opengradient 0.3.14__tar.gz → 0.3.15__tar.gz

{opengradient-0.3.14 → opengradient-0.3.15}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: opengradient
-Version: 0.3.14
+Version: 0.3.15
 Summary: Python SDK for OpenGradient decentralized model management & inference services
 Project-URL: Homepage, https://opengradient.ai
 Author-email: OpenGradient <oliver@opengradient.ai>
@@ -183,6 +183,39 @@ og.infer(model_cid, model_inputs, inference_mode)
 ```
  - inference mode can be `VANILLA`, `ZKML`, or `TEE`
 
+### LLM Inference
+#### LLM Completion
+```python
+tx_hash, response = og.llm_completion(
+    model_cid='meta-llama/Meta-Llama-3-8B-Instruct',
+    prompt="Translate the following English text to French: 'Hello, how are you?'",
+    max_tokens=50,
+    temperature=0.0
+)
+``` 
+
+#### LLM Chat
+```python
+# create messages history
+messages = [
+    {
+        "role": "system",
+        "content": "You are a helpful AI assistant.",
+        "name": "HAL"
+    },
+    {
+        "role": "user",
+        "content": "Hello! How are you doing? Can you repeat my name?",
+    }]
+
+# run LLM inference
+tx_hash, finish_reason, message = og.llm_chat(
+  model_cid=og.LLM.MISTRAL_7B_INSTRUCT_V3,
+  messages=messages
+)
+```
+
+
 
 ## Using the CLI
 
@@ -223,8 +256,18 @@ opengradient infer QmbUqS93oc4JTLMHwpVxsE39mhNxy6hpf6Py3r9oANr8aZ VANILLA --inpu
 ```
 
 #### Run LLM Inference
+We also have explicit support for using LLMs through the completion and chat commands in the CLI.
+
+For example, you can run a competion inference with Llama-3 using the following command:
+
+``` bash
+opengradient completion --model "meta-llama/Meta-Llama-3-8B-Instruct" --prompt "hello who are you?" --max-tokens 50
+```
+
+Or you can use files instead of text input in order to simplify your command:
+
 ```bash
-opengradient llm --model "meta-llama/Meta-Llama-3-8B-Instruct" --prompt "Translate to French: Hello, how are you?" --max-tokens 50 --temperature 0.7
+opengradient chat --model "mistralai/Mistral-7B-Instruct-v0.3" --messages-file messages.json --tools-file tools.json --max-tokens 200
 ```
 
 For more information read the OpenGradient [documentation](https://docs.opengradient.ai/).

{opengradient-0.3.14 → opengradient-0.3.15}/README.md

@@ -51,6 +51,39 @@ og.infer(model_cid, model_inputs, inference_mode)
 ```
  - inference mode can be `VANILLA`, `ZKML`, or `TEE`
 
+### LLM Inference
+#### LLM Completion
+```python
+tx_hash, response = og.llm_completion(
+    model_cid='meta-llama/Meta-Llama-3-8B-Instruct',
+    prompt="Translate the following English text to French: 'Hello, how are you?'",
+    max_tokens=50,
+    temperature=0.0
+)
+``` 
+
+#### LLM Chat
+```python
+# create messages history
+messages = [
+    {
+        "role": "system",
+        "content": "You are a helpful AI assistant.",
+        "name": "HAL"
+    },
+    {
+        "role": "user",
+        "content": "Hello! How are you doing? Can you repeat my name?",
+    }]
+
+# run LLM inference
+tx_hash, finish_reason, message = og.llm_chat(
+  model_cid=og.LLM.MISTRAL_7B_INSTRUCT_V3,
+  messages=messages
+)
+```
+
+
 
 ## Using the CLI
 
@@ -91,8 +124,18 @@ opengradient infer QmbUqS93oc4JTLMHwpVxsE39mhNxy6hpf6Py3r9oANr8aZ VANILLA --inpu
 ```
 
 #### Run LLM Inference
+We also have explicit support for using LLMs through the completion and chat commands in the CLI.
+
+For example, you can run a competion inference with Llama-3 using the following command:
+
+``` bash
+opengradient completion --model "meta-llama/Meta-Llama-3-8B-Instruct" --prompt "hello who are you?" --max-tokens 50
+```
+
+Or you can use files instead of text input in order to simplify your command:
+
 ```bash
-opengradient llm --model "meta-llama/Meta-Llama-3-8B-Instruct" --prompt "Translate to French: Hello, how are you?" --max-tokens 50 --temperature 0.7
+opengradient chat --model "mistralai/Mistral-7B-Instruct-v0.3" --messages-file messages.json --tools-file tools.json --max-tokens 200
 ```
 
 For more information read the OpenGradient [documentation](https://docs.opengradient.ai/).

{opengradient-0.3.14 → opengradient-0.3.15}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "opengradient"
-version = "0.3.14"
+version = "0.3.15"
 description = "Python SDK for OpenGradient decentralized model management & inference services"
 authors = [{name = "OpenGradient", email = "oliver@opengradient.ai"}]
 license = {file = "LICENSE"}

{opengradient-0.3.14 → opengradient-0.3.15}/src/opengradient/__init__.py

@@ -5,7 +5,7 @@ from .defaults import DEFAULT_INFERENCE_CONTRACT_ADDRESS, DEFAULT_RPC_URL
 from .types import InferenceMode, LLM
 from . import llm
 
-__version__ = "0.3.14"
+__version__ = "0.3.15"
 
 _client = None