workflow_tool.py

@@ -0,0 +1,77 @@
+from typing import Callable
+
+from langchain_core.tools import BaseTool, StructuredTool
+
+import opengradient as og
+from .types import ToolType
+
+
+def create_read_workflow_tool(
+    tool_type: ToolType,
+    workflow_contract_address: str,
+    tool_name: str,
+    tool_description: str,
+    output_formatter: Callable[..., str] = lambda x: x,
+) -> BaseTool:
+    """
+    Creates a tool that reads results from a workflow contract on OpenGradient.
+
+    This function generates a tool that can be integrated into either a LangChain pipeline
+    or a Swarm system, allowing the workflow results to be retrieved and formatted as part
+    of a chain of operations.
+
+    Args:
+        tool_type (ToolType): Specifies the framework to create the tool for. Use
+            ToolType.LANGCHAIN for LangChain integration or ToolType.SWARM for Swarm
+            integration.
+        workflow_contract_address (str): The address of the workflow contract from which
+            to read results.
+        tool_name (str): The name to assign to the created tool. This will be used to
+            identify and invoke the tool within the agent.
+        tool_description (str): A description of what the tool does and how it processes
+            the workflow results.
+        output_formatter (Callable[..., str], optional): A function that takes the workflow output
+            and formats it into a string. This ensures the output is compatible with
+            the tool framework. Default returns string as is.
+
+    Returns:
+        BaseTool: For ToolType.LANGCHAIN, returns a LangChain StructuredTool.
+        Callable: For ToolType.SWARM, returns a decorated function with appropriate metadata.
+
+    Raises:
+        ValueError: If an invalid tool_type is provided.
+
+    Examples:
+        >>> def format_output(output):
+        ...     return f"Workflow status: {output.get('status', 'Unknown')}"
+        >>> # Create a LangChain tool
+        >>> langchain_tool = create_read_workflow_tool(
+        ...     tool_type=ToolType.LANGCHAIN,
+        ...     workflow_contract_address="0x123...",
+        ...     tool_name="workflow_reader",
+        ...     output_formatter=format_output,
+        ...     tool_description="Reads and formats workflow execution results"
+        ... )
+        >>> # Create a Swarm tool
+        >>> swarm_tool = create_read_workflow_tool(
+        ...     tool_type=ToolType.SWARM,
+        ...     workflow_contract_address="0x123...",
+        ...     tool_name="workflow_reader",
+        ...     output_formatter=format_output,
+        ...     tool_description="Reads and formats workflow execution results"
+        ... )
+    """
+
+    # define runnable
+    def read_workflow():
+        output = og.read_workflow_result(contract_address=workflow_contract_address)
+        return output_formatter(output)
+
+    if tool_type == ToolType.LANGCHAIN:
+        return StructuredTool.from_function(func=read_workflow, name=tool_name, description=tool_description, args_schema=None)
+    elif tool_type == ToolType.SWARM:
+        read_workflow.__name__ = tool_name
+        read_workflow.__doc__ = tool_description
+        return read_workflow
+    else:
+        raise ValueError(f"Invalid tooltype: {tool_type}")

opengradient/{mltools/model_tool.py → alphasense/run_model_tool.py}

@@ -5,24 +5,15 @@ from langchain_core.tools import BaseTool, StructuredTool
 from pydantic import BaseModel
 
 import opengradient as og
+from .types import ToolType
 
 
-class ToolType(str, Enum):
-    """Indicates the framework the tool is compatible with."""
-
-    LANGCHAIN = "langchain"
-    SWARM = "swarm"
-
-    def __str__(self) -> str:
-        return self.value
-
-
-def create_og_model_tool(
+def create_run_model_tool(
     tool_type: ToolType,
     model_cid: str,
     tool_name: str,
     input_getter: Callable,
-    output_formatter: Callable[..., str],
+    output_formatter: Callable[..., str] = lambda x: x,
     input_schema: Type[BaseModel] = None,
     tool_description: str = "Executes the given ML model",
     inference_mode: og.InferenceMode = og.InferenceMode.VANILLA,
@@ -44,9 +35,9 @@ def create_og_model_tool(
             and invoke the tool within the agent.
         input_getter (Callable): A function that returns the input data required by the model.
             The function should return data in a format compatible with the model's expectations.
-        output_formatter (Callable[..., str]): A function that takes the model output and
+        output_formatter (Callable[..., str], optional): A function that takes the model output and
             formats it into a string. This is required to ensure the output is compatible
-            with the tool framework.
+            with the tool framework. Default returns string as is.
         input_schema (Type[BaseModel], optional): A Pydantic BaseModel class defining the
             input schema. This will be used directly for LangChain tools and converted
             to appropriate annotations for Swarm tools. Default is None.

opengradient/alphasense/types.py

@@ -0,0 +1,11 @@
+from enum import Enum
+
+
+class ToolType(str, Enum):
+    """Indicates the framework the tool is compatible with."""
+
+    LANGCHAIN = "langchain"
+    SWARM = "swarm"
+
+    def __str__(self) -> str:
+        return self.value

opengradient/client.py

@@ -99,7 +99,7 @@ class Client:
             raise ValueError("User not authenticated")
 
         url = "https://api.opengradient.ai/api/v0/models/"
-        headers = {"Authorization": f'Bearer {self._hub_user["idToken"]}', "Content-Type": "application/json"}
+        headers = {"Authorization": f"Bearer {self._hub_user['idToken']}", "Content-Type": "application/json"}
         payload = {"name": model_name, "description": model_desc}
 
         try:
@@ -156,7 +156,7 @@ class Client:
             raise ValueError("User not authenticated")
 
         url = f"https://api.opengradient.ai/api/v0/models/{model_name}/versions"
-        headers = {"Authorization": f'Bearer {self._hub_user["idToken"]}', "Content-Type": "application/json"}
+        headers = {"Authorization": f"Bearer {self._hub_user['idToken']}", "Content-Type": "application/json"}
         payload = {"notes": notes, "is_major": is_major}
 
         try:
@@ -220,7 +220,7 @@ class Client:
             raise FileNotFoundError(f"Model file not found: {model_path}")
 
         url = f"https://api.opengradient.ai/api/v0/models/{model_name}/versions/{version}/files"
-        headers = {"Authorization": f'Bearer {self._hub_user["idToken"]}'}
+        headers = {"Authorization": f"Bearer {self._hub_user['idToken']}"}
 
         logging.info(f"Starting upload for file: {model_path}")
         logging.info(f"File size: {os.path.getsize(model_path)} bytes")
@@ -335,6 +335,7 @@ class Client:
             if len(parsed_logs) < 1:
                 raise OpenGradientError("InferenceResult event not found in transaction logs")
 
+            # TODO: This should return a ModelOutput class object
             model_output = utils.convert_to_model_output(parsed_logs[0]["args"])
             return tx_hash.hex(), model_output
 
@@ -373,7 +374,7 @@ class Client:
             if inference_mode != LlmInferenceMode.VANILLA and inference_mode != LlmInferenceMode.TEE:
                 raise OpenGradientError("Invalid inference mode %s: Inference mode must be VANILLA or TEE" % inference_mode)
 
-            if inference_mode == LlmInferenceMode.TEE and model_cid not in TEE_LLM:
+            if inference_mode == LlmInferenceMode.TEE and model_cid not in [llm.value for llm in TEE_LLM]:
                 raise OpenGradientError("That model CID is not supported yet supported for TEE inference")
 
             contract = self._blockchain.eth.contract(address=self._inference_hub_contract_address, abi=self._inference_abi)
@@ -591,7 +592,7 @@ class Client:
             raise ValueError("User not authenticated")
 
         url = f"https://api.opengradient.ai/api/v0/models/{model_name}/versions/{version}/files"
-        headers = {"Authorization": f'Bearer {self._hub_user["idToken"]}'}
+        headers = {"Authorization": f"Bearer {self._hub_user['idToken']}"}
 
         logging.debug(f"List Files URL: {url}")
         logging.debug(f"Headers: {headers}")
@@ -765,18 +766,19 @@ class Client:
 
         print("📦 Deploying workflow contract...")
 
-
         # Create contract instance
         contract = self._blockchain.eth.contract(abi=abi, bytecode=bytecode)
 
         # Deploy contract with constructor arguments
-        transaction = contract.constructor().build_transaction({
-            "from": self._wallet_account.address,
-            "nonce": self._blockchain.eth.get_transaction_count(self._wallet_account.address, "pending"),
-            "gas": 15000000,
-            "gasPrice": self._blockchain.eth.gas_price,
-            "chainId": self._blockchain.eth.chain_id,
-        })
+        transaction = contract.constructor().build_transaction(
+            {
+                "from": self._wallet_account.address,
+                "nonce": self._blockchain.eth.get_transaction_count(self._wallet_account.address, "pending"),
+                "gas": 15000000,
+                "gasPrice": self._blockchain.eth.gas_price,
+                "chainId": self._blockchain.eth.chain_id,
+            }
+        )
 
         signed_txn = self._wallet_account.sign_transaction(transaction)
         tx_hash = self._blockchain.eth.send_raw_transaction(signed_txn.raw_transaction)
@@ -837,7 +839,7 @@ class Client:
 
         return contract_address
 
-    def read_workflow_result(self, contract_address: str) -> Any:
+    def read_workflow_result(self, contract_address: str) -> ModelOutput:
         """
         Reads the latest inference result from a deployed workflow contract.
 
@@ -845,7 +847,7 @@ class Client:
             contract_address (str): Address of the deployed workflow contract
 
         Returns:
-            Any: The inference result from the contract
+            ModelOutput: The inference result from the contract
 
         Raises:
             ContractLogicError: If the transaction fails
@@ -856,7 +858,8 @@ class Client:
 
         # Get the result
         result = contract.functions.getInferenceResult().call()
-        return result
+
+        return utils.convert_array_to_model_output(result)
 
     def run_workflow(self, contract_address: str) -> ModelOutput:
         """
@@ -898,7 +901,8 @@ class Client:
 
         # Get the inference result from the contract
         result = contract.functions.getInferenceResult().call()
-        return result
+
+        return utils.convert_array_to_model_output(result)
 
 
 def run_with_retry(txn_function, max_retries=DEFAULT_MAX_RETRY, retry_delay=DEFAULT_RETRY_DELAY_SEC):
@@ -910,21 +914,23 @@ def run_with_retry(txn_function, max_retries=DEFAULT_MAX_RETRY, retry_delay=DEFA
         max_retries (int): Maximum number of retry attempts
         retry_delay (float): Delay in seconds between retries for nonce issues
     """
-    NONCE_TOO_LOW = 'nonce too low'
-    NONCE_TOO_HIGH = 'nonce too high'
+    NONCE_TOO_LOW = "nonce too low"
+    NONCE_TOO_HIGH = "nonce too high"
+    INVALID_NONCE = "invalid nonce"
 
     effective_retries = max_retries if max_retries is not None else DEFAULT_MAX_RETRY
-    
+
     for attempt in range(effective_retries):
         try:
             return txn_function()
         except Exception as e:
             error_msg = str(e).lower()
-            
-            if NONCE_TOO_LOW in error_msg or NONCE_TOO_HIGH in error_msg:
-                if attempt == max_retries - 1:
+
+            nonce_errors = [INVALID_NONCE, NONCE_TOO_LOW, NONCE_TOO_HIGH]
+            if any(error in error_msg for error in nonce_errors):
+                if attempt == effective_retries - 1:
                     raise OpenGradientError(f"Transaction failed after {effective_retries} attempts: {e}")
                 time.sleep(retry_delay)
                 continue
-            
+
             raise

opengradient/defaults.py

@@ -1,8 +1,8 @@
 # Default variables
-DEFAULT_RPC_URL="http://18.188.176.119:8545"
-DEFAULT_OG_FAUCET_URL="https://faucet.opengradient.ai/?address="
-DEFAULT_HUB_SIGNUP_URL="https://hub.opengradient.ai/signup"
-DEFAULT_INFERENCE_CONTRACT_ADDRESS="0x8383C9bD7462F12Eb996DD02F78234C0421A6FaE"
-DEFAULT_BLOCKCHAIN_EXPLORER="https://explorer.opengradient.ai/tx/"
-DEFAULT_IMAGE_GEN_HOST="18.217.25.69"
-DEFAULT_IMAGE_GEN_PORT=5125
+DEFAULT_RPC_URL = "http://18.188.176.119:8545"
+DEFAULT_OG_FAUCET_URL = "https://faucet.opengradient.ai/?address="
+DEFAULT_HUB_SIGNUP_URL = "https://hub.opengradient.ai/signup"
+DEFAULT_INFERENCE_CONTRACT_ADDRESS = "0x8383C9bD7462F12Eb996DD02F78234C0421A6FaE"
+DEFAULT_BLOCKCHAIN_EXPLORER = "https://explorer.opengradient.ai/tx/"
+DEFAULT_IMAGE_GEN_HOST = "18.217.25.69"
+DEFAULT_IMAGE_GEN_PORT = 5125

opengradient/types.py

@@ -2,6 +2,7 @@ import time
 from dataclasses import dataclass
 from enum import Enum, IntEnum
 from typing import Dict, List, Optional, Tuple, Union
+import numpy as np
 
 
 class CandleOrder(IntEnum):
@@ -88,8 +89,13 @@ class LlmInferenceMode:
 
 @dataclass
 class ModelOutput:
-    numbers: List[NumberTensor]
-    strings: List[StringTensor]
+    """
+    Model output struct based on translations from smart contract.
+    """
+
+    numbers: Dict[str, np.ndarray]
+    strings: Dict[str, np.ndarray]
+    jsons: Dict[str, np.ndarray]  # Converts to JSON dictionary
     is_simulation_result: bool
 
 
@@ -130,9 +136,9 @@ class Abi:
 
 class LLM(str, Enum):
     """Enum for available LLM models"""
+
     META_LLAMA_3_8B_INSTRUCT = "meta-llama/Meta-Llama-3-8B-Instruct"
     LLAMA_3_2_3B_INSTRUCT = "meta-llama/Llama-3.2-3B-Instruct"
-    MISTRAL_7B_INSTRUCT_V3 = "mistralai/Mistral-7B-Instruct-v0.3"
     QWEN_2_5_72B_INSTRUCT = "Qwen/Qwen2.5-72B-Instruct"
     META_LLAMA_3_1_70B_INSTRUCT = "meta-llama/Llama-3.1-70B-Instruct"
     DOBBY_UNHINGED_3_1_8B = "SentientAGI/Dobby-Mini-Unhinged-Llama-3.1-8B"
@@ -141,6 +147,7 @@ class LLM(str, Enum):
 
 class TEE_LLM(str, Enum):
     """Enum for LLM models available for TEE execution"""
+
     META_LLAMA_3_1_70B_INSTRUCT = "meta-llama/Llama-3.1-70B-Instruct"
 
 

opengradient/utils.py

@@ -6,6 +6,8 @@ from typing import Dict, List, Tuple
 import numpy as np
 from web3.datastructures import AttributeDict
 
+from .types import ModelOutput
+
 
 def convert_to_fixed_point(number: float) -> Tuple[int, int]:
     """
@@ -170,3 +172,49 @@ def convert_to_model_output(event_data: AttributeDict) -> Dict[str, np.ndarray]:
     logging.debug(f"Parsed output: {output_dict}")
 
     return output_dict
+
+
+def convert_array_to_model_output(array_data: List) -> ModelOutput:
+    """
+    Converts inference output (in array form) into a user-readable ModelOutput class.
+    This expects data from the smart contract returned as 4 element array:
+        array_data[0] = NumberTensor
+        array_data[1] = StringTensor
+        array_data[2] = JsonTensor
+        array_data[3] = Bool
+    """
+    # Parse number tensors
+    number_data = {}
+    for tensor in array_data[0]:
+        name = tensor[0]
+        values = tensor[1]
+        shape = tensor[2]
+
+        # Convert from fixed point into np.float32
+        converted_values = []
+        for value in values:
+            converted_values.append(convert_to_float32(value=value[0], decimals=value[1]))
+
+        number_data[name] = np.array(converted_values).reshape(shape)
+
+    # Parse string tensors
+    string_data = {}
+    for tensor in array_data[1]:
+        name = tensor[0]
+        values = tensor[1]
+        shape = tensor[2]
+        string_data[name] = np.array(values).reshape(shape)
+
+    # Parse JSON tensors
+    json_data = {}
+    for tensor in array_data[2]:
+        name = tensor[0]
+        value = tensor[1]
+        json_data[name] = np.array(json.loads(value))
+
+    return ModelOutput(
+        numbers=number_data,
+        strings=string_data,
+        jsons=json_data,
+        is_simulation_result=array_data[3],
+    )

{opengradient-0.4.3.dist-info → opengradient-0.4.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: opengradient
-Version: 0.4.3
+Version: 0.4.5
 Summary: Python SDK for OpenGradient decentralized model management & inference services
 Author-email: OpenGradient <oliver@opengradient.ai>
 License: MIT License

opengradient-0.4.5.dist-info/RECORD

@@ -0,0 +1,27 @@
+opengradient/__init__.py,sha256=RMjHgZ_Ef_l2cjN5a-81XYYx0LtWGKNZCg90-1zl3k0,12893
+opengradient/account.py,sha256=5wrYpws_1lozjOFjLCTHtxgoxK-LmObDAaVy9eDcJY4,1145
+opengradient/cli.py,sha256=5PNwcVwmkJb8A8Apj_JjkG9vDDyNEq0j51omzzQWHIo,25237
+opengradient/client.py,sha256=tPqeRT5e5zwB2xF-57z3ZcsdMYEGHvlhdBQTKL4QPP4,41811
+opengradient/defaults.py,sha256=_WzWawpJ5j2V7sbTYGA3L_gqdftslLLqlRPQ2LBsCHY,417
+opengradient/exceptions.py,sha256=88tfegboGtlehQcwhxsl6ZzhLJWZWlkf_bkHTiCtXpo,3391
+opengradient/types.py,sha256=OeQsS95p3FdSF6O04xX2pEvnyemHonyNs_QxevDAdS8,4268
+opengradient/utils.py,sha256=PIECAkk0lvj8TfBItugv01Hi_cJai09jGW34zhzsJ7E,8321
+opengradient/abi/ModelExecutorHistorical.abi,sha256=AEceI9y-VyeaAvHna6AaCH8XOgF8nzSLGEHWCr89Ddw,2625
+opengradient/abi/inference.abi,sha256=MR5u9npZ-Yx2EqRW17_M-UnGgFF3mMEMepOwaZ-Bkgc,7040
+opengradient/alphasense/__init__.py,sha256=Ah6IpoPTb6UkY7ImOWLJs3tjlxDJx6vZVR7p5IwP_Ks,292
+opengradient/alphasense/read_workflow_tool.py,sha256=p7lMFVgu4wZvvkjqlajBbLOhaUmmb7spra-wJhBm7B0,3205
+opengradient/alphasense/run_model_tool.py,sha256=UamcotxZcKfSGhFFmRTz6VRMvQdrL96yI3dCfKYsgo4,4971
+opengradient/alphasense/types.py,sha256=uxk4JQKbaS2cM3ZiKpdHQb234OJ5ylprNR5vi01QFzA,220
+opengradient/llm/__init__.py,sha256=b_msjZstmTRD20LOaZbBxxigtnL7vxh7CziiyVlqpAo,1104
+opengradient/llm/og_langchain.py,sha256=F9gdrwqMFPjLUakUfSjc4Obx8qIvf7HIphe6eM3ObZo,4322
+opengradient/llm/og_openai.py,sha256=9MA3HDotjcJbbcGJ7DYZUA990QHQLdWpxAYhJSsTiz0,3708
+opengradient/proto/__init__.py,sha256=AhaSmrqV0TXGzCKaoPV8-XUvqs2fGAJBM2aOmDpkNbE,55
+opengradient/proto/infer.proto,sha256=13eaEMcppxkBF8yChptsX9HooWFwJKze7oLZNl-LEb8,1217
+opengradient/proto/infer_pb2.py,sha256=sGWDDVumYhXoCJTG9rLyvKu4XyaEjPE_b038kbNlj7w,3484
+opengradient/proto/infer_pb2_grpc.py,sha256=q42_eZ7OZCMTXdWocYA4Ka3B0c3B74dOhfqdaIOO5AU,6700
+opengradient-0.4.5.dist-info/LICENSE,sha256=xEcvQ3AxZOtDkrqkys2Mm6Y9diEnaSeQRKvxi-JGnNA,1069
+opengradient-0.4.5.dist-info/METADATA,sha256=yc7mqP1VaPx6IeBVJ4cSoGrepN_0cJz1XBhvF02UAmA,5832
+opengradient-0.4.5.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+opengradient-0.4.5.dist-info/entry_points.txt,sha256=yUKTaJx8RXnybkob0J62wVBiCp_1agVbgw9uzsmaeJc,54
+opengradient-0.4.5.dist-info/top_level.txt,sha256=oC1zimVLa2Yi1LQz8c7x-0IQm92milb5ax8gHBHwDqU,13
+opengradient-0.4.5.dist-info/RECORD,,

opengradient/mltools/__init__.py

@@ -1,9 +0,0 @@
-"""
-OpenGradient AlphaSense Tools
-"""
-
-from .model_tool import *
-
-__all__ = ["create_og_model_tool", "ToolType"]
-
-__pdoc__ = {"model_tool": False}

opengradient-0.4.3.dist-info/RECORD

@@ -1,25 +0,0 @@
-opengradient/__init__.py,sha256=81JA72atkYcZqE1o8ZUT77bHTlUGyZS8-xQUh2-uH5E,12883
-opengradient/account.py,sha256=5wrYpws_1lozjOFjLCTHtxgoxK-LmObDAaVy9eDcJY4,1145
-opengradient/cli.py,sha256=5PNwcVwmkJb8A8Apj_JjkG9vDDyNEq0j51omzzQWHIo,25237
-opengradient/client.py,sha256=clDMNOjqC8x61bq5P3NXJp5__I5zAfSTTnXpIXXTpAg,41505
-opengradient/defaults.py,sha256=XQ9q-zC-QYaa1ONhGhniK1ZCO_ryiTjAWbYO3QCvXZ8,403
-opengradient/exceptions.py,sha256=88tfegboGtlehQcwhxsl6ZzhLJWZWlkf_bkHTiCtXpo,3391
-opengradient/types.py,sha256=oLJlC5hE84n63VN7M4YnN6Q1I-RlHt6VIvk-coPkMpM,4159
-opengradient/utils.py,sha256=hf1dQvOHdCFthrAr_Wif_PNn6-C3zZaa3QCZX1HMWoA,6911
-opengradient/abi/ModelExecutorHistorical.abi,sha256=AEceI9y-VyeaAvHna6AaCH8XOgF8nzSLGEHWCr89Ddw,2625
-opengradient/abi/inference.abi,sha256=MR5u9npZ-Yx2EqRW17_M-UnGgFF3mMEMepOwaZ-Bkgc,7040
-opengradient/llm/__init__.py,sha256=b_msjZstmTRD20LOaZbBxxigtnL7vxh7CziiyVlqpAo,1104
-opengradient/llm/og_langchain.py,sha256=F9gdrwqMFPjLUakUfSjc4Obx8qIvf7HIphe6eM3ObZo,4322
-opengradient/llm/og_openai.py,sha256=9MA3HDotjcJbbcGJ7DYZUA990QHQLdWpxAYhJSsTiz0,3708
-opengradient/mltools/__init__.py,sha256=JU1VDzYb-rpko_hn9IlwjOvy_dfW1hvxBCBC2xrnvUM,147
-opengradient/mltools/model_tool.py,sha256=dNoznwAiauff961EzM_9raYGdwcPLIqxIsPE1yCuWPU,5086
-opengradient/proto/__init__.py,sha256=AhaSmrqV0TXGzCKaoPV8-XUvqs2fGAJBM2aOmDpkNbE,55
-opengradient/proto/infer.proto,sha256=13eaEMcppxkBF8yChptsX9HooWFwJKze7oLZNl-LEb8,1217
-opengradient/proto/infer_pb2.py,sha256=sGWDDVumYhXoCJTG9rLyvKu4XyaEjPE_b038kbNlj7w,3484
-opengradient/proto/infer_pb2_grpc.py,sha256=q42_eZ7OZCMTXdWocYA4Ka3B0c3B74dOhfqdaIOO5AU,6700
-opengradient-0.4.3.dist-info/LICENSE,sha256=xEcvQ3AxZOtDkrqkys2Mm6Y9diEnaSeQRKvxi-JGnNA,1069
-opengradient-0.4.3.dist-info/METADATA,sha256=Lp8Bujqlo5R1uYhaQQlwNzkNcCar8VCCE5SQElfWMnw,5832
-opengradient-0.4.3.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-opengradient-0.4.3.dist-info/entry_points.txt,sha256=yUKTaJx8RXnybkob0J62wVBiCp_1agVbgw9uzsmaeJc,54
-opengradient-0.4.3.dist-info/top_level.txt,sha256=oC1zimVLa2Yi1LQz8c7x-0IQm92milb5ax8gHBHwDqU,13
-opengradient-0.4.3.dist-info/RECORD,,