opengradient 0.5.8__tar.gz → 0.5.10__tar.gz

{opengradient-0.5.8/src/opengradient.egg-info → opengradient-0.5.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: opengradient
-Version: 0.5.8
+Version: 0.5.10
 Summary: Python SDK for OpenGradient decentralized model management & inference services
 Author-email: OpenGradient <kyle@vannalabs.ai>
 License-Expression: MIT
@@ -23,7 +23,7 @@ Requires-Dist: requests>=2.32.3
 Requires-Dist: langchain>=0.3.7
 Requires-Dist: openai>=1.58.1
 Requires-Dist: pydantic>=2.9.2
-Requires-Dist: og-test-x402==0.0.1
+Requires-Dist: og-test-x402==0.0.9
 Dynamic: license-file
 
 # OpenGradient Python SDK
@@ -35,6 +35,7 @@ A Python SDK for decentralized model management and inference services on the Op
 - Model management and versioning
 - Decentralized model inference
 - Support for LLM inference with various models
+- **Trusted Execution Environment (TEE) inference** with cryptographic attestation
 - End-to-end verified AI execution
 - Command-line interface (CLI) for direct access
 
@@ -46,7 +47,6 @@ Browse and discover AI models on our [Model Hub](https://hub.opengradient.ai/).
 - Direct integration with the SDK
 
 ## Installation
-
 ```bash
 pip install opengradient
 ```
@@ -62,7 +62,6 @@ You'll need two accounts to use the SDK:
 - **OpenGradient account**: Use an existing Ethereum-compatible wallet or create a new one via SDK
 
 The easiest way to set up your accounts is through our configuration wizard:
-
 ```bash
 opengradient config init
 ```
@@ -73,7 +72,6 @@ This wizard will:
 - Direct you to our Test Faucet for devnet tokens
 
 ### 2. Initialize the SDK
-
 ```python
 import opengradient as og
 og.init(private_key="<private_key>", email="<email>", password="<password>")
@@ -82,8 +80,6 @@ og.init(private_key="<private_key>", email="<email>", password="<password>")
 ### 3. Basic Usage
 
 Browse available models on our [Model Hub](https://hub.opengradient.ai/) or create and upload your own:
-
-
 ```python
 # Create and upload a model
 og.create_model(
@@ -101,20 +97,41 @@ result = og.infer(
 )
 ```
 
-### 4. Examples
+### 4. TEE (Trusted Execution Environment) Inference
+
+OpenGradient supports secure, verifiable inference through TEE for leading LLM providers. Access models from OpenAI, Anthropic, Google, and xAI with cryptographic attestation:
+```python
+from opengradient import TEE_LLM
+
+# Use TEE-enabled models for verifiable AI execution
+result = og.infer(
+    model_cid=TEE_LLM.CLAUDE_3_7_SONNET,  # or any other TEE_LLM model
+    model_inputs={"prompt": "Your prompt here"},
+    inference_mode=og.InferenceMode.TEE
+)
+```
+
+**Available TEE Models:**
+The SDK includes models from multiple providers accessible via the `TEE_LLM` enum:
+- **OpenAI**: GPT-4.1, GPT-4o, o4-mini
+- **Anthropic**: Claude 3.7 Sonnet, Claude 3.5 Haiku, Claude 4.0 Sonnet
+- **Google**: Gemini 2.5 Flash, Gemini 2.5 Pro, and more
+- **xAI**: Grok 3 Beta, Grok 4.1 Fast, and other Grok variants
+
+For the complete list of available models, check the `TEE_LLM` enum in your IDE autocomplete or see the [API documentation](https://docs.opengradient.ai/).
+
+### 5. Examples
 
 See code examples under [examples](./examples).
 
 ## CLI Usage
 
 The SDK includes a command-line interface for quick operations. First, verify your configuration:
-
 ```bash
 opengradient config show
 ```
 
 Run a test inference:
-
 ```bash
 opengradient infer -m QmbUqS93oc4JTLMHwpVxsE39mhNxy6hpf6Py3r9oANr8aZ \
     --input '{"num_input1":[1.0, 2.0, 3.0], "num_input2":10}'
@@ -124,7 +141,9 @@ opengradient infer -m QmbUqS93oc4JTLMHwpVxsE39mhNxy6hpf6Py3r9oANr8aZ \
 
 1. **Off-chain Applications**: Use OpenGradient as a decentralized alternative to centralized AI providers like HuggingFace and OpenAI.
 
-2. **Model Development**: Manage models on the Model Hub and integrate directly into your development workflow.
+2. **Verifiable AI Execution**: Leverage TEE inference for cryptographically attested AI outputs, enabling trustless AI applications.
+
+3. **Model Development**: Manage models on the Model Hub and integrate directly into your development workflow.
 
 ## Documentation
 
@@ -140,4 +159,4 @@ If you use [Claude Code](https://claude.ai/code), copy [docs/CLAUDE_SDK_USERS.md
 
 - Run `opengradient --help` for CLI command reference
 - Visit our [documentation](https://docs.opengradient.ai/) for detailed guides
-- Join our [community](https://.opengradient.ai/) for support
+- Join our [community](https://opengradient.ai/) for support

{opengradient-0.5.8 → opengradient-0.5.10}/README.md

@@ -7,6 +7,7 @@ A Python SDK for decentralized model management and inference services on the Op
 - Model management and versioning
 - Decentralized model inference
 - Support for LLM inference with various models
+- **Trusted Execution Environment (TEE) inference** with cryptographic attestation
 - End-to-end verified AI execution
 - Command-line interface (CLI) for direct access
 
@@ -18,7 +19,6 @@ Browse and discover AI models on our [Model Hub](https://hub.opengradient.ai/).
 - Direct integration with the SDK
 
 ## Installation
-
 ```bash
 pip install opengradient
 ```
@@ -34,7 +34,6 @@ You'll need two accounts to use the SDK:
 - **OpenGradient account**: Use an existing Ethereum-compatible wallet or create a new one via SDK
 
 The easiest way to set up your accounts is through our configuration wizard:
-
 ```bash
 opengradient config init
 ```
@@ -45,7 +44,6 @@ This wizard will:
 - Direct you to our Test Faucet for devnet tokens
 
 ### 2. Initialize the SDK
-
 ```python
 import opengradient as og
 og.init(private_key="<private_key>", email="<email>", password="<password>")
@@ -54,8 +52,6 @@ og.init(private_key="<private_key>", email="<email>", password="<password>")
 ### 3. Basic Usage
 
 Browse available models on our [Model Hub](https://hub.opengradient.ai/) or create and upload your own:
-
-
 ```python
 # Create and upload a model
 og.create_model(
@@ -73,20 +69,41 @@ result = og.infer(
 )
 ```
 
-### 4. Examples
+### 4. TEE (Trusted Execution Environment) Inference
+
+OpenGradient supports secure, verifiable inference through TEE for leading LLM providers. Access models from OpenAI, Anthropic, Google, and xAI with cryptographic attestation:
+```python
+from opengradient import TEE_LLM
+
+# Use TEE-enabled models for verifiable AI execution
+result = og.infer(
+    model_cid=TEE_LLM.CLAUDE_3_7_SONNET,  # or any other TEE_LLM model
+    model_inputs={"prompt": "Your prompt here"},
+    inference_mode=og.InferenceMode.TEE
+)
+```
+
+**Available TEE Models:**
+The SDK includes models from multiple providers accessible via the `TEE_LLM` enum:
+- **OpenAI**: GPT-4.1, GPT-4o, o4-mini
+- **Anthropic**: Claude 3.7 Sonnet, Claude 3.5 Haiku, Claude 4.0 Sonnet
+- **Google**: Gemini 2.5 Flash, Gemini 2.5 Pro, and more
+- **xAI**: Grok 3 Beta, Grok 4.1 Fast, and other Grok variants
+
+For the complete list of available models, check the `TEE_LLM` enum in your IDE autocomplete or see the [API documentation](https://docs.opengradient.ai/).
+
+### 5. Examples
 
 See code examples under [examples](./examples).
 
 ## CLI Usage
 
 The SDK includes a command-line interface for quick operations. First, verify your configuration:
-
 ```bash
 opengradient config show
 ```
 
 Run a test inference:
-
 ```bash
 opengradient infer -m QmbUqS93oc4JTLMHwpVxsE39mhNxy6hpf6Py3r9oANr8aZ \
     --input '{"num_input1":[1.0, 2.0, 3.0], "num_input2":10}'
@@ -96,7 +113,9 @@ opengradient infer -m QmbUqS93oc4JTLMHwpVxsE39mhNxy6hpf6Py3r9oANr8aZ \
 
 1. **Off-chain Applications**: Use OpenGradient as a decentralized alternative to centralized AI providers like HuggingFace and OpenAI.
 
-2. **Model Development**: Manage models on the Model Hub and integrate directly into your development workflow.
+2. **Verifiable AI Execution**: Leverage TEE inference for cryptographically attested AI outputs, enabling trustless AI applications.
+
+3. **Model Development**: Manage models on the Model Hub and integrate directly into your development workflow.
 
 ## Documentation
 
@@ -112,4 +131,4 @@ If you use [Claude Code](https://claude.ai/code), copy [docs/CLAUDE_SDK_USERS.md
 
 - Run `opengradient --help` for CLI command reference
 - Visit our [documentation](https://docs.opengradient.ai/) for detailed guides
-- Join our [community](https://.opengradient.ai/) for support
+- Join our [community](https://opengradient.ai/) for support

{opengradient-0.5.8 → opengradient-0.5.10}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "opengradient"
-version = "0.5.8"
+version = "0.5.10"
 description = "Python SDK for OpenGradient decentralized model management & inference services"
 authors = [{name = "OpenGradient", email = "kyle@vannalabs.ai"}]
 readme = "README.md"
@@ -29,7 +29,7 @@ dependencies = [
     "langchain>=0.3.7",
     "openai>=1.58.1",
     "pydantic>=2.9.2",
-    "og-test-x402==0.0.1",
+    "og-test-x402==0.0.9",
 ]
 
 [project.scripts]

{opengradient-0.5.8 → opengradient-0.5.10}/src/opengradient/__init__.py

@@ -17,14 +17,19 @@ from .types import (
     InferenceResult,
     LlmInferenceMode,
     TextGenerationOutput,
+    TextGenerationStream,
     ModelOutput,
     ModelRepository,
     FileUploadResult,
     x402SettlementMode,
 )
+from .alpha import _AlphaNamespace
 
 from . import llm, alphasense
 
+# Module-level alpha namespace for workflow/ML execution features (Alpha Testnet only)
+alpha = _AlphaNamespace()
+
 _client = None
 
 
@@ -225,7 +230,8 @@ def llm_chat(
     tool_choice: Optional[str] = None,
     max_retries: Optional[int] = None,
     x402_settlement_mode: Optional[x402SettlementMode] = x402SettlementMode.SETTLE_BATCH,
-) -> TextGenerationOutput:
+    stream: Optional[bool] = False,
+) -> Union[TextGenerationOutput, TextGenerationStream]:
     """Have a chat conversation with an LLM.
 
     Args:
@@ -239,9 +245,10 @@ def llm_chat(
         tool_choice: Optional specific tool to use
         max_retries: Maximum number of retries for failed transactions
         x402_settlement_mode: Settlement modes for x402 payment protocol transactions (enum x402SettlementMode)
+        stream: Optional boolean to enable streaming
 
     Returns:
-        TextGenerationOutput
+        TextGenerationOutput or TextGenerationStream
 
     Raises:
         RuntimeError: If SDK is not initialized
@@ -258,7 +265,8 @@ def llm_chat(
         tools=tools,
         tool_choice=tool_choice,
         max_retries=max_retries,
-        x402_settlement_mode=x402_settlement_mode
+        x402_settlement_mode=x402_settlement_mode,
+        stream=stream,
     )
 
 
@@ -280,93 +288,6 @@ def list_files(model_name: str, version: str) -> List[Dict]:
     return _client.list_files(model_name, version)
 
 
-def new_workflow(
-    model_cid: str,
-    input_query: HistoricalInputQuery,
-    input_tensor_name: str,
-    scheduler_params: Optional[SchedulerParams] = None,
-) -> str:
-    """
-    Deploy a new workflow contract with the specified parameters.
-
-    This function deploys a new workflow contract and optionally registers it with
-    the scheduler for automated execution. If scheduler_params is not provided,
-    the workflow will be deployed without automated execution scheduling.
-
-    Args:
-        model_cid: IPFS CID of the model
-        input_query: HistoricalInputQuery containing query parameters
-        input_tensor_name: Name of the input tensor
-        scheduler_params: Optional scheduler configuration as SchedulerParams instance
-            If not provided, the workflow will be deployed without scheduling.
-
-    Returns:
-        str: Deployed contract address. If scheduler_params was provided, the workflow
-             will be automatically executed according to the specified schedule.
-    """
-    if _client is None:
-        raise RuntimeError("OpenGradient client not initialized. Call og.init(...) first.")
-
-    return _client.new_workflow(
-        model_cid=model_cid, input_query=input_query, input_tensor_name=input_tensor_name, scheduler_params=scheduler_params
-    )
-
-
-def read_workflow_result(contract_address: str) -> ModelOutput:
-    """
-    Reads the latest inference result from a deployed workflow contract.
-
-    This function retrieves the most recent output from a deployed model executor contract.
-    It includes built-in retry logic to handle blockchain state delays.
-
-    Args:
-        contract_address (str): Address of the deployed workflow contract
-
-    Returns:
-        Dict[str, Union[str, Dict]]: A dictionary containing:
-            - status: "success" or "error"
-            - result: The model output data if successful
-            - error: Error message if status is "error"
-
-    Raises:
-        RuntimeError: If OpenGradient client is not initialized
-    """
-    if _client is None:
-        raise RuntimeError("OpenGradient client not initialized. Call og.init() first.")
-    return _client.read_workflow_result(contract_address)
-
-
-def run_workflow(contract_address: str) -> ModelOutput:
-    """
-    Executes the workflow by calling run() on the contract to pull latest data and perform inference.
-
-    Args:
-        contract_address (str): Address of the deployed workflow contract
-
-    Returns:
-        Dict[str, Union[str, Dict]]: Status of the run operation
-    """
-    if _client is None:
-        raise RuntimeError("OpenGradient client not initialized. Call og.init() first.")
-    return _client.run_workflow(contract_address)
-
-
-def read_workflow_history(contract_address: str, num_results: int) -> List[ModelOutput]:
-    """
-    Gets historical inference results from a workflow contract.
-
-    Args:
-        contract_address (str): Address of the deployed workflow contract
-        num_results (int): Number of historical results to retrieve
-
-    Returns:
-        List[Dict]: List of historical inference results
-    """
-    if _client is None:
-        raise RuntimeError("OpenGradient client not initialized. Call og.init() first.")
-    return _client.read_workflow_history(contract_address, num_results)
-
-
 __all__ = [
     "list_files",
     "login",
@@ -379,10 +300,7 @@ __all__ = [
     "init",
     "LLM",
     "TEE_LLM",
-    "new_workflow",
-    "read_workflow_result",
-    "run_workflow",
-    "read_workflow_history",
+    "alpha",
     "InferenceMode",
     "LlmInferenceMode",
     "HistoricalInputQuery",