bump

Author: alizenhom

src/examples/cerebras_example/__init__.py

@@ -1,6 +1,11 @@
 class CerebrasRunner:
     def run(self):
-        from .main import completion_example, completion_with_tools_example
+        from .main import (
+            completion_example,
+            completion_with_tools_example,
+            openai_cerebras_example,
+        )
 
         completion_with_tools_example()
         completion_example()
+        openai_cerebras_example()

src/examples/cerebras_example/main.py

@@ -3,14 +3,38 @@
 from dotenv import load_dotenv
 import re
 import json
+from openai import OpenAI
+import os
 
 load_dotenv()
 
 langtrace.init()
-
+openai_client = OpenAI(
+    base_url="https://api.cerebras.ai/v1",
+    api_key=os.getenv("CEREBRAS_API_KEY"),
+)
 client = Cerebras()
 
 
+def openai_cerebras_example(stream=False):
+    completion = openai_client.chat.completions.create(
+        messages=[
+            {
+                "role": "user",
+                "content": "Why is fast inference important?",
+            }
+        ],
+        model="llama3.1-8b",
+        stream=stream,
+    )
+
+    if stream:
+        for chunk in completion:
+            print(chunk)
+    else:
+        return completion
+
+
 def completion_example(stream=False):
     completion = client.chat.completions.create(
         messages=[

src/langtrace_python_sdk/version.py

@@ -1 +1 @@
-__version__ = "3.3.0"
+__version__ = "3.3.1"